diff --git a/index.html b/index.html
index e67c5d2..b1d44a1 100644
--- a/index.html
+++ b/index.html
@@ -26,8 +26,8 @@
         <h1>Ofsted ILACS Summary</h1>
         <p>Summarised outcomes of published short and standard ILACS inspection reports by Ofsted, refreshed daily.<br/>An expanded version of the shown summary sheet, refreshed concurrently, is available to <a href="ofsted_childrens_services_overview.xlsx">download here</a> as an .xlsx file. <br/>Data summary is based on the original <i>ILACS Outcomes Summary</i> published periodically by the ADCS: <a href="https://adcs.org.uk/inspection/article/ilacs-outcomes-summary">https://adcs.org.uk/inspection/article/ilacs-outcomes-summary</a>. <a href="https://github.com/data-to-insight/ofsted-ilacs-scrape-tool/blob/main/README.md">Read the tool/project background details and future work.</a>.</p>
         <p>Disclaimer: This summary is built from scraped data direct from https://reports.ofsted.gov.uk/ published PDF inspection report files. As a result of the nuances|variance within the inspection report content or pdf encoding, we're noting some problematic data extraction for a small number of LAs*.<br/> *LA extraction issues: southend-on-sea, [overall, help_and_protection_grade,care_leavers_grade], nottingham,[inspection_framework, inspection_date], redcar and cleveland,[inspection_framework, inspection_date], knowsley,[inspector_name], stoke-on-trent,[inspector_name]<br/><a href="mailto:datatoinsight.enquiries@gmail.com?subject=Ofsted-Scrape-Tool">Feedback</a> on specific problems|inaccuracies|suggestions welcomed.*</p>
-        <p><b>Summary data last updated: 04 11 2024 09:42</b></p>
-        <p><b>LA inspections last updated: ['80571_thurrock - 29 october 2024']</b></p>
+        <p><b>Summary data last updated: 18 11 2024 10:58</b></p>
+        <p><b>LA inspections last updated: []</b></p>
         <div class="container">
     <table border="1" class="dataframe">
   <thead>
@@ -359,15 +359,15 @@ <h1>Ofsted ILACS Summary</h1>
       <td>GL</td>
       <td>E09000001</td>
       <td>London Corporation</td>
-      <td><a href="https://files.ofsted.gov.uk/v1/file/50149902">ofsted.gov.uk/50149902</a></td>
+      <td><a href="https://files.ofsted.gov.uk/v1/file/50260648">ofsted.gov.uk/50260648</a></td>
       <td>outstanding</td>
       <td>short</td>
-      <td>Matt Reed</td>
-      <td>02/03/2020</td>
+      <td>Christine Kennet</td>
+      <td>23/09/2024</td>
       <td>outstanding</td>
       <td>good</td>
       <td>outstanding</td>
-      <td>inspection_pre_dates_judgement</td>
+      <td>outstanding</td>
     </tr>
     <tr>
       <td>80451</td>
diff --git a/ofsted_childrens_services_overview.xlsx b/ofsted_childrens_services_overview.xlsx
index b60352b..fc88ac6 100644
Binary files a/ofsted_childrens_services_overview.xlsx and b/ofsted_childrens_services_overview.xlsx differ
diff --git a/output.log b/output.log
index ac510cf..e3f73d8 100644
--- a/output.log
+++ b/output.log
@@ -1,2703 +1,4106 @@
-2024-11-11 07:52:12,015 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:52:12,018 - built Dictionary<1216 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2696 corpus positions)
-2024-11-11 07:52:12,021 - Dictionary lifecycle event {'msg': "built Dictionary<1216 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2696 corpus positions)", 'datetime': '2024-11-11T07:52:12.018440', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:52:12,023 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:52:12,023 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:52:12,023 - using serial LDA version on this node
-2024-11-11 07:52:12,024 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:52:12,024 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:52:12,028 - -8.108 per-word bound, 275.9 perplexity estimate based on a held-out corpus of 1 documents with 2696 words
-2024-11-11 07:52:12,028 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:52:12,029 - topic #0 (0.333): 0.011*"’" + 0.006*"leaders" + 0.005*"within" + 0.005*"needs" + 0.005*"practice" + 0.005*"Barnsley" + 0.004*"senior" + 0.004*"11" + 0.004*"September" + 0.004*"response"
-2024-11-11 07:52:12,030 - topic #1 (0.333): 0.016*"’" + 0.007*"needs" + 0.007*"practice" + 0.006*"leaders" + 0.006*"within" + 0.005*"Barnsley" + 0.005*"response" + 0.005*"plans" + 0.004*"15" + 0.004*"11"
-2024-11-11 07:52:12,030 - topic #2 (0.333): 0.025*"’" + 0.010*"needs" + 0.008*"leaders" + 0.007*"within" + 0.007*"Barnsley" + 0.006*"practice" + 0.005*"plans" + 0.005*"quality" + 0.004*"2023" + 0.004*"senior"
-2024-11-11 07:52:12,030 - topic diff=0.810804, rho=1.000000
-2024-11-11 07:52:12,030 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1216, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:52:12.030363', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:52:12,032 - Failed to import jpype dependencies. Fallback to subprocess.
-2024-11-11 07:52:12,032 - No module named 'jpype'
-2024-11-11 07:52:14,331 - Inspection date 2023-09-11 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:52:14,331 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:52:14,332 - Inspection date 2023-09-11 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:52:14,332 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:52:14,332 - Inspection date 2023-09-11 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:52:14,332 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:52:14,332 - Inspection date 2023-09-11 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:52:14,332 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:52:14,332 - Inspection date 2023-09-11 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:52:14,332 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:52:14,333 - Inspection date 2023-09-11 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:52:14,333 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:52:22,555 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:52:22,557 - built Dictionary<1048 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2085 corpus positions)
-2024-11-11 07:52:22,557 - Dictionary lifecycle event {'msg': "built Dictionary<1048 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2085 corpus positions)", 'datetime': '2024-11-11T07:52:22.557961', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:52:22,558 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:52:22,559 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:52:22,559 - using serial LDA version on this node
-2024-11-11 07:52:22,559 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:52:22,559 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:52:22,562 - -8.022 per-word bound, 259.9 perplexity estimate based on a held-out corpus of 1 documents with 2085 words
-2024-11-11 07:52:22,563 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:52:22,564 - topic #0 (0.333): 0.016*"’" + 0.009*"well" + 0.007*"needs" + 0.006*"practice" + 0.006*"effective" + 0.005*"North" + 0.005*"leaders" + 0.005*"Somerset" + 0.005*"plans" + 0.005*"4"
-2024-11-11 07:52:22,564 - topic #1 (0.333): 0.015*"’" + 0.008*"well" + 0.005*"practice" + 0.005*"needs" + 0.005*"plans" + 0.005*"2022" + 0.004*"East" + 0.004*"Bath" + 0.004*"receive" + 0.004*"4"
-2024-11-11 07:52:22,564 - topic #2 (0.333): 0.022*"’" + 0.008*"well" + 0.006*"needs" + 0.006*"plans" + 0.005*"leaders" + 0.005*"practice" + 0.005*"protection" + 0.005*"receive" + 0.005*"including" + 0.005*"East"
-2024-11-11 07:52:22,564 - topic diff=0.746614, rho=1.000000
-2024-11-11 07:52:22,565 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1048, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:52:22.565021', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:52:23,351 - Inspection date 2022-02-28 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:52:23,351 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:52:23,352 - Inspection date 2022-02-28 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:52:23,352 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:52:23,352 - Inspection date 2022-02-28 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:52:23,352 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:52:23,352 - Inspection date 2022-02-28 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:52:23,352 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:52:23,352 - Inspection date 2022-02-28 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:52:23,352 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:52:23,353 - Inspection date 2022-02-28 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:52:23,353 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:52:34,831 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:52:34,834 - built Dictionary<1202 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2585 corpus positions)
-2024-11-11 07:52:34,834 - Dictionary lifecycle event {'msg': "built Dictionary<1202 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2585 corpus positions)", 'datetime': '2024-11-11T07:52:34.834323', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:52:34,835 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:52:34,835 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:52:34,835 - using serial LDA version on this node
-2024-11-11 07:52:34,836 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:52:34,836 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:52:34,840 - -8.114 per-word bound, 277.1 perplexity estimate based on a held-out corpus of 1 documents with 2585 words
-2024-11-11 07:52:34,840 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:52:34,841 - topic #0 (0.333): 0.019*"’" + 0.007*"well" + 0.006*"ensure" + 0.006*"needs" + 0.006*"good" + 0.006*"plans" + 0.006*"supported" + 0.005*"Borough" + 0.005*"Bedford" + 0.004*"need"
-2024-11-11 07:52:34,842 - topic #1 (0.333): 0.021*"’" + 0.006*"needs" + 0.006*"ensure" + 0.005*"Bedford" + 0.005*"education" + 0.005*"family" + 0.004*"well" + 0.004*"supported" + 0.004*"progress" + 0.004*"good"
-2024-11-11 07:52:34,842 - topic #2 (0.333): 0.016*"’" + 0.007*"needs" + 0.006*"ensure" + 0.006*"well" + 0.005*"progress" + 0.005*"plans" + 0.005*"Bedford" + 0.004*"education" + 0.004*"family" + 0.004*"receive"
-2024-11-11 07:52:34,842 - topic diff=0.789104, rho=1.000000
-2024-11-11 07:52:34,842 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1202, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:52:34.842463', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:52:35,809 - Inspection date 2021-11-15 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:52:35,809 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:52:35,810 - Inspection date 2021-11-15 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:52:35,810 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:52:35,810 - Inspection date 2021-11-15 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:52:35,810 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:52:35,810 - Inspection date 2021-11-15 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:52:35,810 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:52:35,811 - Inspection date 2021-11-15 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:52:35,811 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:52:35,811 - Inspection date 2021-11-15 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:52:35,811 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:52:46,940 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:52:46,942 - built Dictionary<1065 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2378 corpus positions)
-2024-11-11 07:52:46,942 - Dictionary lifecycle event {'msg': "built Dictionary<1065 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2378 corpus positions)", 'datetime': '2024-11-11T07:52:46.942799', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:52:46,943 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:52:46,944 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:52:46,944 - using serial LDA version on this node
-2024-11-11 07:52:46,944 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:52:46,944 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:52:46,947 - -7.970 per-word bound, 250.7 perplexity estimate based on a held-out corpus of 1 documents with 2378 words
-2024-11-11 07:52:46,948 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:52:46,949 - topic #0 (0.333): 0.012*"’" + 0.009*"needs" + 0.006*"effective" + 0.005*"well" + 0.004*"Birmingham" + 0.004*"progress" + 0.004*"trust" + 0.004*"2023" + 0.004*"impact" + 0.004*"3"
-2024-11-11 07:52:46,949 - topic #1 (0.333): 0.017*"’" + 0.008*"needs" + 0.007*"progress" + 0.006*"plans" + 0.006*"well" + 0.006*"trust" + 0.005*"3" + 0.005*"Birmingham" + 0.005*"effective" + 0.005*"timely"
-2024-11-11 07:52:46,949 - topic #2 (0.333): 0.016*"’" + 0.011*"needs" + 0.007*"well" + 0.007*"effective" + 0.007*"plans" + 0.006*"Birmingham" + 0.005*"trust" + 0.005*"appropriate" + 0.005*"risk" + 0.005*"20"
-2024-11-11 07:52:46,949 - topic diff=0.802266, rho=1.000000
-2024-11-11 07:52:46,949 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1065, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:52:46.949834', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:52:47,976 - Inspection date 2023-02-20 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:52:47,976 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:52:47,976 - Inspection date 2023-02-20 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:52:47,977 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:52:47,977 - Inspection date 2023-02-20 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:52:47,977 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:52:47,977 - Inspection date 2023-02-20 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:52:47,977 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:52:47,978 - Inspection date 2023-02-20 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:52:47,978 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:52:47,978 - Inspection date 2023-02-20 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:52:47,978 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:52:58,792 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:52:58,794 - built Dictionary<1055 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2353 corpus positions)
-2024-11-11 07:52:58,794 - Dictionary lifecycle event {'msg': "built Dictionary<1055 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2353 corpus positions)", 'datetime': '2024-11-11T07:52:58.794407', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:52:58,795 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:52:58,795 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:52:58,795 - using serial LDA version on this node
-2024-11-11 07:52:58,796 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:52:58,796 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:52:58,799 - -7.958 per-word bound, 248.6 perplexity estimate based on a held-out corpus of 1 documents with 2353 words
-2024-11-11 07:52:58,799 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:52:58,801 - topic #0 (0.333): 0.016*"’" + 0.008*"needs" + 0.007*"quality" + 0.007*"Darwen" + 0.006*"practice" + 0.005*"Blackburn" + 0.005*"February" + 0.005*"impact" + 0.005*"planning" + 0.005*"well"
-2024-11-11 07:52:58,801 - topic #1 (0.333): 0.015*"’" + 0.009*"practice" + 0.008*"needs" + 0.007*"impact" + 0.007*"Blackburn" + 0.007*"Darwen" + 0.006*"well" + 0.006*"quality" + 0.005*"effective" + 0.005*"plans"
-2024-11-11 07:52:58,801 - topic #2 (0.333): 0.009*"’" + 0.007*"quality" + 0.007*"Blackburn" + 0.007*"well" + 0.006*"practice" + 0.005*"impact" + 0.005*"Darwen" + 0.005*"means" + 0.004*"4" + 0.004*"receive"
-2024-11-11 07:52:58,801 - topic diff=0.812320, rho=1.000000
-2024-11-11 07:52:58,801 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1055, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:52:58.801674', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:52:59,780 - Inspection date 2022-01-24 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:52:59,780 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:52:59,780 - Inspection date 2022-01-24 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:52:59,780 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:52:59,781 - Inspection date 2022-01-24 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:52:59,781 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:52:59,781 - Inspection date 2022-01-24 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:52:59,781 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:52:59,781 - Inspection date 2022-01-24 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:52:59,781 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:52:59,781 - Inspection date 2022-01-24 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:52:59,781 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:09,937 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:53:09,939 - built Dictionary<1037 unique tokens: ['0', '0161', '030', '0300', '1']...> from 1 documents (total 2392 corpus positions)
-2024-11-11 07:53:09,939 - Dictionary lifecycle event {'msg': "built Dictionary<1037 unique tokens: ['0', '0161', '030', '0300', '1']...> from 1 documents (total 2392 corpus positions)", 'datetime': '2024-11-11T07:53:09.939448', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:53:09,940 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:53:09,940 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:53:09,940 - using serial LDA version on this node
-2024-11-11 07:53:09,941 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:53:09,941 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:53:09,944 - -7.926 per-word bound, 243.2 perplexity estimate based on a held-out corpus of 1 documents with 2392 words
-2024-11-11 07:53:09,944 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:53:09,946 - topic #0 (0.333): 0.016*"’" + 0.009*"needs" + 0.008*"well" + 0.005*"16" + 0.004*"supported" + 0.004*"effective" + 0.004*"practice" + 0.004*"Blackpool" + 0.004*"team" + 0.004*"experiences"
-2024-11-11 07:53:09,946 - topic #1 (0.333): 0.019*"’" + 0.012*"needs" + 0.010*"well" + 0.010*"Blackpool" + 0.006*"effective" + 0.005*"practice" + 0.005*"progress" + 0.005*"experiences" + 0.005*"supported" + 0.005*"good"
-2024-11-11 07:53:09,946 - topic #2 (0.333): 0.014*"’" + 0.009*"needs" + 0.008*"well" + 0.007*"plans" + 0.007*"Blackpool" + 0.006*"effective" + 0.005*"practice" + 0.005*"5" + 0.005*"16" + 0.005*"quality"
-2024-11-11 07:53:09,946 - topic diff=0.839106, rho=1.000000
-2024-11-11 07:53:09,946 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1037, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:53:09.946745', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:53:10,862 - Inspection date 2022-12-05 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:53:10,862 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:10,862 - Inspection date 2022-12-05 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:53:10,863 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:10,863 - Inspection date 2022-12-05 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:53:10,863 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:10,863 - Inspection date 2022-12-05 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:53:10,863 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:10,863 - Inspection date 2022-12-05 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:53:10,863 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:10,863 - Inspection date 2022-12-05 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:53:10,864 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:21,279 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:53:21,281 - built Dictionary<972 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2055 corpus positions)
-2024-11-11 07:53:21,281 - Dictionary lifecycle event {'msg': "built Dictionary<972 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2055 corpus positions)", 'datetime': '2024-11-11T07:53:21.281854', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:53:21,282 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:53:21,282 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:53:21,283 - using serial LDA version on this node
-2024-11-11 07:53:21,283 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:53:21,283 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:53:21,286 - -7.912 per-word bound, 240.8 perplexity estimate based on a held-out corpus of 1 documents with 2055 words
-2024-11-11 07:53:21,286 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:53:21,287 - topic #0 (0.333): 0.021*"’" + 0.009*"plans" + 0.009*"needs" + 0.008*"well" + 0.006*"Bolton" + 0.006*"supported" + 0.005*"15" + 0.005*"need" + 0.005*"strong" + 0.005*"timely"
-2024-11-11 07:53:21,288 - topic #1 (0.333): 0.014*"’" + 0.008*"needs" + 0.006*"well" + 0.006*"Bolton" + 0.005*"plans" + 0.004*"strong" + 0.004*"planning" + 0.004*"timely" + 0.004*"experiences" + 0.004*"need"
-2024-11-11 07:53:21,288 - topic #2 (0.333): 0.020*"’" + 0.010*"needs" + 0.010*"Bolton" + 0.009*"well" + 0.007*"plans" + 0.006*"supported" + 0.006*"11" + 0.006*"planning" + 0.005*"effective" + 0.005*"need"
-2024-11-11 07:53:21,288 - topic diff=0.784516, rho=1.000000
-2024-11-11 07:53:21,288 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=972, num_topics=3, decay=0.5, chunksize=2000> in 0.00s', 'datetime': '2024-11-11T07:53:21.288400', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:53:22,314 - Inspection date 2023-09-11 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:53:22,314 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:22,315 - Inspection date 2023-09-11 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:53:22,315 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:22,315 - Inspection date 2023-09-11 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:53:22,315 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:22,315 - Inspection date 2023-09-11 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:53:22,315 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:22,315 - Inspection date 2023-09-11 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:53:22,315 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:22,315 - Inspection date 2023-09-11 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:53:22,316 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:30,982 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:53:30,984 - built Dictionary<1035 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2004 corpus positions)
-2024-11-11 07:53:30,985 - Dictionary lifecycle event {'msg': "built Dictionary<1035 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2004 corpus positions)", 'datetime': '2024-11-11T07:53:30.984973', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:53:30,985 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:53:30,986 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:53:30,986 - using serial LDA version on this node
-2024-11-11 07:53:30,986 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:53:30,986 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:53:30,992 - -8.029 per-word bound, 261.1 perplexity estimate based on a held-out corpus of 1 documents with 2004 words
-2024-11-11 07:53:30,992 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:53:30,994 - topic #0 (0.333): 0.018*"’" + 0.006*"quality" + 0.006*"practice" + 0.005*"impact" + 0.005*"progress" + 0.005*"Poole" + 0.005*"However" + 0.005*"risk" + 0.004*"well" + 0.004*"number"
-2024-11-11 07:53:30,994 - topic #1 (0.333): 0.014*"’" + 0.005*"practice" + 0.005*"quality" + 0.005*"progress" + 0.004*"Bournemouth" + 0.004*"However" + 0.004*"Poole" + 0.004*"6" + 0.004*"time" + 0.004*"Christchurch"
-2024-11-11 07:53:30,995 - topic #2 (0.333): 0.021*"’" + 0.006*"quality" + 0.006*"practice" + 0.005*"17" + 0.005*"progress" + 0.005*"Christchurch" + 0.005*"6" + 0.005*"time" + 0.005*"Bournemouth" + 0.005*"risk"
-2024-11-11 07:53:30,995 - topic diff=0.754641, rho=1.000000
-2024-11-11 07:53:30,995 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1035, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:53:30.995272', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:53:33,063 - Inspection date 2021-12-06 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:53:33,064 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:33,064 - Inspection date 2021-12-06 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:53:33,064 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:33,064 - Inspection date 2021-12-06 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:53:33,064 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:33,065 - Inspection date 2021-12-06 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:53:33,065 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:33,065 - Inspection date 2021-12-06 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:53:33,065 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:33,065 - Inspection date 2021-12-06 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:53:33,065 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:41,588 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:53:41,592 - built Dictionary<900 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1846 corpus positions)
-2024-11-11 07:53:41,592 - Dictionary lifecycle event {'msg': "built Dictionary<900 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1846 corpus positions)", 'datetime': '2024-11-11T07:53:41.592375', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:53:41,602 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:53:41,602 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:53:41,602 - using serial LDA version on this node
-2024-11-11 07:53:41,603 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:53:41,603 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:53:41,608 - -7.854 per-word bound, 231.4 perplexity estimate based on a held-out corpus of 1 documents with 1846 words
-2024-11-11 07:53:41,608 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:53:41,610 - topic #0 (0.333): 0.017*"’" + 0.007*"Bracknell" + 0.007*"Forest" + 0.006*"good" + 0.006*"plans" + 0.006*"needs" + 0.006*"quality" + 0.006*"well" + 0.005*"need" + 0.005*"impact"
-2024-11-11 07:53:41,611 - topic #1 (0.333): 0.019*"’" + 0.008*"risk" + 0.008*"needs" + 0.007*"Forest" + 0.007*"Bracknell" + 0.007*"quality" + 0.007*"effective" + 0.007*"good" + 0.006*"progress" + 0.006*"provided"
-2024-11-11 07:53:41,611 - topic #2 (0.333): 0.009*"’" + 0.005*"needs" + 0.004*"Forest" + 0.004*"impact" + 0.004*"17" + 0.004*"Bracknell" + 0.004*"provided" + 0.004*"progress" + 0.004*"positive" + 0.004*"risk"
-2024-11-11 07:53:41,611 - topic diff=0.795570, rho=1.000000
-2024-11-11 07:53:41,612 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=900, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:53:41.611989', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:53:42,951 - Inspection date 2022-06-13 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:53:42,951 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:42,951 - Inspection date 2022-06-13 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:53:42,951 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:42,952 - Inspection date 2022-06-13 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:53:42,952 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:42,952 - Inspection date 2022-06-13 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:53:42,952 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:42,952 - Inspection date 2022-06-13 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:53:42,952 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:42,952 - Inspection date 2022-06-13 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:53:42,952 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:52,531 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:53:52,534 - built Dictionary<1124 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2249 corpus positions)
-2024-11-11 07:53:52,534 - Dictionary lifecycle event {'msg': "built Dictionary<1124 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2249 corpus positions)", 'datetime': '2024-11-11T07:53:52.534180', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:53:52,535 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:53:52,535 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:53:52,535 - using serial LDA version on this node
-2024-11-11 07:53:52,535 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:53:52,535 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:53:52,539 - -8.091 per-word bound, 272.7 perplexity estimate based on a held-out corpus of 1 documents with 2249 words
-2024-11-11 07:53:52,539 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:53:52,540 - topic #0 (0.333): 0.020*"’" + 0.008*"well" + 0.007*"needs" + 0.007*"practice" + 0.007*"Brighton" + 0.006*"Hove" + 0.006*"relationships" + 0.005*"experiences" + 0.005*"progress" + 0.005*"11"
-2024-11-11 07:53:52,541 - topic #1 (0.333): 0.014*"’" + 0.007*"needs" + 0.006*"practice" + 0.005*"well" + 0.005*"progress" + 0.005*"experiences" + 0.004*"Brighton" + 0.004*"relationships" + 0.004*"receive" + 0.004*"Hove"
-2024-11-11 07:53:52,541 - topic #2 (0.333): 0.014*"’" + 0.008*"Hove" + 0.008*"well" + 0.007*"Brighton" + 0.006*"needs" + 0.005*"progress" + 0.005*"experiences" + 0.005*"practice" + 0.005*"relationships" + 0.005*"2024"
-2024-11-11 07:53:52,541 - topic diff=0.751308, rho=1.000000
-2024-11-11 07:53:52,541 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1124, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:53:52.541355', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:53:53,418 - Inspection date None / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:53:53,418 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:53,419 - Inspection date None / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:53:53,419 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:53,419 - Inspection date None / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:53:53,419 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:53,419 - Inspection date None / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:53:53,419 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:53,419 - Inspection date None / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:53:53,419 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:53:53,419 - Inspection date None / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:53:53,419 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:06,462 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:54:06,464 - built Dictionary<1151 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2647 corpus positions)
-2024-11-11 07:54:06,464 - Dictionary lifecycle event {'msg': "built Dictionary<1151 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2647 corpus positions)", 'datetime': '2024-11-11T07:54:06.464570', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:54:06,465 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:54:06,465 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:54:06,466 - using serial LDA version on this node
-2024-11-11 07:54:06,466 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:54:06,466 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:54:06,470 - -8.027 per-word bound, 260.9 perplexity estimate based on a held-out corpus of 1 documents with 2647 words
-2024-11-11 07:54:06,470 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:54:06,471 - topic #0 (0.333): 0.012*"’" + 0.006*"well" + 0.006*"needs" + 0.005*"good" + 0.005*"Bristol" + 0.005*"health" + 0.005*"16" + 0.004*"plans" + 0.004*"always" + 0.004*"need"
-2024-11-11 07:54:06,471 - topic #1 (0.333): 0.023*"’" + 0.010*"needs" + 0.009*"well" + 0.009*"good" + 0.009*"Bristol" + 0.006*"leaders" + 0.006*"progress" + 0.005*"27" + 0.005*"need" + 0.005*"health"
-2024-11-11 07:54:06,471 - topic #2 (0.333): 0.019*"’" + 0.010*"well" + 0.008*"good" + 0.007*"Bristol" + 0.006*"needs" + 0.005*"progress" + 0.005*"health" + 0.005*"plans" + 0.005*"timely" + 0.005*"need"
-2024-11-11 07:54:06,471 - topic diff=0.829442, rho=1.000000
-2024-11-11 07:54:06,471 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1151, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:54:06.471914', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:54:07,264 - Inspection date 2023-01-16 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:54:07,265 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:07,265 - Inspection date 2023-01-16 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:54:07,265 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:07,265 - Inspection date 2023-01-16 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:54:07,265 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:07,265 - Inspection date 2023-01-16 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:54:07,266 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:07,266 - Inspection date 2023-01-16 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:54:07,266 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:07,266 - Inspection date 2023-01-16 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:54:07,266 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:17,881 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:54:17,884 - built Dictionary<1263 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2404 corpus positions)
-2024-11-11 07:54:17,884 - Dictionary lifecycle event {'msg': "built Dictionary<1263 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2404 corpus positions)", 'datetime': '2024-11-11T07:54:17.884699', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:54:17,885 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:54:17,886 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:54:17,886 - using serial LDA version on this node
-2024-11-11 07:54:17,886 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:54:17,886 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:54:17,890 - -8.243 per-word bound, 302.9 perplexity estimate based on a held-out corpus of 1 documents with 2404 words
-2024-11-11 07:54:17,890 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:54:17,892 - topic #0 (0.333): 0.013*"’" + 0.005*"plans" + 0.004*"17" + 0.004*"practice" + 0.004*"6" + 0.004*"many" + 0.004*"number" + 0.004*"teams" + 0.004*"Buckinghamshire" + 0.004*"2021"
-2024-11-11 07:54:17,892 - topic #1 (0.333): 0.012*"’" + 0.005*"number" + 0.004*"plans" + 0.004*"2021" + 0.004*"Buckinghamshire" + 0.004*"17" + 0.004*"December" + 0.004*"protection" + 0.004*"progress" + 0.004*"6"
-2024-11-11 07:54:17,892 - topic #2 (0.333): 0.015*"’" + 0.005*"plans" + 0.005*"number" + 0.005*"Buckinghamshire" + 0.005*"protection" + 0.004*"17" + 0.004*"many" + 0.004*"practice" + 0.004*"6" + 0.004*"well"
-2024-11-11 07:54:17,892 - topic diff=0.724649, rho=1.000000
-2024-11-11 07:54:17,892 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1263, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:54:17.892696', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:54:18,856 - Inspection date 2021-12-06 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:54:18,856 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:18,856 - Inspection date 2021-12-06 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:54:18,857 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:18,857 - Inspection date 2021-12-06 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:54:18,857 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:18,857 - Inspection date 2021-12-06 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:54:18,857 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:18,857 - Inspection date 2021-12-06 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:54:18,857 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:18,857 - Inspection date 2021-12-06 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:54:18,857 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:29,437 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:54:29,439 - built Dictionary<1076 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2427 corpus positions)
-2024-11-11 07:54:29,439 - Dictionary lifecycle event {'msg': "built Dictionary<1076 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2427 corpus positions)", 'datetime': '2024-11-11T07:54:29.439770', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:54:29,440 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:54:29,440 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:54:29,441 - using serial LDA version on this node
-2024-11-11 07:54:29,441 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:54:29,441 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:54:29,444 - -7.976 per-word bound, 251.7 perplexity estimate based on a held-out corpus of 1 documents with 2427 words
-2024-11-11 07:54:29,445 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:54:29,446 - topic #0 (0.333): 0.007*"’" + 0.006*"2021" + 0.006*"needs" + 0.006*"practice" + 0.005*"protection" + 0.005*"Bury" + 0.005*"impact" + 0.005*"November" + 0.005*"team" + 0.005*"need"
-2024-11-11 07:54:29,446 - topic #1 (0.333): 0.016*"’" + 0.008*"protection" + 0.007*"2021" + 0.006*"team" + 0.006*"needs" + 0.006*"practice" + 0.006*"risk" + 0.005*"impact" + 0.005*"quality" + 0.005*"Bury"
-2024-11-11 07:54:29,446 - topic #2 (0.333): 0.009*"’" + 0.007*"needs" + 0.006*"2021" + 0.005*"need" + 0.005*"protection" + 0.005*"team" + 0.004*"practice" + 0.004*"5" + 0.004*"lack" + 0.004*"impact"
-2024-11-11 07:54:29,446 - topic diff=0.807360, rho=1.000000
-2024-11-11 07:54:29,446 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1076, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:54:29.446898', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:54:30,315 - Inspection date 2021-10-25 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:54:30,315 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:30,315 - Inspection date 2021-10-25 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:54:30,316 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:30,316 - Inspection date 2021-10-25 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:54:30,316 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:30,316 - Inspection date 2021-10-25 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:54:30,316 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:30,316 - Inspection date 2021-10-25 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:54:30,316 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:30,316 - Inspection date 2021-10-25 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:54:30,317 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:40,731 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:54:40,734 - built Dictionary<1109 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2389 corpus positions)
-2024-11-11 07:54:40,734 - Dictionary lifecycle event {'msg': "built Dictionary<1109 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2389 corpus positions)", 'datetime': '2024-11-11T07:54:40.734349', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:54:40,735 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:54:40,735 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:54:40,735 - using serial LDA version on this node
-2024-11-11 07:54:40,736 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:54:40,736 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:54:40,739 - -8.029 per-word bound, 261.3 perplexity estimate based on a held-out corpus of 1 documents with 2389 words
-2024-11-11 07:54:40,739 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:54:40,741 - topic #0 (0.333): 0.022*"’" + 0.011*"needs" + 0.009*"Calderdale" + 0.006*"plans" + 0.006*"well" + 0.006*"risk" + 0.006*"progress" + 0.005*"ensure" + 0.005*"experiences" + 0.005*"parents"
-2024-11-11 07:54:40,741 - topic #1 (0.333): 0.020*"’" + 0.008*"needs" + 0.007*"Calderdale" + 0.006*"progress" + 0.006*"well" + 0.005*"parents" + 0.005*"ensure" + 0.005*"plans" + 0.004*"need" + 0.004*"information"
-2024-11-11 07:54:40,741 - topic #2 (0.333): 0.019*"’" + 0.010*"needs" + 0.009*"Calderdale" + 0.006*"plans" + 0.006*"well" + 0.006*"ensure" + 0.005*"information" + 0.004*"PAs" + 0.004*"progress" + 0.004*"risks"
-2024-11-11 07:54:40,741 - topic diff=0.782917, rho=1.000000
-2024-11-11 07:54:40,741 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1109, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:54:40.741601', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:54:41,555 - Inspection date 2024-02-19 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:54:41,555 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:41,556 - Inspection date 2024-02-19 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:54:41,556 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:41,556 - Inspection date 2024-02-19 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:54:41,556 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:41,556 - Inspection date 2024-02-19 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:54:41,556 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:41,556 - Inspection date 2024-02-19 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:54:41,556 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:41,557 - Inspection date 2024-02-19 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:54:41,557 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:53,207 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:54:53,210 - built Dictionary<1082 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2339 corpus positions)
-2024-11-11 07:54:53,210 - Dictionary lifecycle event {'msg': "built Dictionary<1082 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2339 corpus positions)", 'datetime': '2024-11-11T07:54:53.210208', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:54:53,211 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:54:53,211 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:54:53,211 - using serial LDA version on this node
-2024-11-11 07:54:53,211 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:54:53,212 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:54:53,215 - -8.001 per-word bound, 256.1 perplexity estimate based on a held-out corpus of 1 documents with 2339 words
-2024-11-11 07:54:53,215 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:54:53,216 - topic #0 (0.333): 0.012*"’" + 0.006*"Cambridgeshire" + 0.006*"leaders" + 0.006*"needs" + 0.005*"good" + 0.005*"well" + 0.005*"2024" + 0.005*"quality" + 0.005*"clear" + 0.004*"leadership"
-2024-11-11 07:54:53,216 - topic #1 (0.333): 0.021*"’" + 0.008*"needs" + 0.007*"leaders" + 0.006*"Cambridgeshire" + 0.005*"good" + 0.005*"well" + 0.005*"experiences" + 0.004*"practice" + 0.004*"4" + 0.004*"However"
-2024-11-11 07:54:53,217 - topic #2 (0.333): 0.016*"’" + 0.007*"Cambridgeshire" + 0.006*"needs" + 0.006*"good" + 0.005*"effective" + 0.005*"leaders" + 0.005*"quality" + 0.005*"response" + 0.005*"4" + 0.004*"practice"
-2024-11-11 07:54:53,217 - topic diff=0.783222, rho=1.000000
-2024-11-11 07:54:53,217 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1082, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:54:53.217352', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:54:54,270 - Inspection date 2024-03-04 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:54:54,271 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:54,271 - Inspection date 2024-03-04 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:54:54,271 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:54,271 - Inspection date 2024-03-04 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:54:54,271 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:54,271 - Inspection date 2024-03-04 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:54:54,271 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:54,272 - Inspection date 2024-03-04 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:54:54,272 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:54:54,272 - Inspection date 2024-03-04 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:54:54,272 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:03,634 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:55:03,636 - built Dictionary<1030 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2199 corpus positions)
-2024-11-11 07:55:03,636 - Dictionary lifecycle event {'msg': "built Dictionary<1030 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2199 corpus positions)", 'datetime': '2024-11-11T07:55:03.636627', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:55:03,637 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:55:03,637 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:55:03,637 - using serial LDA version on this node
-2024-11-11 07:55:03,638 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:55:03,638 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:55:03,641 - -7.963 per-word bound, 249.6 perplexity estimate based on a held-out corpus of 1 documents with 2199 words
-2024-11-11 07:55:03,641 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:55:03,643 - topic #0 (0.333): 0.012*"’" + 0.009*"well" + 0.007*"carers" + 0.007*"needs" + 0.006*"plans" + 0.005*"Bedfordshire" + 0.005*"good" + 0.005*"need" + 0.005*"Central" + 0.004*"progress"
-2024-11-11 07:55:03,643 - topic #1 (0.333): 0.022*"’" + 0.010*"well" + 0.008*"needs" + 0.007*"good" + 0.007*"need" + 0.006*"progress" + 0.006*"plans" + 0.006*"carers" + 0.005*"effective" + 0.005*"Central"
-2024-11-11 07:55:03,643 - topic #2 (0.333): 0.010*"’" + 0.007*"need" + 0.007*"needs" + 0.006*"well" + 0.005*"progress" + 0.005*"carers" + 0.005*"protection" + 0.005*"good" + 0.005*"plans" + 0.004*"Bedfordshire"
-2024-11-11 07:55:03,643 - topic diff=0.793270, rho=1.000000
-2024-11-11 07:55:03,643 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1030, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:55:03.643765', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:55:04,564 - Inspection date 2022-01-17 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:55:04,564 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:04,564 - Inspection date 2022-01-17 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:55:04,564 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:04,565 - Inspection date 2022-01-17 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:55:04,565 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:04,565 - Inspection date 2022-01-17 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:55:04,565 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:04,565 - Inspection date 2022-01-17 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:55:04,565 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:04,565 - Inspection date 2022-01-17 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:55:04,565 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:14,976 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:55:14,978 - built Dictionary<1051 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2272 corpus positions)
-2024-11-11 07:55:14,978 - Dictionary lifecycle event {'msg': "built Dictionary<1051 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2272 corpus positions)", 'datetime': '2024-11-11T07:55:14.978932', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:55:14,980 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:55:14,980 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:55:14,980 - using serial LDA version on this node
-2024-11-11 07:55:14,980 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:55:14,980 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:55:14,983 - -7.973 per-word bound, 251.2 perplexity estimate based on a held-out corpus of 1 documents with 2272 words
-2024-11-11 07:55:14,984 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:55:14,985 - topic #0 (0.333): 0.011*"’" + 0.008*"plans" + 0.007*"2024" + 0.007*"well" + 0.006*"East" + 0.006*"needs" + 0.006*"practice" + 0.006*"quality" + 0.005*"Cheshire" + 0.005*"effective"
-2024-11-11 07:55:14,985 - topic #1 (0.333): 0.010*"’" + 0.007*"2024" + 0.006*"practice" + 0.006*"needs" + 0.006*"plans" + 0.006*"well" + 0.006*"quality" + 0.005*"leaders" + 0.005*"East" + 0.005*"effective"
-2024-11-11 07:55:14,985 - topic #2 (0.333): 0.015*"’" + 0.009*"needs" + 0.008*"2024" + 0.007*"practice" + 0.006*"well" + 0.006*"plans" + 0.006*"Cheshire" + 0.006*"quality" + 0.006*"access" + 0.005*"East"
-2024-11-11 07:55:14,985 - topic diff=0.780988, rho=1.000000
-2024-11-11 07:55:14,985 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1051, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:55:14.985777', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:55:15,877 - Inspection date 2024-02-26 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:55:15,877 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:15,877 - Inspection date 2024-02-26 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:55:15,878 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:15,878 - Inspection date 2024-02-26 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:55:15,878 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:15,878 - Inspection date 2024-02-26 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:55:15,878 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:15,878 - Inspection date 2024-02-26 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:55:15,878 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:15,878 - Inspection date 2024-02-26 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:55:15,878 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:25,860 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:55:25,862 - built Dictionary<1010 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2203 corpus positions)
-2024-11-11 07:55:25,862 - Dictionary lifecycle event {'msg': "built Dictionary<1010 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2203 corpus positions)", 'datetime': '2024-11-11T07:55:25.862802', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:55:25,863 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:55:25,863 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:55:25,864 - using serial LDA version on this node
-2024-11-11 07:55:25,864 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:55:25,864 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:55:25,867 - -7.932 per-word bound, 244.1 perplexity estimate based on a held-out corpus of 1 documents with 2203 words
-2024-11-11 07:55:25,867 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:55:25,869 - topic #0 (0.333): 0.015*"’" + 0.005*"well" + 0.005*"plans" + 0.005*"progress" + 0.004*"impact" + 0.004*"needs" + 0.004*"Cheshire" + 0.004*"access" + 0.004*"15" + 0.004*"information"
-2024-11-11 07:55:25,869 - topic #1 (0.333): 0.017*"’" + 0.007*"needs" + 0.006*"well" + 0.005*"impact" + 0.005*"plans" + 0.005*"West" + 0.005*"2024" + 0.005*"good" + 0.005*"meetings" + 0.005*"Cheshire"
-2024-11-11 07:55:25,869 - topic #2 (0.333): 0.014*"’" + 0.006*"needs" + 0.006*"well" + 0.006*"progress" + 0.006*"plans" + 0.005*"good" + 0.005*"access" + 0.005*"Chester" + 0.005*"19" + 0.005*"15"
-2024-11-11 07:55:25,869 - topic diff=0.790877, rho=1.000000
-2024-11-11 07:55:25,869 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1010, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:55:25.869546', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:55:26,850 - Inspection date 2024-07-15 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:55:26,851 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:26,851 - Inspection date 2024-07-15 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:55:26,851 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:26,851 - Inspection date 2024-07-15 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:55:26,852 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:26,852 - Inspection date 2024-07-15 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:55:26,852 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:26,852 - Inspection date 2024-07-15 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:55:26,852 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:26,852 - Inspection date 2024-07-15 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:55:26,852 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:37,283 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:55:37,285 - built Dictionary<1164 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2639 corpus positions)
-2024-11-11 07:55:37,285 - Dictionary lifecycle event {'msg': "built Dictionary<1164 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2639 corpus positions)", 'datetime': '2024-11-11T07:55:37.285791', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:55:37,286 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:55:37,287 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:55:37,287 - using serial LDA version on this node
-2024-11-11 07:55:37,287 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:55:37,287 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:55:37,291 - -8.047 per-word bound, 264.6 perplexity estimate based on a held-out corpus of 1 documents with 2639 words
-2024-11-11 07:55:37,291 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:55:37,292 - topic #0 (0.333): 0.024*"’" + 0.005*"progress" + 0.005*"Bradford" + 0.005*"plans" + 0.004*"quality" + 0.004*"2" + 0.004*"practice" + 0.004*"worker" + 0.004*"impact" + 0.004*"December"
-2024-11-11 07:55:37,292 - topic #1 (0.333): 0.022*"’" + 0.009*"plans" + 0.006*"needs" + 0.005*"Council" + 0.005*"need" + 0.005*"Bradford" + 0.005*"risk" + 0.005*"2" + 0.004*"Borough" + 0.004*"◼"
-2024-11-11 07:55:37,292 - topic #2 (0.333): 0.014*"’" + 0.005*"plans" + 0.005*"Bradford" + 0.005*"senior" + 0.005*"impact" + 0.005*"2" + 0.005*"need" + 0.004*"risk" + 0.004*"21" + 0.004*"quality"
-2024-11-11 07:55:37,293 - topic diff=0.810809, rho=1.000000
-2024-11-11 07:55:37,293 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1164, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:55:37.293151', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:55:38,255 - Inspection date 2022-11-21 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:55:38,255 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:38,255 - Inspection date 2022-11-21 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:55:38,255 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:38,256 - Inspection date 2022-11-21 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:55:38,256 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:38,256 - Inspection date 2022-11-21 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:55:38,256 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:38,256 - Inspection date 2022-11-21 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:55:38,256 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:38,256 - Inspection date 2022-11-21 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:55:38,256 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:48,196 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:55:48,198 - built Dictionary<1105 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2273 corpus positions)
-2024-11-11 07:55:48,198 - Dictionary lifecycle event {'msg': "built Dictionary<1105 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2273 corpus positions)", 'datetime': '2024-11-11T07:55:48.198513', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:55:48,199 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:55:48,199 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:55:48,199 - using serial LDA version on this node
-2024-11-11 07:55:48,200 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:55:48,200 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:55:48,203 - -8.055 per-word bound, 265.9 perplexity estimate based on a held-out corpus of 1 documents with 2273 words
-2024-11-11 07:55:48,203 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:55:48,205 - topic #0 (0.333): 0.025*"’" + 0.009*"City" + 0.009*"London" + 0.009*"well" + 0.008*"needs" + 0.006*"progress" + 0.005*"plans" + 0.005*"practice" + 0.004*"strong" + 0.004*"2024"
-2024-11-11 07:55:48,205 - topic #1 (0.333): 0.014*"’" + 0.006*"City" + 0.005*"well" + 0.005*"London" + 0.005*"needs" + 0.005*"plans" + 0.004*"experiences" + 0.004*"progress" + 0.004*"27" + 0.004*"practice"
-2024-11-11 07:55:48,205 - topic #2 (0.333): 0.025*"’" + 0.012*"City" + 0.008*"well" + 0.007*"London" + 0.006*"needs" + 0.006*"practice" + 0.005*"plans" + 0.005*"23" + 0.005*"progress" + 0.004*"strong"
-2024-11-11 07:55:48,205 - topic diff=0.765660, rho=1.000000
-2024-11-11 07:55:48,205 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1105, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:55:48.205523', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:55:49,152 - Inspection date 2024-09-23 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:55:49,153 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:49,153 - Inspection date 2024-09-23 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:55:49,153 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:49,153 - Inspection date 2024-09-23 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:55:49,153 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:49,153 - Inspection date 2024-09-23 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:55:49,154 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:49,154 - Inspection date 2024-09-23 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:55:49,154 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:49,154 - Inspection date 2024-09-23 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:55:49,154 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:58,856 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:55:58,858 - built Dictionary<1007 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2281 corpus positions)
-2024-11-11 07:55:58,858 - Dictionary lifecycle event {'msg': "built Dictionary<1007 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2281 corpus positions)", 'datetime': '2024-11-11T07:55:58.858366', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:55:58,859 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:55:58,859 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:55:58,859 - using serial LDA version on this node
-2024-11-11 07:55:58,860 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:55:58,860 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:55:58,863 - -7.903 per-word bound, 239.4 perplexity estimate based on a held-out corpus of 1 documents with 2281 words
-2024-11-11 07:55:58,863 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:55:58,864 - topic #0 (0.333): 0.018*"’" + 0.010*"Wakefield" + 0.009*"well" + 0.009*"leaders" + 0.008*"November" + 0.008*"effective" + 0.008*"good" + 0.007*"quality" + 0.006*"plans" + 0.006*"19"
-2024-11-11 07:55:58,864 - topic #1 (0.333): 0.016*"’" + 0.008*"quality" + 0.007*"November" + 0.007*"plans" + 0.006*"leaders" + 0.006*"needs" + 0.006*"progress" + 0.006*"Wakefield" + 0.006*"good" + 0.006*"effective"
-2024-11-11 07:55:58,864 - topic #2 (0.333): 0.015*"’" + 0.007*"well" + 0.006*"needs" + 0.005*"quality" + 0.005*"leaders" + 0.005*"November" + 0.005*"8" + 0.005*"practice" + 0.005*"plans" + 0.005*"Wakefield"
-2024-11-11 07:55:58,864 - topic diff=0.811367, rho=1.000000
-2024-11-11 07:55:58,865 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1007, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:55:58.865041', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:55:59,744 - Inspection date 2021-11-08 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:55:59,744 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:59,744 - Inspection date 2021-11-08 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:55:59,745 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:59,745 - Inspection date 2021-11-08 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:55:59,745 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:59,745 - Inspection date 2021-11-08 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:55:59,745 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:59,745 - Inspection date 2021-11-08 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:55:59,745 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:55:59,745 - Inspection date 2021-11-08 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:55:59,745 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:08,722 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:56:08,724 - built Dictionary<909 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1855 corpus positions)
-2024-11-11 07:56:08,725 - Dictionary lifecycle event {'msg': "built Dictionary<909 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1855 corpus positions)", 'datetime': '2024-11-11T07:56:08.725029', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:56:08,725 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:56:08,726 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:56:08,726 - using serial LDA version on this node
-2024-11-11 07:56:08,726 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:56:08,726 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:56:08,729 - -7.868 per-word bound, 233.6 perplexity estimate based on a held-out corpus of 1 documents with 1855 words
-2024-11-11 07:56:08,729 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:56:08,730 - topic #0 (0.333): 0.013*"’" + 0.007*"needs" + 0.006*"quality" + 0.006*"York" + 0.006*"However" + 0.005*"March" + 0.005*"training" + 0.005*"ensure" + 0.005*"22" + 0.005*"18"
-2024-11-11 07:56:08,731 - topic #1 (0.333): 0.012*"’" + 0.007*"needs" + 0.006*"quality" + 0.005*"effective" + 0.005*"However" + 0.005*"plans" + 0.004*"education" + 0.004*"March" + 0.004*"ensure" + 0.004*"good"
-2024-11-11 07:56:08,731 - topic #2 (0.333): 0.018*"’" + 0.010*"March" + 0.008*"needs" + 0.007*"effective" + 0.007*"quality" + 0.006*"well" + 0.006*"ensure" + 0.005*"York" + 0.005*"practice" + 0.005*"7"
-2024-11-11 07:56:08,731 - topic diff=0.775203, rho=1.000000
-2024-11-11 07:56:08,731 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=909, num_topics=3, decay=0.5, chunksize=2000> in 0.00s', 'datetime': '2024-11-11T07:56:08.731477', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:56:09,584 - Inspection date 2022-03-07 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:56:09,585 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:09,585 - Inspection date 2022-03-07 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:56:09,585 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:09,585 - Inspection date 2022-03-07 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:56:09,585 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:09,585 - Inspection date 2022-03-07 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:56:09,585 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:09,585 - Inspection date 2022-03-07 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:56:09,586 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:09,586 - Inspection date 2022-03-07 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:56:09,586 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:19,013 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:56:19,015 - built Dictionary<1053 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2351 corpus positions)
-2024-11-11 07:56:19,015 - Dictionary lifecycle event {'msg': "built Dictionary<1053 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2351 corpus positions)", 'datetime': '2024-11-11T07:56:19.015936', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:56:19,016 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:56:19,017 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:56:19,017 - using serial LDA version on this node
-2024-11-11 07:56:19,017 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:56:19,017 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:56:19,020 - -7.960 per-word bound, 249.1 perplexity estimate based on a held-out corpus of 1 documents with 2351 words
-2024-11-11 07:56:19,021 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:56:19,022 - topic #0 (0.333): 0.019*"’" + 0.009*"Cornwall" + 0.007*"needs" + 0.007*"well" + 0.007*"need" + 0.005*"effective" + 0.005*"homes" + 0.005*"5" + 0.004*"progress" + 0.004*"receive"
-2024-11-11 07:56:19,022 - topic #1 (0.333): 0.013*"’" + 0.012*"needs" + 0.007*"need" + 0.007*"Cornwall" + 0.006*"well" + 0.005*"oversight" + 0.005*"progress" + 0.004*"leaders" + 0.004*"receive" + 0.004*"2024"
-2024-11-11 07:56:19,022 - topic #2 (0.333): 0.022*"’" + 0.007*"Cornwall" + 0.007*"needs" + 0.006*"need" + 0.006*"receive" + 0.006*"well" + 0.005*"supported" + 0.005*"effective" + 0.005*"5" + 0.004*"1"
-2024-11-11 07:56:19,022 - topic diff=0.789314, rho=1.000000
-2024-11-11 07:56:19,022 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1053, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:56:19.022900', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:56:19,900 - Inspection date 2024-07-01 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:56:19,900 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:19,901 - Inspection date 2024-07-01 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:56:19,901 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:19,901 - Inspection date 2024-07-01 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:56:19,901 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:19,901 - Inspection date 2024-07-01 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:56:19,901 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:19,901 - Inspection date 2024-07-01 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:56:19,902 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:19,902 - Inspection date 2024-07-01 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:56:19,902 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:27,125 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:56:27,127 - built Dictionary<754 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1521 corpus positions)
-2024-11-11 07:56:27,127 - Dictionary lifecycle event {'msg': "built Dictionary<754 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1521 corpus positions)", 'datetime': '2024-11-11T07:56:27.127621', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:56:27,128 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:56:27,128 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:56:27,128 - using serial LDA version on this node
-2024-11-11 07:56:27,129 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:56:27,129 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:56:27,131 - -7.683 per-word bound, 205.4 perplexity estimate based on a held-out corpus of 1 documents with 1521 words
-2024-11-11 07:56:27,131 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:56:27,132 - topic #0 (0.333): 0.013*"’" + 0.010*"Isles" + 0.010*"Scilly" + 0.008*"practice" + 0.007*"information" + 0.006*"need" + 0.006*"needs" + 0.005*"13" + 0.005*"quality" + 0.005*"protection"
-2024-11-11 07:56:27,133 - topic #1 (0.333): 0.025*"’" + 0.013*"Isles" + 0.012*"Scilly" + 0.010*"need" + 0.009*"information" + 0.007*"protection" + 0.007*"place" + 0.007*"needs" + 0.007*"practice" + 0.007*"risks"
-2024-11-11 07:56:27,133 - topic #2 (0.333): 0.021*"’" + 0.013*"Scilly" + 0.011*"Isles" + 0.010*"practice" + 0.009*"information" + 0.007*"protection" + 0.007*"quality" + 0.006*"needs" + 0.006*"need" + 0.005*"11"
-2024-11-11 07:56:27,133 - topic diff=0.760311, rho=1.000000
-2024-11-11 07:56:27,133 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=754, num_topics=3, decay=0.5, chunksize=2000> in 0.00s', 'datetime': '2024-11-11T07:56:27.133363', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:56:28,040 - Inspection date 2023-07-11 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:56:28,040 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:28,041 - Inspection date 2023-07-11 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:56:28,041 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:28,041 - Inspection date 2023-07-11 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:56:28,041 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:28,041 - Inspection date 2023-07-11 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:56:28,041 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:28,041 - Inspection date 2023-07-11 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:56:28,041 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:28,042 - Inspection date 2023-07-11 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:56:28,042 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:38,421 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:56:38,422 - built Dictionary<938 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2074 corpus positions)
-2024-11-11 07:56:38,423 - Dictionary lifecycle event {'msg': "built Dictionary<938 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2074 corpus positions)", 'datetime': '2024-11-11T07:56:38.423171', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:56:38,424 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:56:38,424 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:56:38,424 - using serial LDA version on this node
-2024-11-11 07:56:38,424 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:56:38,424 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:56:38,427 - -7.848 per-word bound, 230.3 perplexity estimate based on a held-out corpus of 1 documents with 2074 words
-2024-11-11 07:56:38,427 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:56:38,429 - topic #0 (0.333): 0.024*"’" + 0.008*"supported" + 0.008*"needs" + 0.008*"Coventry" + 0.007*"well" + 0.006*"need" + 0.005*"family" + 0.005*"strong" + 0.005*"plans" + 0.004*"2022"
-2024-11-11 07:56:38,429 - topic #1 (0.333): 0.011*"’" + 0.007*"Coventry" + 0.007*"well" + 0.006*"family" + 0.005*"needs" + 0.005*"plans" + 0.005*"strong" + 0.004*"supported" + 0.004*"20" + 0.004*"need"
-2024-11-11 07:56:38,429 - topic #2 (0.333): 0.019*"’" + 0.009*"well" + 0.009*"Coventry" + 0.008*"needs" + 0.007*"plans" + 0.006*"supported" + 0.006*"family" + 0.005*"strong" + 0.005*"20" + 0.005*"need"
-2024-11-11 07:56:38,429 - topic diff=0.808344, rho=1.000000
-2024-11-11 07:56:38,429 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=938, num_topics=3, decay=0.5, chunksize=2000> in 0.00s', 'datetime': '2024-11-11T07:56:38.429682', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:56:39,311 - Inspection date 2022-06-20 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:56:39,311 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:39,312 - Inspection date 2022-06-20 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:56:39,312 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:39,312 - Inspection date 2022-06-20 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:56:39,312 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:39,312 - Inspection date 2022-06-20 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:56:39,312 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:39,312 - Inspection date 2022-06-20 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:56:39,312 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:39,313 - Inspection date 2022-06-20 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:56:39,313 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:51,632 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:56:51,634 - built Dictionary<1195 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2653 corpus positions)
-2024-11-11 07:56:51,634 - Dictionary lifecycle event {'msg': "built Dictionary<1195 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2653 corpus positions)", 'datetime': '2024-11-11T07:56:51.634614', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:56:51,635 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:56:51,635 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:56:51,636 - using serial LDA version on this node
-2024-11-11 07:56:51,636 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:56:51,636 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:56:51,640 - -8.093 per-word bound, 273.1 perplexity estimate based on a held-out corpus of 1 documents with 2653 words
-2024-11-11 07:56:51,640 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:56:51,641 - topic #0 (0.333): 0.016*"’" + 0.007*"Darlington" + 0.007*"well" + 0.006*"needs" + 0.006*"October" + 0.005*"practice" + 0.005*"effective" + 0.004*"need" + 0.004*"plans" + 0.004*"provide"
-2024-11-11 07:56:51,641 - topic #1 (0.333): 0.018*"’" + 0.009*"leaders" + 0.008*"October" + 0.007*"well" + 0.007*"practice" + 0.006*"needs" + 0.006*"Darlington" + 0.005*"supported" + 0.005*"education" + 0.005*"family"
-2024-11-11 07:56:51,642 - topic #2 (0.333): 0.021*"’" + 0.010*"well" + 0.007*"needs" + 0.006*"leaders" + 0.006*"quality" + 0.006*"practice" + 0.005*"October" + 0.005*"effective" + 0.004*"10" + 0.004*"Darlington"
-2024-11-11 07:56:51,642 - topic diff=0.799201, rho=1.000000
-2024-11-11 07:56:51,642 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1195, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:56:51.642261', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:56:52,478 - Inspection date 2022-10-10 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:56:52,478 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:52,479 - Inspection date 2022-10-10 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:56:52,479 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:52,479 - Inspection date 2022-10-10 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:56:52,479 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:52,479 - Inspection date 2022-10-10 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:56:52,479 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:52,479 - Inspection date 2022-10-10 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:56:52,479 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:56:52,479 - Inspection date 2022-10-10 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:56:52,480 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:03,323 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:57:03,325 - built Dictionary<1121 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2396 corpus positions)
-2024-11-11 07:57:03,325 - Dictionary lifecycle event {'msg': "built Dictionary<1121 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2396 corpus positions)", 'datetime': '2024-11-11T07:57:03.325568', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:57:03,326 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:57:03,326 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:57:03,326 - using serial LDA version on this node
-2024-11-11 07:57:03,327 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:57:03,327 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:57:03,330 - -8.049 per-word bound, 264.8 perplexity estimate based on a held-out corpus of 1 documents with 2396 words
-2024-11-11 07:57:03,331 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:57:03,332 - topic #0 (0.333): 0.026*"’" + 0.010*"needs" + 0.007*"Derby" + 0.007*"receive" + 0.006*"appropriate" + 0.006*"plans" + 0.005*"leaders" + 0.005*"progress" + 0.005*"quality" + 0.005*"21"
-2024-11-11 07:57:03,332 - topic #1 (0.333): 0.011*"’" + 0.008*"needs" + 0.007*"Derby" + 0.006*"quality" + 0.004*"well" + 0.004*"leaders" + 0.004*"receive" + 0.004*"progress" + 0.004*"need" + 0.004*"good"
-2024-11-11 07:57:03,332 - topic #2 (0.333): 0.022*"’" + 0.010*"needs" + 0.008*"quality" + 0.007*"Derby" + 0.006*"receive" + 0.006*"progress" + 0.006*"need" + 0.006*"plans" + 0.006*"good" + 0.006*"well"
-2024-11-11 07:57:03,332 - topic diff=0.787596, rho=1.000000
-2024-11-11 07:57:03,332 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1121, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:57:03.332893', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:57:04,296 - Inspection date 2022-03-21 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:57:04,296 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:04,297 - Inspection date 2022-03-21 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:57:04,297 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:04,297 - Inspection date 2022-03-21 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:57:04,297 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:04,297 - Inspection date 2022-03-21 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:57:04,297 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:04,297 - Inspection date 2022-03-21 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:57:04,297 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:04,298 - Inspection date 2022-03-21 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:57:04,298 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:13,120 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:57:13,122 - built Dictionary<1046 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2035 corpus positions)
-2024-11-11 07:57:13,122 - Dictionary lifecycle event {'msg': "built Dictionary<1046 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2035 corpus positions)", 'datetime': '2024-11-11T07:57:13.122688', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:57:13,123 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:57:13,123 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:57:13,124 - using serial LDA version on this node
-2024-11-11 07:57:13,124 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:57:13,124 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:57:13,127 - -8.040 per-word bound, 263.2 perplexity estimate based on a held-out corpus of 1 documents with 2035 words
-2024-11-11 07:57:13,127 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:57:13,129 - topic #0 (0.333): 0.008*"’" + 0.006*"well" + 0.005*"Derbyshire" + 0.005*"positive" + 0.004*"leaders" + 0.004*"plans" + 0.004*"effective" + 0.004*"education" + 0.004*"needs" + 0.004*"good"
-2024-11-11 07:57:13,129 - topic #1 (0.333): 0.018*"’" + 0.008*"Derbyshire" + 0.007*"well" + 0.006*"needs" + 0.005*"10" + 0.005*"plans" + 0.005*"education" + 0.005*"number" + 0.005*"health" + 0.004*"positive"
-2024-11-11 07:57:13,129 - topic #2 (0.333): 0.014*"’" + 0.010*"well" + 0.005*"Derbyshire" + 0.005*"plans" + 0.005*"need" + 0.005*"leaders" + 0.005*"good" + 0.005*"health" + 0.004*"positive" + 0.004*"October"
-2024-11-11 07:57:13,129 - topic diff=0.747546, rho=1.000000
-2024-11-11 07:57:13,129 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1046, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:57:13.129645', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:57:14,085 - Inspection date 2023-10-30 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:57:14,086 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:14,086 - Inspection date 2023-10-30 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:57:14,086 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:14,086 - Inspection date 2023-10-30 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:57:14,086 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:14,086 - Inspection date 2023-10-30 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:57:14,086 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:14,087 - Inspection date 2023-10-30 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:57:14,087 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:14,087 - Inspection date 2023-10-30 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:57:14,087 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:24,569 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:57:24,571 - built Dictionary<1175 unique tokens: ['0161', '0300', '1', '1,000', '10']...> from 1 documents (total 2313 corpus positions)
-2024-11-11 07:57:24,571 - Dictionary lifecycle event {'msg': "built Dictionary<1175 unique tokens: ['0161', '0300', '1', '1,000', '10']...> from 1 documents (total 2313 corpus positions)", 'datetime': '2024-11-11T07:57:24.571511', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:57:24,572 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:57:24,572 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:57:24,572 - using serial LDA version on this node
-2024-11-11 07:57:24,573 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:57:24,573 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:57:24,576 - -8.144 per-word bound, 282.8 perplexity estimate based on a held-out corpus of 1 documents with 2313 words
-2024-11-11 07:57:24,577 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:57:24,578 - topic #0 (0.333): 0.010*"’" + 0.007*"well" + 0.005*"risk" + 0.004*"living" + 0.004*"practice" + 0.004*"health" + 0.004*"case" + 0.004*"leaders" + 0.004*"areas" + 0.004*"protection"
-2024-11-11 07:57:24,578 - topic #1 (0.333): 0.009*"’" + 0.005*"progress" + 0.005*"leaders" + 0.005*"health" + 0.005*"risk" + 0.004*"well" + 0.004*"plans" + 0.004*"including" + 0.004*"Devon" + 0.004*"time"
-2024-11-11 07:57:24,578 - topic #2 (0.333): 0.008*"’" + 0.006*"well" + 0.005*"leaders" + 0.005*"health" + 0.005*"progress" + 0.004*"need" + 0.004*"quality" + 0.004*"Devon" + 0.004*"risk" + 0.004*"risks"
-2024-11-11 07:57:24,578 - topic diff=0.728401, rho=1.000000
-2024-11-11 07:57:24,578 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1175, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:57:24.578895', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:57:25,522 - Inspection date 2020-01-20 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:57:25,522 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:25,522 - Inspection date 2020-01-20 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:57:25,522 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:25,522 - Inspection date 2020-01-20 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:57:25,522 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:25,522 - Inspection date 2020-01-20 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:57:25,522 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:25,523 - Inspection date 2020-01-20 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:57:25,523 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:25,523 - Inspection date 2020-01-20 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:57:25,523 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:35,744 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:57:35,746 - built Dictionary<1175 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2429 corpus positions)
-2024-11-11 07:57:35,747 - Dictionary lifecycle event {'msg': "built Dictionary<1175 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2429 corpus positions)", 'datetime': '2024-11-11T07:57:35.747070', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:57:35,748 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:57:35,748 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:57:35,748 - using serial LDA version on this node
-2024-11-11 07:57:35,748 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:57:35,748 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:57:35,752 - -8.111 per-word bound, 276.5 perplexity estimate based on a held-out corpus of 1 documents with 2429 words
-2024-11-11 07:57:35,752 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:57:35,754 - topic #0 (0.333): 0.017*"’" + 0.005*"well" + 0.005*"leaders" + 0.005*"Doncaster" + 0.005*"arrangements" + 0.005*"Trust" + 0.005*"February" + 0.004*"records" + 0.004*"means" + 0.004*"supported"
-2024-11-11 07:57:35,754 - topic #1 (0.333): 0.021*"’" + 0.007*"Doncaster" + 0.006*"many" + 0.006*"well" + 0.005*"progress" + 0.005*"plans" + 0.005*"oversight" + 0.005*"quality" + 0.005*"effective" + 0.005*"receive"
-2024-11-11 07:57:35,754 - topic #2 (0.333): 0.022*"’" + 0.008*"well" + 0.006*"Doncaster" + 0.005*"records" + 0.005*"information" + 0.005*"progress" + 0.005*"leaders" + 0.005*"14" + 0.005*"quality" + 0.005*"Trust"
-2024-11-11 07:57:35,754 - topic diff=0.765924, rho=1.000000
-2024-11-11 07:57:35,754 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1175, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:57:35.754529', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:57:37,497 - Inspection date 2022-02-14 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:57:37,497 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:37,497 - Inspection date 2022-02-14 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:57:37,497 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:37,497 - Inspection date 2022-02-14 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:57:37,497 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:37,498 - Inspection date 2022-02-14 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:57:37,498 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:37,498 - Inspection date 2022-02-14 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:57:37,498 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:37,498 - Inspection date 2022-02-14 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:57:37,498 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:45,245 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:57:45,247 - built Dictionary<1067 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1942 corpus positions)
-2024-11-11 07:57:45,247 - Dictionary lifecycle event {'msg': "built Dictionary<1067 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1942 corpus positions)", 'datetime': '2024-11-11T07:57:45.247489', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:57:45,248 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:57:45,248 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:57:45,248 - using serial LDA version on this node
-2024-11-11 07:57:45,249 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:57:45,249 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:57:45,252 - -8.104 per-word bound, 275.1 perplexity estimate based on a held-out corpus of 1 documents with 1942 words
-2024-11-11 07:57:45,252 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:57:45,253 - topic #0 (0.333): 0.012*"’" + 0.007*"Dorset" + 0.006*"well" + 0.006*"good" + 0.004*"8" + 0.004*"needs" + 0.004*"27" + 0.004*"need" + 0.004*"arrangements" + 0.004*"September"
-2024-11-11 07:57:45,254 - topic #1 (0.333): 0.010*"’" + 0.007*"good" + 0.005*"Dorset" + 0.005*"well" + 0.004*"27" + 0.004*"leaders" + 0.004*"arrangements" + 0.004*"Senior" + 0.004*"need" + 0.004*"home"
-2024-11-11 07:57:45,254 - topic #2 (0.333): 0.018*"’" + 0.010*"Dorset" + 0.006*"well" + 0.006*"good" + 0.005*"needs" + 0.005*"arrangements" + 0.005*"October" + 0.004*"quality" + 0.004*"8" + 0.004*"change"
-2024-11-11 07:57:45,254 - topic diff=0.723329, rho=1.000000
-2024-11-11 07:57:45,254 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1067, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:57:45.254426', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:57:46,054 - Inspection date 2021-09-27 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:57:46,055 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:46,055 - Inspection date 2021-09-27 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:57:46,055 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:46,055 - Inspection date 2021-09-27 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:57:46,055 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:46,056 - Inspection date 2021-09-27 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:57:46,056 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:46,056 - Inspection date 2021-09-27 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:57:46,056 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:46,056 - Inspection date 2021-09-27 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:57:46,056 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:55,629 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:57:55,632 - built Dictionary<1050 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2138 corpus positions)
-2024-11-11 07:57:55,632 - Dictionary lifecycle event {'msg': "built Dictionary<1050 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2138 corpus positions)", 'datetime': '2024-11-11T07:57:55.632392', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:57:55,633 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:57:55,633 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:57:55,633 - using serial LDA version on this node
-2024-11-11 07:57:55,634 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:57:55,634 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:57:55,637 - -8.010 per-word bound, 257.8 perplexity estimate based on a held-out corpus of 1 documents with 2138 words
-2024-11-11 07:57:55,637 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:57:55,638 - topic #0 (0.333): 0.014*"’" + 0.009*"Dudley" + 0.009*"needs" + 0.005*"always" + 0.005*"arrangements" + 0.005*"well" + 0.005*"ensure" + 0.004*"plans" + 0.004*"oversight" + 0.004*"home"
-2024-11-11 07:57:55,638 - topic #1 (0.333): 0.011*"’" + 0.007*"Dudley" + 0.007*"needs" + 0.005*"always" + 0.005*"plans" + 0.005*"arrangements" + 0.005*"well" + 0.004*"However" + 0.004*"practice" + 0.004*"quality"
-2024-11-11 07:57:55,639 - topic #2 (0.333): 0.018*"’" + 0.016*"needs" + 0.007*"Dudley" + 0.006*"well" + 0.005*"plans" + 0.005*"quality" + 0.005*"oversight" + 0.005*"arrangements" + 0.005*"always" + 0.005*"October"
-2024-11-11 07:57:55,639 - topic diff=0.757299, rho=1.000000
-2024-11-11 07:57:55,639 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1050, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:57:55.639295', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:57:56,521 - Inspection date 2022-10-31 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:57:56,521 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:56,521 - Inspection date 2022-10-31 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:57:56,521 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:56,522 - Inspection date 2022-10-31 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:57:56,522 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:56,522 - Inspection date 2022-10-31 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:57:56,522 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:56,522 - Inspection date 2022-10-31 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:57:56,522 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:57:56,522 - Inspection date 2022-10-31 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:57:56,522 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:07,041 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:58:07,043 - built Dictionary<1051 unique tokens: ['0', '0161', '0300', '1', '10']...> from 1 documents (total 2278 corpus positions)
-2024-11-11 07:58:07,044 - Dictionary lifecycle event {'msg': "built Dictionary<1051 unique tokens: ['0', '0161', '0300', '1', '10']...> from 1 documents (total 2278 corpus positions)", 'datetime': '2024-11-11T07:58:07.044065', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:58:07,045 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:58:07,045 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:58:07,045 - using serial LDA version on this node
-2024-11-11 07:58:07,045 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:58:07,045 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:58:07,049 - -7.977 per-word bound, 252.0 perplexity estimate based on a held-out corpus of 1 documents with 2278 words
-2024-11-11 07:58:07,049 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:58:07,050 - topic #0 (0.333): 0.015*"’" + 0.011*"needs" + 0.007*"well" + 0.006*"plans" + 0.006*"May" + 0.006*"ensure" + 0.006*"number" + 0.005*"Durham" + 0.005*"risks" + 0.005*"practice"
-2024-11-11 07:58:07,050 - topic #1 (0.333): 0.014*"’" + 0.011*"needs" + 0.007*"May" + 0.007*"plans" + 0.006*"ensure" + 0.006*"well" + 0.006*"Durham" + 0.005*"practice" + 0.005*"supported" + 0.004*"carers"
-2024-11-11 07:58:07,050 - topic #2 (0.333): 0.014*"’" + 0.010*"needs" + 0.010*"Durham" + 0.008*"May" + 0.007*"well" + 0.006*"plans" + 0.005*"practice" + 0.005*"ensure" + 0.004*"leaders" + 0.004*"appropriate"
-2024-11-11 07:58:07,050 - topic diff=0.769418, rho=1.000000
-2024-11-11 07:58:07,051 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1051, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:58:07.051019', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:58:07,924 - Inspection date 2022-05-09 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:58:07,924 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:07,924 - Inspection date 2022-05-09 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:58:07,924 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:07,925 - Inspection date 2022-05-09 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:58:07,925 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:07,925 - Inspection date 2022-05-09 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:58:07,925 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:07,925 - Inspection date 2022-05-09 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:58:07,925 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:07,925 - Inspection date 2022-05-09 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:58:07,925 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:17,398 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:58:17,400 - built Dictionary<972 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2014 corpus positions)
-2024-11-11 07:58:17,401 - Dictionary lifecycle event {'msg': "built Dictionary<972 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2014 corpus positions)", 'datetime': '2024-11-11T07:58:17.401124', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:58:17,402 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:58:17,402 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:58:17,402 - using serial LDA version on this node
-2024-11-11 07:58:17,402 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:58:17,402 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:58:17,405 - -7.929 per-word bound, 243.7 perplexity estimate based on a held-out corpus of 1 documents with 2014 words
-2024-11-11 07:58:17,406 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:58:17,407 - topic #0 (0.333): 0.013*"’" + 0.010*"needs" + 0.008*"plans" + 0.008*"progress" + 0.007*"East" + 0.007*"well" + 0.005*"partners" + 0.005*"Riding" + 0.005*"10" + 0.005*"30"
-2024-11-11 07:58:17,407 - topic #1 (0.333): 0.017*"’" + 0.010*"well" + 0.009*"needs" + 0.008*"Riding" + 0.007*"plans" + 0.006*"East" + 0.006*"progress" + 0.005*"education" + 0.005*"10" + 0.005*"good"
-2024-11-11 07:58:17,407 - topic #2 (0.333): 0.018*"’" + 0.010*"plans" + 0.008*"needs" + 0.007*"well" + 0.007*"progress" + 0.006*"Riding" + 0.006*"East" + 0.005*"30" + 0.005*"2023" + 0.005*"quality"
-2024-11-11 07:58:17,407 - topic diff=0.774374, rho=1.000000
-2024-11-11 07:58:17,407 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=972, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:58:17.407790', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:58:18,263 - Inspection date 2023-01-30 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:58:18,264 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:18,264 - Inspection date 2023-01-30 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:58:18,264 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:18,264 - Inspection date 2023-01-30 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:58:18,264 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:18,265 - Inspection date 2023-01-30 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:58:18,265 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:18,265 - Inspection date 2023-01-30 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:58:18,265 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:18,265 - Inspection date 2023-01-30 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:58:18,265 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:27,930 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:58:27,932 - built Dictionary<1111 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2220 corpus positions)
-2024-11-11 07:58:27,933 - Dictionary lifecycle event {'msg': "built Dictionary<1111 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2220 corpus positions)", 'datetime': '2024-11-11T07:58:27.933012', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:58:27,934 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:58:27,934 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:58:27,934 - using serial LDA version on this node
-2024-11-11 07:58:27,934 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:58:27,934 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:58:27,938 - -8.076 per-word bound, 269.9 perplexity estimate based on a held-out corpus of 1 documents with 2220 words
-2024-11-11 07:58:27,938 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:58:27,939 - topic #0 (0.333): 0.020*"’" + 0.010*"needs" + 0.009*"well" + 0.007*"plans" + 0.007*"progress" + 0.007*"Sussex" + 0.006*"including" + 0.005*"impact" + 0.005*"East" + 0.005*"effective"
-2024-11-11 07:58:27,940 - topic #1 (0.333): 0.013*"’" + 0.008*"well" + 0.007*"plans" + 0.006*"needs" + 0.006*"Sussex" + 0.005*"including" + 0.005*"experiences" + 0.005*"effective" + 0.004*"impact" + 0.004*"relationships"
-2024-11-11 07:58:27,940 - topic #2 (0.333): 0.014*"’" + 0.010*"well" + 0.009*"East" + 0.009*"plans" + 0.007*"progress" + 0.006*"needs" + 0.005*"including" + 0.005*"impact" + 0.005*"11" + 0.005*"Sussex"
-2024-11-11 07:58:27,940 - topic diff=0.760532, rho=1.000000
-2024-11-11 07:58:27,940 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1111, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:58:27.940391', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:58:28,822 - Inspection date 2023-12-11 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:58:28,823 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:28,823 - Inspection date 2023-12-11 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:58:28,823 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:28,823 - Inspection date 2023-12-11 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:58:28,823 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:28,824 - Inspection date 2023-12-11 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:58:28,824 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:28,824 - Inspection date 2023-12-11 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:58:28,824 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:28,824 - Inspection date 2023-12-11 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:58:28,824 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:39,524 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:58:39,526 - built Dictionary<1142 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2686 corpus positions)
-2024-11-11 07:58:39,526 - Dictionary lifecycle event {'msg': "built Dictionary<1142 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2686 corpus positions)", 'datetime': '2024-11-11T07:58:39.526874', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:58:39,528 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:58:39,528 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:58:39,528 - using serial LDA version on this node
-2024-11-11 07:58:39,528 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:58:39,528 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:58:39,532 - -8.013 per-word bound, 258.4 perplexity estimate based on a held-out corpus of 1 documents with 2686 words
-2024-11-11 07:58:39,532 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:58:39,533 - topic #0 (0.333): 0.018*"’" + 0.007*"progress" + 0.006*"well" + 0.006*"plans" + 0.006*"needs" + 0.006*"family" + 0.006*"experiences" + 0.005*"understand" + 0.005*"practice" + 0.005*"Essex"
-2024-11-11 07:58:39,533 - topic #1 (0.333): 0.017*"’" + 0.007*"progress" + 0.007*"well" + 0.006*"needs" + 0.005*"plans" + 0.005*"risk" + 0.005*"‘" + 0.005*"parents" + 0.005*"helped" + 0.004*"new"
-2024-11-11 07:58:39,534 - topic #2 (0.333): 0.019*"’" + 0.007*"well" + 0.006*"plans" + 0.006*"needs" + 0.005*"Essex" + 0.005*"family" + 0.005*"progress" + 0.005*"practice" + 0.005*"new" + 0.005*"need"
-2024-11-11 07:58:39,534 - topic diff=0.808049, rho=1.000000
-2024-11-11 07:58:39,534 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1142, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:58:39.534303', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:58:40,548 - Inspection date 2023-06-26 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:58:40,548 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:40,548 - Inspection date 2023-06-26 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:58:40,548 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:40,548 - Inspection date 2023-06-26 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:58:40,548 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:40,548 - Inspection date 2023-06-26 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:58:40,549 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:40,549 - Inspection date 2023-06-26 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:58:40,549 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:40,549 - Inspection date 2023-06-26 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:58:40,549 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:50,354 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:58:50,358 - built Dictionary<1112 unique tokens: ['0161', '0300', '0–19', '1', '10']...> from 1 documents (total 2356 corpus positions)
-2024-11-11 07:58:50,358 - Dictionary lifecycle event {'msg': "built Dictionary<1112 unique tokens: ['0161', '0300', '0–19', '1', '10']...> from 1 documents (total 2356 corpus positions)", 'datetime': '2024-11-11T07:58:50.358478', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:58:50,359 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:58:50,359 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:58:50,359 - using serial LDA version on this node
-2024-11-11 07:58:50,360 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:58:50,360 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:58:50,363 - -8.042 per-word bound, 263.6 perplexity estimate based on a held-out corpus of 1 documents with 2356 words
-2024-11-11 07:58:50,364 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:58:50,365 - topic #0 (0.333): 0.009*"’" + 0.009*"effective" + 0.008*"needs" + 0.006*"practice" + 0.006*"good" + 0.006*"quality" + 0.005*"well" + 0.005*"plans" + 0.004*"improve" + 0.004*"timely"
-2024-11-11 07:58:50,365 - topic #1 (0.333): 0.018*"’" + 0.008*"effective" + 0.008*"good" + 0.007*"well" + 0.006*"timely" + 0.006*"practice" + 0.006*"quality" + 0.005*"need" + 0.005*"early" + 0.005*"needs"
-2024-11-11 07:58:50,365 - topic #2 (0.333): 0.012*"’" + 0.008*"effective" + 0.007*"practice" + 0.007*"quality" + 0.006*"good" + 0.005*"timely" + 0.004*"needs" + 0.004*"early" + 0.004*"home" + 0.004*"plans"
-2024-11-11 07:58:50,365 - topic diff=0.770698, rho=1.000000
-2024-11-11 07:58:50,366 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1112, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:58:50.366003', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:58:51,236 - Inspection date 2019-04-29 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:58:51,236 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:51,236 - Inspection date 2019-04-29 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:58:51,236 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:51,236 - Inspection date 2019-04-29 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:58:51,237 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:51,237 - Inspection date 2019-04-29 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:58:51,237 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:51,237 - Inspection date 2019-04-29 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:58:51,237 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:58:51,237 - Inspection date 2019-04-29 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:58:51,237 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:01,729 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:59:01,732 - built Dictionary<1161 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2579 corpus positions)
-2024-11-11 07:59:01,732 - Dictionary lifecycle event {'msg': "built Dictionary<1161 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2579 corpus positions)", 'datetime': '2024-11-11T07:59:01.732340', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:59:01,733 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:59:01,733 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:59:01,733 - using serial LDA version on this node
-2024-11-11 07:59:01,734 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:59:01,734 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:59:01,737 - -8.061 per-word bound, 267.1 perplexity estimate based on a held-out corpus of 1 documents with 2579 words
-2024-11-11 07:59:01,737 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:59:01,739 - topic #0 (0.333): 0.011*"’" + 0.006*"plans" + 0.005*"needs" + 0.005*"2022" + 0.005*"February" + 0.005*"need" + 0.005*"experienced" + 0.004*"leaders" + 0.004*"progress" + 0.004*"timely"
-2024-11-11 07:59:01,739 - topic #1 (0.333): 0.019*"’" + 0.011*"needs" + 0.008*"February" + 0.008*"2022" + 0.007*"plans" + 0.006*"well" + 0.006*"Gloucestershire" + 0.005*"appropriate" + 0.005*"progress" + 0.005*"family"
-2024-11-11 07:59:01,739 - topic #2 (0.333): 0.020*"’" + 0.007*"needs" + 0.007*"February" + 0.007*"2022" + 0.006*"plans" + 0.005*"good" + 0.005*"well" + 0.005*"protection" + 0.005*"Gloucestershire" + 0.005*"18"
-2024-11-11 07:59:01,739 - topic diff=0.827677, rho=1.000000
-2024-11-11 07:59:01,739 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1161, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:59:01.739773', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:59:02,594 - Inspection date 2022-02-07 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:59:02,595 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:02,595 - Inspection date 2022-02-07 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:59:02,595 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:02,595 - Inspection date 2022-02-07 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:59:02,595 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:02,595 - Inspection date 2022-02-07 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:59:02,595 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:02,596 - Inspection date 2022-02-07 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:59:02,596 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:02,596 - Inspection date 2022-02-07 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:59:02,596 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:14,611 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:59:14,614 - built Dictionary<1172 unique tokens: ['00', '0161', '03', '0300', '1']...> from 1 documents (total 2652 corpus positions)
-2024-11-11 07:59:14,614 - Dictionary lifecycle event {'msg': "built Dictionary<1172 unique tokens: ['00', '0161', '03', '0300', '1']...> from 1 documents (total 2652 corpus positions)", 'datetime': '2024-11-11T07:59:14.614486', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:59:14,615 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:59:14,615 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:59:14,615 - using serial LDA version on this node
-2024-11-11 07:59:14,616 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:59:14,616 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:59:14,620 - -8.056 per-word bound, 266.1 perplexity estimate based on a held-out corpus of 1 documents with 2652 words
-2024-11-11 07:59:14,620 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:59:14,621 - topic #0 (0.333): 0.017*"’" + 0.007*"needs" + 0.006*"quality" + 0.006*"Halton" + 0.006*"including" + 0.005*"need" + 0.005*"many" + 0.005*"Leaders" + 0.005*"13" + 0.004*"lack"
-2024-11-11 07:59:14,621 - topic #1 (0.333): 0.018*"’" + 0.008*"needs" + 0.007*"many" + 0.006*"Halton" + 0.006*"plans" + 0.005*"protection" + 0.005*"lack" + 0.005*"recently" + 0.005*"2024" + 0.005*"need"
-2024-11-11 07:59:14,621 - topic #2 (0.333): 0.010*"’" + 0.007*"quality" + 0.007*"needs" + 0.006*"many" + 0.005*"including" + 0.005*"need" + 0.005*"Halton" + 0.005*"Leaders" + 0.005*"progress" + 0.004*"plans"
-2024-11-11 07:59:14,621 - topic diff=0.804368, rho=1.000000
-2024-11-11 07:59:14,622 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1172, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:59:14.622045', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:59:15,486 - Inspection date 2024-05-13 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:59:15,486 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:15,486 - Inspection date 2024-05-13 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:59:15,486 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:15,486 - Inspection date 2024-05-13 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:59:15,486 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:15,487 - Inspection date 2024-05-13 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:59:15,487 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:15,487 - Inspection date 2024-05-13 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:59:15,487 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:15,487 - Inspection date 2024-05-13 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:59:15,487 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:26,030 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:59:26,032 - built Dictionary<1092 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2524 corpus positions)
-2024-11-11 07:59:26,032 - Dictionary lifecycle event {'msg': "built Dictionary<1092 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2524 corpus positions)", 'datetime': '2024-11-11T07:59:26.032915', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:59:26,034 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:59:26,034 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:59:26,034 - using serial LDA version on this node
-2024-11-11 07:59:26,034 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:59:26,034 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:59:26,038 - -7.979 per-word bound, 252.3 perplexity estimate based on a held-out corpus of 1 documents with 2524 words
-2024-11-11 07:59:26,038 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:59:26,039 - topic #0 (0.333): 0.021*"’" + 0.008*"well" + 0.008*"new" + 0.008*"family" + 0.007*"plans" + 0.007*"progress" + 0.006*"needs" + 0.006*"Hampshire" + 0.006*"practice" + 0.006*"quality"
-2024-11-11 07:59:26,040 - topic #1 (0.333): 0.016*"’" + 0.006*"well" + 0.006*"new" + 0.006*"plans" + 0.006*"progress" + 0.006*"family" + 0.005*"receive" + 0.005*"quality" + 0.004*"practice" + 0.004*"2024"
-2024-11-11 07:59:26,040 - topic #2 (0.333): 0.008*"’" + 0.007*"family" + 0.005*"well" + 0.005*"new" + 0.004*"quality" + 0.004*"achieve" + 0.004*"understand" + 0.004*"plans" + 0.004*"receive" + 0.004*"progress"
-2024-11-11 07:59:26,040 - topic diff=0.834973, rho=1.000000
-2024-11-11 07:59:26,040 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1092, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:59:26.040451', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:59:27,013 - Inspection date 2024-06-10 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:59:27,013 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:27,013 - Inspection date 2024-06-10 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:59:27,013 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:27,013 - Inspection date 2024-06-10 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:59:27,013 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:27,014 - Inspection date 2024-06-10 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:59:27,014 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:27,014 - Inspection date 2024-06-10 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:59:27,014 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:27,014 - Inspection date 2024-06-10 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:59:27,014 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:39,275 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:59:39,277 - built Dictionary<1171 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2584 corpus positions)
-2024-11-11 07:59:39,277 - Dictionary lifecycle event {'msg': "built Dictionary<1171 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2584 corpus positions)", 'datetime': '2024-11-11T07:59:39.277703', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:59:39,278 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:59:39,278 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:59:39,279 - using serial LDA version on this node
-2024-11-11 07:59:39,279 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:59:39,279 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:59:39,283 - -8.069 per-word bound, 268.5 perplexity estimate based on a held-out corpus of 1 documents with 2584 words
-2024-11-11 07:59:39,283 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:59:39,284 - topic #0 (0.333): 0.018*"’" + 0.007*"needs" + 0.007*"March" + 0.007*"Hartlepool" + 0.006*"supported" + 0.005*"18" + 0.005*"leaders" + 0.005*"well" + 0.004*"ensure" + 0.004*"clear"
-2024-11-11 07:59:39,284 - topic #1 (0.333): 0.020*"’" + 0.008*"Hartlepool" + 0.008*"March" + 0.007*"needs" + 0.007*"well" + 0.006*"leaders" + 0.006*"plans" + 0.005*"practice" + 0.005*"strong" + 0.005*"clear"
-2024-11-11 07:59:39,284 - topic #2 (0.333): 0.020*"’" + 0.007*"March" + 0.005*"Hartlepool" + 0.005*"well" + 0.005*"needs" + 0.005*"effective" + 0.005*"leaders" + 0.005*"ensure" + 0.004*"need" + 0.004*"18"
-2024-11-11 07:59:39,284 - topic diff=0.792593, rho=1.000000
-2024-11-11 07:59:39,285 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1171, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:59:39.285052', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:59:40,192 - Inspection date 2024-03-18 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:59:40,192 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:40,192 - Inspection date 2024-03-18 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:59:40,193 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:40,193 - Inspection date 2024-03-18 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:59:40,193 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:40,193 - Inspection date 2024-03-18 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:59:40,193 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:40,193 - Inspection date 2024-03-18 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:59:40,193 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:40,193 - Inspection date 2024-03-18 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:59:40,193 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:51,576 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 07:59:51,578 - built Dictionary<1142 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2531 corpus positions)
-2024-11-11 07:59:51,578 - Dictionary lifecycle event {'msg': "built Dictionary<1142 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2531 corpus positions)", 'datetime': '2024-11-11T07:59:51.578950', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:59:51,580 - using symmetric alpha at 0.3333333333333333
-2024-11-11 07:59:51,580 - using symmetric eta at 0.3333333333333333
-2024-11-11 07:59:51,580 - using serial LDA version on this node
-2024-11-11 07:59:51,580 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 07:59:51,580 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 07:59:51,584 - -8.042 per-word bound, 263.6 perplexity estimate based on a held-out corpus of 1 documents with 2531 words
-2024-11-11 07:59:51,584 - PROGRESS: pass 0, at document #1/1
-2024-11-11 07:59:51,585 - topic #0 (0.333): 0.015*"’" + 0.005*"lack" + 0.005*"Herefordshire" + 0.005*"needs" + 0.005*"practice" + 0.005*"impact" + 0.004*"July" + 0.004*"carers" + 0.004*"quality" + 0.004*"progress"
-2024-11-11 07:59:51,585 - topic #1 (0.333): 0.020*"’" + 0.006*"practice" + 0.006*"Herefordshire" + 0.005*"many" + 0.005*"impact" + 0.005*"needs" + 0.005*"lack" + 0.005*"plans" + 0.004*"oversight" + 0.004*"2022"
-2024-11-11 07:59:51,586 - topic #2 (0.333): 0.016*"’" + 0.005*"practice" + 0.005*"Herefordshire" + 0.005*"lack" + 0.005*"many" + 0.004*"impact" + 0.004*"carers" + 0.004*"needs" + 0.004*"agency" + 0.004*"2022"
-2024-11-11 07:59:51,586 - topic diff=0.794756, rho=1.000000
-2024-11-11 07:59:51,586 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1142, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T07:59:51.586193', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 07:59:52,557 - Inspection date 2022-07-18 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 07:59:52,558 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:52,558 - Inspection date 2022-07-18 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 07:59:52,558 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:52,558 - Inspection date 2022-07-18 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 07:59:52,558 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:52,558 - Inspection date 2022-07-18 / Column 'in_care' not found in the DataFrame.
-2024-11-11 07:59:52,558 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:52,558 - Inspection date 2022-07-18 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 07:59:52,558 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 07:59:52,559 - Inspection date 2022-07-18 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 07:59:52,559 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:03,930 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:00:03,932 - built Dictionary<1192 unique tokens: ['0161', '0300', '1', '10', '100']...> from 1 documents (total 2456 corpus positions)
-2024-11-11 08:00:03,932 - Dictionary lifecycle event {'msg': "built Dictionary<1192 unique tokens: ['0161', '0300', '1', '10', '100']...> from 1 documents (total 2456 corpus positions)", 'datetime': '2024-11-11T08:00:03.932562', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:00:03,933 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:00:03,933 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:00:03,933 - using serial LDA version on this node
-2024-11-11 08:00:03,934 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:00:03,934 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:00:03,938 - -8.127 per-word bound, 279.5 perplexity estimate based on a held-out corpus of 1 documents with 2456 words
-2024-11-11 08:00:03,938 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:00:03,939 - topic #0 (0.333): 0.024*"’" + 0.006*"Hertfordshire" + 0.005*"well" + 0.005*"January" + 0.005*"needs" + 0.004*"27" + 0.004*"leaders" + 0.004*"risk" + 0.004*"training" + 0.003*"‘"
-2024-11-11 08:00:03,939 - topic #1 (0.333): 0.027*"’" + 0.008*"needs" + 0.007*"receive" + 0.006*"Hertfordshire" + 0.006*"well" + 0.006*"plans" + 0.004*"23" + 0.004*"need" + 0.004*"positive" + 0.004*"‘"
-2024-11-11 08:00:03,939 - topic #2 (0.333): 0.016*"’" + 0.007*"well" + 0.006*"Hertfordshire" + 0.005*"leaders" + 0.005*"needs" + 0.004*"receive" + 0.004*"2023" + 0.004*"risk" + 0.004*"family" + 0.004*"plans"
-2024-11-11 08:00:03,939 - topic diff=0.788611, rho=1.000000
-2024-11-11 08:00:03,939 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1192, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:00:03.939922', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:00:05,746 - Inspection date 2023-01-23 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:00:05,746 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:05,746 - Inspection date 2023-01-23 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:00:05,746 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:05,747 - Inspection date 2023-01-23 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:00:05,747 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:05,747 - Inspection date 2023-01-23 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:00:05,747 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:05,747 - Inspection date 2023-01-23 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:00:05,747 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:05,747 - Inspection date 2023-01-23 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:00:05,747 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:14,908 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:00:14,910 - built Dictionary<976 unique tokens: ['0161', '0300', '1', '10', '10-year']...> from 1 documents (total 1934 corpus positions)
-2024-11-11 08:00:14,910 - Dictionary lifecycle event {'msg': "built Dictionary<976 unique tokens: ['0161', '0300', '1', '10', '10-year']...> from 1 documents (total 1934 corpus positions)", 'datetime': '2024-11-11T08:00:14.910694', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:00:14,911 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:00:14,911 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:00:14,911 - using serial LDA version on this node
-2024-11-11 08:00:14,912 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:00:14,912 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:00:14,915 - -7.953 per-word bound, 247.7 perplexity estimate based on a held-out corpus of 1 documents with 1934 words
-2024-11-11 08:00:14,915 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:00:14,916 - topic #0 (0.333): 0.013*"’" + 0.008*"leaders" + 0.005*"needs" + 0.005*"supported" + 0.005*"progress" + 0.005*"Wight" + 0.005*"practice" + 0.004*"Isle" + 0.004*"November" + 0.004*"well"
-2024-11-11 08:00:14,917 - topic #1 (0.333): 0.011*"’" + 0.007*"leaders" + 0.006*"well" + 0.005*"plans" + 0.005*"Isle" + 0.005*"needs" + 0.005*"progress" + 0.005*"Wight" + 0.005*"3" + 0.004*"Senior"
-2024-11-11 08:00:14,917 - topic #2 (0.333): 0.024*"’" + 0.009*"leaders" + 0.006*"needs" + 0.006*"well" + 0.006*"Senior" + 0.006*"3" + 0.005*"PAs" + 0.005*"good" + 0.005*"supported" + 0.005*"improve"
-2024-11-11 08:00:14,917 - topic diff=0.782526, rho=1.000000
-2024-11-11 08:00:14,917 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=976, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:00:14.917399', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:00:15,900 - Inspection date 2023-10-30 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:00:15,901 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:15,901 - Inspection date 2023-10-30 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:00:15,901 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:15,901 - Inspection date 2023-10-30 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:00:15,901 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:15,901 - Inspection date 2023-10-30 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:00:15,901 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:15,901 - Inspection date 2023-10-30 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:00:15,902 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:15,902 - Inspection date 2023-10-30 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:00:15,902 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:27,411 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:00:27,413 - built Dictionary<1298 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2888 corpus positions)
-2024-11-11 08:00:27,413 - Dictionary lifecycle event {'msg': "built Dictionary<1298 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2888 corpus positions)", 'datetime': '2024-11-11T08:00:27.413887', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:00:27,415 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:00:27,415 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:00:27,415 - using serial LDA version on this node
-2024-11-11 08:00:27,415 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:00:27,416 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:00:27,419 - -8.165 per-word bound, 287.0 perplexity estimate based on a held-out corpus of 1 documents with 2888 words
-2024-11-11 08:00:27,420 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:00:27,421 - topic #0 (0.333): 0.013*"’" + 0.010*"Kent" + 0.008*"needs" + 0.006*"supported" + 0.005*"well" + 0.005*"Council" + 0.004*"need" + 0.004*"impact" + 0.004*"County" + 0.004*"leaders"
-2024-11-11 08:00:27,421 - topic #1 (0.333): 0.014*"’" + 0.007*"Kent" + 0.006*"needs" + 0.006*"well" + 0.005*"Council" + 0.005*"practice" + 0.005*"progress" + 0.005*"County" + 0.004*"2022" + 0.004*"supported"
-2024-11-11 08:00:27,421 - topic #2 (0.333): 0.023*"’" + 0.011*"Kent" + 0.007*"needs" + 0.007*"Council" + 0.007*"well" + 0.006*"County" + 0.006*"supported" + 0.005*"progress" + 0.005*"including" + 0.005*"leaders"
-2024-11-11 08:00:27,421 - topic diff=0.806915, rho=1.000000
-2024-11-11 08:00:27,421 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1298, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:00:27.421940', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:00:28,318 - Inspection date 2022-05-09 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:00:28,318 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:28,319 - Inspection date 2022-05-09 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:00:28,319 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:28,320 - Inspection date 2022-05-09 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:00:28,320 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:28,320 - Inspection date 2022-05-09 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:00:28,320 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:28,321 - Inspection date 2022-05-09 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:00:28,321 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:28,321 - Inspection date 2022-05-09 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:00:28,321 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:37,354 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:00:37,356 - built Dictionary<976 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1970 corpus positions)
-2024-11-11 08:00:37,357 - Dictionary lifecycle event {'msg': "built Dictionary<976 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1970 corpus positions)", 'datetime': '2024-11-11T08:00:37.357041', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:00:37,358 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:00:37,358 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:00:37,358 - using serial LDA version on this node
-2024-11-11 08:00:37,358 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:00:37,358 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:00:37,363 - -7.944 per-word bound, 246.3 perplexity estimate based on a held-out corpus of 1 documents with 1970 words
-2024-11-11 08:00:37,363 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:00:37,364 - topic #0 (0.333): 0.010*"’" + 0.007*"number" + 0.006*"progress" + 0.005*"planning" + 0.005*"need" + 0.005*"management" + 0.005*"risks" + 0.005*"protection" + 0.005*"Hull" + 0.005*"right"
-2024-11-11 08:00:37,364 - topic #1 (0.333): 0.013*"’" + 0.007*"number" + 0.006*"planning" + 0.006*"protection" + 0.005*"well" + 0.005*"needs" + 0.005*"Hull" + 0.005*"teams" + 0.005*"management" + 0.005*"25"
-2024-11-11 08:00:37,365 - topic #2 (0.333): 0.021*"’" + 0.008*"planning" + 0.007*"practice" + 0.007*"well" + 0.007*"number" + 0.006*"protection" + 0.006*"need" + 0.006*"Hull" + 0.005*"risks" + 0.005*"agency"
-2024-11-11 08:00:37,365 - topic diff=0.764043, rho=1.000000
-2024-11-11 08:00:37,365 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=976, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:00:37.365270', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:00:38,201 - Inspection date 2022-11-14 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:00:38,201 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:38,201 - Inspection date 2022-11-14 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:00:38,201 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:38,202 - Inspection date 2022-11-14 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:00:38,202 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:38,202 - Inspection date 2022-11-14 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:00:38,202 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:38,202 - Inspection date 2022-11-14 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:00:38,202 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:38,202 - Inspection date 2022-11-14 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:00:38,203 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:48,400 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:00:48,402 - built Dictionary<963 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2139 corpus positions)
-2024-11-11 08:00:48,403 - Dictionary lifecycle event {'msg': "built Dictionary<963 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2139 corpus positions)", 'datetime': '2024-11-11T08:00:48.403149', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:00:48,404 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:00:48,404 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:00:48,404 - using serial LDA version on this node
-2024-11-11 08:00:48,404 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:00:48,404 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:00:48,407 - -7.871 per-word bound, 234.2 perplexity estimate based on a held-out corpus of 1 documents with 2139 words
-2024-11-11 08:00:48,408 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:00:48,409 - topic #0 (0.333): 0.025*"’" + 0.008*"plans" + 0.007*"needs" + 0.007*"effective" + 0.006*"Kirklees" + 0.006*"impact" + 0.006*"quality" + 0.005*"well" + 0.005*"experiences" + 0.005*"leaders"
-2024-11-11 08:00:48,409 - topic #1 (0.333): 0.015*"’" + 0.008*"Kirklees" + 0.008*"needs" + 0.007*"effective" + 0.007*"plans" + 0.006*"well" + 0.005*"quality" + 0.005*"timely" + 0.005*"need" + 0.005*"impact"
-2024-11-11 08:00:48,409 - topic #2 (0.333): 0.021*"’" + 0.007*"Kirklees" + 0.007*"effective" + 0.007*"needs" + 0.006*"well" + 0.006*"plans" + 0.006*"need" + 0.005*"impact" + 0.005*"leaders" + 0.005*"PAs"
-2024-11-11 08:00:48,409 - topic diff=0.788971, rho=1.000000
-2024-11-11 08:00:48,409 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=963, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:00:48.409912', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:00:49,510 - Inspection date 2024-07-08 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:00:49,510 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:49,511 - Inspection date 2024-07-08 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:00:49,511 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:49,511 - Inspection date 2024-07-08 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:00:49,512 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:49,512 - Inspection date 2024-07-08 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:00:49,512 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:49,512 - Inspection date 2024-07-08 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:00:49,512 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:49,513 - Inspection date 2024-07-08 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:00:49,513 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:57,587 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:00:57,589 - built Dictionary<886 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1837 corpus positions)
-2024-11-11 08:00:57,589 - Dictionary lifecycle event {'msg': "built Dictionary<886 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1837 corpus positions)", 'datetime': '2024-11-11T08:00:57.589418', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:00:57,590 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:00:57,590 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:00:57,590 - using serial LDA version on this node
-2024-11-11 08:00:57,590 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:00:57,590 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:00:57,593 - -7.830 per-word bound, 227.5 perplexity estimate based on a held-out corpus of 1 documents with 1837 words
-2024-11-11 08:00:57,593 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:00:57,595 - topic #0 (0.333): 0.013*"’" + 0.008*"progress" + 0.008*"plans" + 0.008*"needs" + 0.006*"quality" + 0.006*"22" + 0.006*"Knowsley" + 0.005*"place" + 0.004*"need" + 0.004*"11"
-2024-11-11 08:00:57,595 - topic #1 (0.333): 0.017*"’" + 0.009*"progress" + 0.007*"plans" + 0.007*"quality" + 0.007*"2021" + 0.007*"needs" + 0.007*"Knowsley" + 0.006*"experiences" + 0.005*"good" + 0.005*"abuse"
-2024-11-11 08:00:57,595 - topic #2 (0.333): 0.013*"’" + 0.007*"needs" + 0.006*"progress" + 0.006*"quality" + 0.005*"plans" + 0.005*"need" + 0.005*"experiences" + 0.005*"Knowsley" + 0.005*"2021" + 0.005*"impact"
-2024-11-11 08:00:57,595 - topic diff=0.744443, rho=1.000000
-2024-11-11 08:00:57,596 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=886, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:00:57.595999', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:00:58,396 - Inspection date 2021-10-11 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:00:58,396 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:58,396 - Inspection date 2021-10-11 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:00:58,396 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:58,396 - Inspection date 2021-10-11 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:00:58,396 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:58,397 - Inspection date 2021-10-11 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:00:58,397 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:58,397 - Inspection date 2021-10-11 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:00:58,397 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:00:58,397 - Inspection date 2021-10-11 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:00:58,397 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:08,132 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:01:08,134 - built Dictionary<1048 unique tokens: ['0', '0161', '0300', '1', '10']...> from 1 documents (total 2263 corpus positions)
-2024-11-11 08:01:08,134 - Dictionary lifecycle event {'msg': "built Dictionary<1048 unique tokens: ['0', '0161', '0300', '1', '10']...> from 1 documents (total 2263 corpus positions)", 'datetime': '2024-11-11T08:01:08.134507', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:01:08,135 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:01:08,135 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:01:08,135 - using serial LDA version on this node
-2024-11-11 08:01:08,136 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:01:08,136 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:01:08,139 - -7.967 per-word bound, 250.2 perplexity estimate based on a held-out corpus of 1 documents with 2263 words
-2024-11-11 08:01:08,139 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:01:08,140 - topic #0 (0.333): 0.012*"’" + 0.008*"need" + 0.008*"well" + 0.007*"needs" + 0.005*"progress" + 0.005*"parents" + 0.005*"plans" + 0.005*"number" + 0.005*"9" + 0.005*"Lancashire"
-2024-11-11 08:01:08,141 - topic #1 (0.333): 0.006*"’" + 0.005*"well" + 0.005*"need" + 0.004*"plans" + 0.003*"needs" + 0.003*"9" + 0.003*"parents" + 0.003*"homes" + 0.003*"progress" + 0.003*"December"
-2024-11-11 08:01:08,141 - topic #2 (0.333): 0.023*"’" + 0.011*"well" + 0.008*"needs" + 0.008*"Lancashire" + 0.007*"need" + 0.007*"supported" + 0.006*"live" + 0.006*"plans" + 0.006*"practice" + 0.006*"positive"
-2024-11-11 08:01:08,141 - topic diff=0.821544, rho=1.000000
-2024-11-11 08:01:08,141 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1048, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:01:08.141425', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:01:09,079 - Inspection date 2022-11-28 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:01:09,079 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:09,080 - Inspection date 2022-11-28 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:01:09,080 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:09,080 - Inspection date 2022-11-28 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:01:09,080 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:09,080 - Inspection date 2022-11-28 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:01:09,081 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:09,081 - Inspection date 2022-11-28 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:01:09,081 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:09,081 - Inspection date 2022-11-28 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:01:09,081 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:19,202 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:01:19,205 - built Dictionary<1071 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2261 corpus positions)
-2024-11-11 08:01:19,206 - Dictionary lifecycle event {'msg': "built Dictionary<1071 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2261 corpus positions)", 'datetime': '2024-11-11T08:01:19.206122', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:01:19,208 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:01:19,208 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:01:19,208 - using serial LDA version on this node
-2024-11-11 08:01:19,208 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:01:19,209 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:01:19,214 - -8.007 per-word bound, 257.3 perplexity estimate based on a held-out corpus of 1 documents with 2261 words
-2024-11-11 08:01:19,214 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:01:19,216 - topic #0 (0.333): 0.020*"’" + 0.008*"Leeds" + 0.006*"needs" + 0.006*"well" + 0.005*"risk" + 0.005*"plans" + 0.005*"education" + 0.005*"supported" + 0.004*"including" + 0.004*"protection"
-2024-11-11 08:01:19,216 - topic #1 (0.333): 0.013*"’" + 0.008*"Leeds" + 0.008*"needs" + 0.007*"well" + 0.005*"practice" + 0.005*"4" + 0.005*"ensure" + 0.005*"protection" + 0.004*"risk" + 0.004*"21"
-2024-11-11 08:01:19,216 - topic #2 (0.333): 0.013*"’" + 0.007*"needs" + 0.006*"Leeds" + 0.006*"risk" + 0.004*"well" + 0.004*"March" + 0.004*"making" + 0.004*"ensure" + 0.004*"practice" + 0.004*"2022"
-2024-11-11 08:01:19,216 - topic diff=0.774715, rho=1.000000
-2024-11-11 08:01:19,217 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1071, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:01:19.217034', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:01:20,168 - Inspection date 2022-02-21 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:01:20,168 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:20,169 - Inspection date 2022-02-21 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:01:20,169 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:20,169 - Inspection date 2022-02-21 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:01:20,169 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:20,169 - Inspection date 2022-02-21 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:01:20,169 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:20,169 - Inspection date 2022-02-21 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:01:20,169 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:20,170 - Inspection date 2022-02-21 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:01:20,170 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:28,943 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:01:28,945 - built Dictionary<932 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1950 corpus positions)
-2024-11-11 08:01:28,945 - Dictionary lifecycle event {'msg': "built Dictionary<932 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1950 corpus positions)", 'datetime': '2024-11-11T08:01:28.945925', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:01:28,946 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:01:28,946 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:01:28,947 - using serial LDA version on this node
-2024-11-11 08:01:28,947 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:01:28,947 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:01:28,950 - -7.877 per-word bound, 235.0 perplexity estimate based on a held-out corpus of 1 documents with 1950 words
-2024-11-11 08:01:28,950 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:01:28,951 - topic #0 (0.333): 0.022*"’" + 0.009*"well" + 0.008*"Leicester" + 0.007*"2021" + 0.006*"needs" + 0.006*"ensure" + 0.006*"number" + 0.006*"good" + 0.006*"1" + 0.005*"20"
-2024-11-11 08:01:28,952 - topic #1 (0.333): 0.017*"’" + 0.010*"2021" + 0.009*"Leicester" + 0.008*"well" + 0.006*"needs" + 0.005*"number" + 0.005*"good" + 0.005*"improve" + 0.005*"ensure" + 0.005*"including"
-2024-11-11 08:01:28,952 - topic #2 (0.333): 0.021*"’" + 0.009*"well" + 0.009*"2021" + 0.008*"needs" + 0.007*"good" + 0.006*"Leicester" + 0.006*"ensure" + 0.006*"20" + 0.005*"including" + 0.005*"1"
-2024-11-11 08:01:28,952 - topic diff=0.776732, rho=1.000000
-2024-11-11 08:01:28,952 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=932, num_topics=3, decay=0.5, chunksize=2000> in 0.00s', 'datetime': '2024-11-11T08:01:28.952376', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:01:30,035 - Inspection date 2021-09-20 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:01:30,035 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:30,035 - Inspection date 2021-09-20 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:01:30,035 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:30,035 - Inspection date 2021-09-20 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:01:30,036 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:30,036 - Inspection date 2021-09-20 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:01:30,036 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:30,036 - Inspection date 2021-09-20 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:01:30,036 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:30,036 - Inspection date 2021-09-20 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:01:30,036 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:42,974 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:01:42,977 - built Dictionary<1223 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2745 corpus positions)
-2024-11-11 08:01:42,977 - Dictionary lifecycle event {'msg': "built Dictionary<1223 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2745 corpus positions)", 'datetime': '2024-11-11T08:01:42.977613', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:01:42,978 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:01:42,978 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:01:42,979 - using serial LDA version on this node
-2024-11-11 08:01:42,979 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:01:42,979 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:01:42,983 - -8.106 per-word bound, 275.5 perplexity estimate based on a held-out corpus of 1 documents with 2745 words
-2024-11-11 08:01:42,983 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:01:42,984 - topic #0 (0.333): 0.018*"’" + 0.009*"well" + 0.006*"progress" + 0.005*"Leicestershire" + 0.005*"ensure" + 0.005*"understand" + 0.005*"risk" + 0.005*"need" + 0.005*"plans" + 0.005*"needs"
-2024-11-11 08:01:42,984 - topic #1 (0.333): 0.015*"’" + 0.009*"well" + 0.006*"Leicestershire" + 0.005*"experiences" + 0.005*"plans" + 0.005*"family" + 0.005*"needs" + 0.005*"understand" + 0.004*"quality" + 0.004*"need"
-2024-11-11 08:01:42,984 - topic #2 (0.333): 0.020*"’" + 0.008*"well" + 0.007*"family" + 0.007*"Leicestershire" + 0.006*"needs" + 0.006*"need" + 0.005*"experiences" + 0.005*"PAs" + 0.005*"risk" + 0.005*"progress"
-2024-11-11 08:01:42,985 - topic diff=0.811363, rho=1.000000
-2024-11-11 08:01:42,985 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1223, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:01:42.985120', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:01:43,905 - Inspection date 2024-04-22 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:01:43,905 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:43,905 - Inspection date 2024-04-22 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:01:43,905 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:43,905 - Inspection date 2024-04-22 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:01:43,905 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:43,905 - Inspection date 2024-04-22 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:01:43,905 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:43,905 - Inspection date 2024-04-22 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:01:43,906 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:43,906 - Inspection date 2024-04-22 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:01:43,906 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:56,504 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:01:56,506 - built Dictionary<1323 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2927 corpus positions)
-2024-11-11 08:01:56,507 - Dictionary lifecycle event {'msg': "built Dictionary<1323 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2927 corpus positions)", 'datetime': '2024-11-11T08:01:56.507001', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:01:56,508 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:01:56,508 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:01:56,508 - using serial LDA version on this node
-2024-11-11 08:01:56,509 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:01:56,509 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:01:56,513 - -8.192 per-word bound, 292.4 perplexity estimate based on a held-out corpus of 1 documents with 2927 words
-2024-11-11 08:01:56,513 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:01:56,514 - topic #0 (0.333): 0.019*"’" + 0.006*"Lincolnshire" + 0.006*"well" + 0.004*"28" + 0.004*"need" + 0.004*"progress" + 0.004*"24" + 0.004*"family" + 0.004*"plans" + 0.004*"needs"
-2024-11-11 08:01:56,514 - topic #1 (0.333): 0.023*"’" + 0.010*"needs" + 0.008*"Lincolnshire" + 0.006*"well" + 0.005*"plans" + 0.005*"April" + 0.005*"family" + 0.005*"progress" + 0.004*"2023" + 0.004*"24"
-2024-11-11 08:01:56,515 - topic #2 (0.333): 0.021*"’" + 0.006*"Lincolnshire" + 0.005*"needs" + 0.005*"plans" + 0.005*"well" + 0.005*"progress" + 0.004*"family" + 0.004*"education" + 0.004*"24" + 0.004*"28"
-2024-11-11 08:01:56,515 - topic diff=0.791201, rho=1.000000
-2024-11-11 08:01:56,515 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1323, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:01:56.515299', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:01:57,419 - Inspection date 2023-04-24 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:01:57,419 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:57,420 - Inspection date 2023-04-24 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:01:57,420 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:57,420 - Inspection date 2023-04-24 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:01:57,420 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:57,420 - Inspection date 2023-04-24 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:01:57,420 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:57,420 - Inspection date 2023-04-24 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:01:57,420 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:01:57,420 - Inspection date 2023-04-24 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:01:57,421 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:09,299 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:02:09,302 - built Dictionary<1134 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2720 corpus positions)
-2024-11-11 08:02:09,302 - Dictionary lifecycle event {'msg': "built Dictionary<1134 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2720 corpus positions)", 'datetime': '2024-11-11T08:02:09.302397', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:02:09,303 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:02:09,303 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:02:09,303 - using serial LDA version on this node
-2024-11-11 08:02:09,304 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:02:09,304 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:02:09,307 - -7.994 per-word bound, 254.9 perplexity estimate based on a held-out corpus of 1 documents with 2720 words
-2024-11-11 08:02:09,307 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:02:09,309 - topic #0 (0.333): 0.020*"’" + 0.007*"always" + 0.007*"Liverpool" + 0.006*"needs" + 0.005*"practice" + 0.005*"quality" + 0.005*"PAs" + 0.004*"protection" + 0.004*"need" + 0.004*"24"
-2024-11-11 08:02:09,309 - topic #1 (0.333): 0.021*"’" + 0.007*"needs" + 0.007*"practice" + 0.007*"need" + 0.006*"always" + 0.006*"Liverpool" + 0.005*"quality" + 0.005*"protection" + 0.004*"met" + 0.004*"PAs"
-2024-11-11 08:02:09,309 - topic #2 (0.333): 0.017*"’" + 0.008*"needs" + 0.007*"need" + 0.007*"practice" + 0.006*"quality" + 0.006*"always" + 0.006*"13" + 0.005*"Liverpool" + 0.005*"protection" + 0.004*"senior"
-2024-11-11 08:02:09,309 - topic diff=0.838223, rho=1.000000
-2024-11-11 08:02:09,309 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1134, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:02:09.309764', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:02:10,169 - Inspection date 2023-03-13 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:02:10,169 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:10,170 - Inspection date 2023-03-13 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:02:10,170 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:10,170 - Inspection date 2023-03-13 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:02:10,170 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:10,170 - Inspection date 2023-03-13 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:02:10,170 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:10,170 - Inspection date 2023-03-13 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:02:10,170 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:10,171 - Inspection date 2023-03-13 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:02:10,171 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:21,563 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:02:21,567 - built Dictionary<1193 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2610 corpus positions)
-2024-11-11 08:02:21,568 - Dictionary lifecycle event {'msg': "built Dictionary<1193 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2610 corpus positions)", 'datetime': '2024-11-11T08:02:21.568218', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:02:21,570 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:02:21,570 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:02:21,570 - using serial LDA version on this node
-2024-11-11 08:02:21,571 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:02:21,571 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:02:21,578 - -8.093 per-word bound, 273.0 perplexity estimate based on a held-out corpus of 1 documents with 2610 words
-2024-11-11 08:02:21,578 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:02:21,580 - topic #0 (0.333): 0.022*"’" + 0.007*"needs" + 0.006*"practice" + 0.005*"well" + 0.005*"plans" + 0.005*"carers" + 0.005*"good" + 0.004*"information" + 0.004*"Dagenham" + 0.004*"progress"
-2024-11-11 08:02:21,581 - topic #1 (0.333): 0.022*"’" + 0.008*"needs" + 0.007*"good" + 0.006*"plans" + 0.005*"carers" + 0.005*"well" + 0.005*"practice" + 0.005*"progress" + 0.004*"Barking" + 0.004*"information"
-2024-11-11 08:02:21,581 - topic #2 (0.333): 0.023*"’" + 0.008*"needs" + 0.006*"plans" + 0.005*"information" + 0.005*"good" + 0.005*"e" + 0.005*"London" + 0.005*"carers" + 0.005*"planning" + 0.005*"well"
-2024-11-11 08:02:21,581 - topic diff=0.796422, rho=1.000000
-2024-11-11 08:02:21,581 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1193, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:02:21.581550', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:02:22,469 - Inspection date 2023-07-10 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:02:22,469 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:22,469 - Inspection date 2023-07-10 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:02:22,470 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:22,470 - Inspection date 2023-07-10 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:02:22,470 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:22,470 - Inspection date 2023-07-10 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:02:22,470 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:22,470 - Inspection date 2023-07-10 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:02:22,470 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:22,470 - Inspection date 2023-07-10 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:02:22,471 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:33,603 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:02:33,606 - built Dictionary<1132 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2445 corpus positions)
-2024-11-11 08:02:33,606 - Dictionary lifecycle event {'msg': "built Dictionary<1132 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2445 corpus positions)", 'datetime': '2024-11-11T08:02:33.606333', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:02:33,607 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:02:33,607 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:02:33,607 - using serial LDA version on this node
-2024-11-11 08:02:33,608 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:02:33,608 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:02:33,611 - -8.051 per-word bound, 265.3 perplexity estimate based on a held-out corpus of 1 documents with 2445 words
-2024-11-11 08:02:33,611 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:02:33,613 - topic #0 (0.333): 0.022*"’" + 0.010*"needs" + 0.008*"Barnet" + 0.007*"plans" + 0.006*"well" + 0.005*"10" + 0.005*"experiences" + 0.005*"strong" + 0.005*"risk" + 0.004*"progress"
-2024-11-11 08:02:33,613 - topic #1 (0.333): 0.022*"’" + 0.010*"needs" + 0.009*"well" + 0.008*"plans" + 0.007*"Barnet" + 0.004*"June" + 0.004*"experiences" + 0.004*"14" + 0.004*"carers" + 0.004*"information"
-2024-11-11 08:02:33,613 - topic #2 (0.333): 0.017*"’" + 0.006*"well" + 0.006*"Barnet" + 0.006*"plans" + 0.006*"needs" + 0.004*"risk" + 0.004*"understand" + 0.004*"June" + 0.004*"progress" + 0.004*"experiences"
-2024-11-11 08:02:33,613 - topic diff=0.787417, rho=1.000000
-2024-11-11 08:02:33,613 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1132, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:02:33.613531', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:02:34,521 - Inspection date 2024-06-10 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:02:34,521 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:34,522 - Inspection date 2024-06-10 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:02:34,522 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:34,522 - Inspection date 2024-06-10 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:02:34,522 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:34,522 - Inspection date 2024-06-10 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:02:34,522 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:34,522 - Inspection date 2024-06-10 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:02:34,522 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:34,522 - Inspection date 2024-06-10 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:02:34,522 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:46,108 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:02:46,110 - built Dictionary<1190 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2563 corpus positions)
-2024-11-11 08:02:46,110 - Dictionary lifecycle event {'msg': "built Dictionary<1190 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2563 corpus positions)", 'datetime': '2024-11-11T08:02:46.110724', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:02:46,111 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:02:46,112 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:02:46,112 - using serial LDA version on this node
-2024-11-11 08:02:46,112 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:02:46,112 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:02:46,116 - -8.098 per-word bound, 274.0 perplexity estimate based on a held-out corpus of 1 documents with 2563 words
-2024-11-11 08:02:46,116 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:02:46,117 - topic #0 (0.333): 0.015*"’" + 0.006*"plans" + 0.006*"effective" + 0.005*"need" + 0.005*"needs" + 0.004*"well" + 0.004*"education" + 0.004*"10" + 0.004*"oversight" + 0.004*"make"
-2024-11-11 08:02:46,117 - topic #1 (0.333): 0.025*"’" + 0.007*"well" + 0.007*"needs" + 0.007*"Bexley" + 0.006*"need" + 0.005*"effective" + 0.005*"including" + 0.005*"plans" + 0.005*"practice" + 0.005*"6"
-2024-11-11 08:02:46,118 - topic #2 (0.333): 0.013*"’" + 0.005*"needs" + 0.005*"well" + 0.005*"effective" + 0.005*"plans" + 0.004*"10" + 0.004*"progress" + 0.004*"need" + 0.004*"Bexley" + 0.004*"helps"
-2024-11-11 08:02:46,118 - topic diff=0.798125, rho=1.000000
-2024-11-11 08:02:46,118 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1190, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:02:46.118376', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:02:47,210 - Inspection date 2023-02-06 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:02:47,210 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:47,210 - Inspection date 2023-02-06 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:02:47,210 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:47,211 - Inspection date 2023-02-06 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:02:47,211 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:47,211 - Inspection date 2023-02-06 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:02:47,211 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:47,211 - Inspection date 2023-02-06 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:02:47,211 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:47,211 - Inspection date 2023-02-06 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:02:47,211 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:57,810 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:02:57,812 - built Dictionary<1038 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2371 corpus positions)
-2024-11-11 08:02:57,812 - Dictionary lifecycle event {'msg': "built Dictionary<1038 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2371 corpus positions)", 'datetime': '2024-11-11T08:02:57.812700', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:02:57,813 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:02:57,813 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:02:57,814 - using serial LDA version on this node
-2024-11-11 08:02:57,814 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:02:57,814 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:02:57,817 - -7.929 per-word bound, 243.7 perplexity estimate based on a held-out corpus of 1 documents with 2371 words
-2024-11-11 08:02:57,817 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:02:57,819 - topic #0 (0.333): 0.012*"’" + 0.006*"well" + 0.006*"plans" + 0.006*"good" + 0.006*"leaders" + 0.005*"progress" + 0.005*"family" + 0.005*"number" + 0.005*"Brent" + 0.005*"quality"
-2024-11-11 08:02:57,819 - topic #1 (0.333): 0.020*"’" + 0.011*"well" + 0.008*"leaders" + 0.007*"progress" + 0.007*"number" + 0.006*"Brent" + 0.006*"plans" + 0.006*"practice" + 0.006*"quality" + 0.005*"However"
-2024-11-11 08:02:57,819 - topic #2 (0.333): 0.018*"’" + 0.008*"well" + 0.007*"plans" + 0.007*"leaders" + 0.006*"good" + 0.005*"progress" + 0.005*"timely" + 0.005*"senior" + 0.005*"range" + 0.005*"quality"
-2024-11-11 08:02:57,819 - topic diff=0.828107, rho=1.000000
-2024-11-11 08:02:57,819 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1038, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:02:57.819640', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:02:58,702 - Inspection date 2023-02-20 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:02:58,703 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:58,703 - Inspection date 2023-02-20 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:02:58,703 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:58,703 - Inspection date 2023-02-20 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:02:58,703 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:58,703 - Inspection date 2023-02-20 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:02:58,703 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:58,704 - Inspection date 2023-02-20 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:02:58,704 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:02:58,704 - Inspection date 2023-02-20 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:02:58,704 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:11,449 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:03:11,451 - built Dictionary<1266 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2640 corpus positions)
-2024-11-11 08:03:11,452 - Dictionary lifecycle event {'msg': "built Dictionary<1266 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2640 corpus positions)", 'datetime': '2024-11-11T08:03:11.452067', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:03:11,453 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:03:11,453 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:03:11,453 - using serial LDA version on this node
-2024-11-11 08:03:11,453 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:03:11,454 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:03:11,457 - -8.186 per-word bound, 291.3 perplexity estimate based on a held-out corpus of 1 documents with 2640 words
-2024-11-11 08:03:11,457 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:03:11,459 - topic #0 (0.333): 0.020*"’" + 0.009*"Bromley" + 0.008*"needs" + 0.006*"plans" + 0.006*"practice" + 0.005*"well" + 0.005*"leaders" + 0.004*"receive" + 0.004*"health" + 0.004*"education"
-2024-11-11 08:03:11,459 - topic #1 (0.333): 0.021*"’" + 0.008*"Bromley" + 0.008*"well" + 0.006*"needs" + 0.005*"leaders" + 0.004*"plans" + 0.004*"practice" + 0.004*"17" + 0.004*"health" + 0.004*"progress"
-2024-11-11 08:03:11,459 - topic #2 (0.333): 0.018*"’" + 0.009*"Bromley" + 0.007*"well" + 0.006*"needs" + 0.006*"plans" + 0.005*"education" + 0.005*"leaders" + 0.005*"health" + 0.005*"practice" + 0.005*"experiences"
-2024-11-11 08:03:11,459 - topic diff=0.768196, rho=1.000000
-2024-11-11 08:03:11,459 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1266, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:03:11.459729', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:03:12,468 - Inspection date 2023-11-13 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:03:12,469 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:12,469 - Inspection date 2023-11-13 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:03:12,469 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:12,469 - Inspection date 2023-11-13 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:03:12,469 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:12,469 - Inspection date 2023-11-13 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:03:12,469 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:12,470 - Inspection date 2023-11-13 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:03:12,470 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:12,470 - Inspection date 2023-11-13 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:03:12,470 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:20,986 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:03:20,988 - built Dictionary<993 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1735 corpus positions)
-2024-11-11 08:03:20,988 - Dictionary lifecycle event {'msg': "built Dictionary<993 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1735 corpus positions)", 'datetime': '2024-11-11T08:03:20.988561', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:03:20,989 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:03:20,989 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:03:20,989 - using serial LDA version on this node
-2024-11-11 08:03:20,990 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:03:20,990 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:03:20,993 - -8.061 per-word bound, 267.1 perplexity estimate based on a held-out corpus of 1 documents with 1735 words
-2024-11-11 08:03:20,993 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:03:20,994 - topic #0 (0.333): 0.011*"’" + 0.008*"Camden" + 0.007*"well" + 0.005*"practice" + 0.005*"leaders" + 0.005*"needs" + 0.005*"response" + 0.004*"protection" + 0.004*"appropriate" + 0.004*"meetings"
-2024-11-11 08:03:20,994 - topic #1 (0.333): 0.009*"’" + 0.007*"leaders" + 0.007*"practice" + 0.006*"Camden" + 0.005*"29" + 0.005*"protection" + 0.004*"progress" + 0.004*"response" + 0.004*"25" + 0.004*"health"
-2024-11-11 08:03:20,995 - topic #2 (0.333): 0.011*"’" + 0.007*"Camden" + 0.007*"leaders" + 0.006*"needs" + 0.005*"practice" + 0.005*"protection" + 0.005*"well" + 0.004*"2022" + 0.004*"response" + 0.004*"25"
-2024-11-11 08:03:20,995 - topic diff=0.697217, rho=1.000000
-2024-11-11 08:03:20,995 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=993, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:03:20.995266', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:03:21,903 - Inspection date 2022-04-25 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:03:21,904 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:21,904 - Inspection date 2022-04-25 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:03:21,904 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:21,905 - Inspection date 2022-04-25 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:03:21,905 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:21,905 - Inspection date 2022-04-25 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:03:21,905 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:21,906 - Inspection date 2022-04-25 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:03:21,906 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:21,906 - Inspection date 2022-04-25 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:03:21,906 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:32,159 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:03:32,161 - built Dictionary<1046 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2209 corpus positions)
-2024-11-11 08:03:32,161 - Dictionary lifecycle event {'msg': "built Dictionary<1046 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2209 corpus positions)", 'datetime': '2024-11-11T08:03:32.161693', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:03:32,162 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:03:32,162 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:03:32,162 - using serial LDA version on this node
-2024-11-11 08:03:32,163 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:03:32,163 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:03:32,166 - -7.989 per-word bound, 254.0 perplexity estimate based on a held-out corpus of 1 documents with 2209 words
-2024-11-11 08:03:32,166 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:03:32,167 - topic #0 (0.333): 0.013*"’" + 0.008*"needs" + 0.007*"well" + 0.006*"Croydon" + 0.005*"Senior" + 0.005*"ensure" + 0.005*"effective" + 0.005*"need" + 0.004*"arrangements" + 0.004*"risk"
-2024-11-11 08:03:32,168 - topic #1 (0.333): 0.013*"’" + 0.008*"well" + 0.008*"needs" + 0.007*"need" + 0.006*"good" + 0.006*"Croydon" + 0.005*"Senior" + 0.005*"ensure" + 0.005*"quality" + 0.005*"effective"
-2024-11-11 08:03:32,168 - topic #2 (0.333): 0.010*"’" + 0.006*"quality" + 0.006*"well" + 0.005*"health" + 0.005*"Senior" + 0.005*"needs" + 0.005*"Croydon" + 0.005*"plans" + 0.004*"ensure" + 0.004*"education"
-2024-11-11 08:03:32,168 - topic diff=0.769095, rho=1.000000
-2024-11-11 08:03:32,168 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1046, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:03:32.168463', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:03:33,375 - Inspection date 2020-02-03 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:03:33,376 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:33,376 - Inspection date 2020-02-03 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:03:33,376 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:33,376 - Inspection date 2020-02-03 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:03:33,376 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:33,376 - Inspection date 2020-02-03 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:03:33,376 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:33,376 - Inspection date 2020-02-03 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:03:33,376 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:33,377 - Inspection date 2020-02-03 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:03:33,377 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:44,372 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:03:44,375 - built Dictionary<1119 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2365 corpus positions)
-2024-11-11 08:03:44,375 - Dictionary lifecycle event {'msg': "built Dictionary<1119 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2365 corpus positions)", 'datetime': '2024-11-11T08:03:44.375209', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:03:44,376 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:03:44,376 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:03:44,376 - using serial LDA version on this node
-2024-11-11 08:03:44,376 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:03:44,377 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:03:44,380 - -8.050 per-word bound, 265.0 perplexity estimate based on a held-out corpus of 1 documents with 2365 words
-2024-11-11 08:03:44,380 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:03:44,381 - topic #0 (0.333): 0.013*"’" + 0.007*"Ealing" + 0.006*"plans" + 0.006*"progress" + 0.005*"well" + 0.005*"3" + 0.005*"needs" + 0.004*"impact" + 0.004*"health" + 0.004*"including"
-2024-11-11 08:03:44,382 - topic #1 (0.333): 0.018*"’" + 0.007*"Ealing" + 0.007*"progress" + 0.007*"well" + 0.006*"plans" + 0.006*"needs" + 0.006*"need" + 0.006*"effective" + 0.006*"London" + 0.005*"22"
-2024-11-11 08:03:44,382 - topic #2 (0.333): 0.019*"’" + 0.009*"Ealing" + 0.009*"well" + 0.006*"needs" + 0.005*"need" + 0.005*"effective" + 0.005*"including" + 0.005*"May" + 0.004*"22" + 0.004*"quality"
-2024-11-11 08:03:44,382 - topic diff=0.786797, rho=1.000000
-2024-11-11 08:03:44,382 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1119, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:03:44.382366', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:03:45,283 - Inspection date 2024-04-22 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:03:45,283 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:45,284 - Inspection date 2024-04-22 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:03:45,284 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:45,284 - Inspection date 2024-04-22 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:03:45,284 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:45,284 - Inspection date 2024-04-22 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:03:45,284 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:45,284 - Inspection date 2024-04-22 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:03:45,284 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:45,284 - Inspection date 2024-04-22 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:03:45,285 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:55,910 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:03:55,912 - built Dictionary<1108 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2531 corpus positions)
-2024-11-11 08:03:55,912 - Dictionary lifecycle event {'msg': "built Dictionary<1108 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2531 corpus positions)", 'datetime': '2024-11-11T08:03:55.912716', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:03:55,913 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:03:55,913 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:03:55,914 - using serial LDA version on this node
-2024-11-11 08:03:55,914 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:03:55,914 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:03:55,918 - -8.001 per-word bound, 256.2 perplexity estimate based on a held-out corpus of 1 documents with 2531 words
-2024-11-11 08:03:55,918 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:03:55,919 - topic #0 (0.333): 0.015*"’" + 0.009*"needs" + 0.007*"well" + 0.006*"Enfield" + 0.005*"plans" + 0.004*"protection" + 0.004*"timely" + 0.004*"access" + 0.004*"ensure" + 0.004*"good"
-2024-11-11 08:03:55,919 - topic #1 (0.333): 0.018*"’" + 0.012*"needs" + 0.010*"well" + 0.009*"plans" + 0.008*"Enfield" + 0.007*"need" + 0.006*"receive" + 0.005*"timely" + 0.005*"practice" + 0.005*"good"
-2024-11-11 08:03:55,919 - topic #2 (0.333): 0.016*"’" + 0.009*"well" + 0.008*"needs" + 0.006*"Enfield" + 0.005*"practice" + 0.005*"plans" + 0.005*"need" + 0.004*"timely" + 0.004*"good" + 0.004*"receive"
-2024-11-11 08:03:55,919 - topic diff=0.807583, rho=1.000000
-2024-11-11 08:03:55,920 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1108, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:03:55.919994', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:03:56,851 - Inspection date 2024-07-22 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:03:56,852 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:56,852 - Inspection date 2024-07-22 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:03:56,852 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:56,852 - Inspection date 2024-07-22 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:03:56,852 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:56,852 - Inspection date 2024-07-22 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:03:56,852 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:56,853 - Inspection date 2024-07-22 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:03:56,853 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:03:56,853 - Inspection date 2024-07-22 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:03:56,853 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:06,882 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:04:06,884 - built Dictionary<1023 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2078 corpus positions)
-2024-11-11 08:04:06,884 - Dictionary lifecycle event {'msg': "built Dictionary<1023 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2078 corpus positions)", 'datetime': '2024-11-11T08:04:06.884262', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:04:06,885 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:04:06,885 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:04:06,885 - using serial LDA version on this node
-2024-11-11 08:04:06,885 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:04:06,885 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:04:06,889 - -7.990 per-word bound, 254.2 perplexity estimate based on a held-out corpus of 1 documents with 2078 words
-2024-11-11 08:04:06,889 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:04:06,891 - topic #0 (0.333): 0.016*"’" + 0.011*"Greenwich" + 0.006*"needs" + 0.006*"well" + 0.006*"plans" + 0.005*"provide" + 0.005*"2024" + 0.005*"progress" + 0.004*"carers" + 0.004*"3"
-2024-11-11 08:04:06,891 - topic #1 (0.333): 0.018*"’" + 0.009*"Greenwich" + 0.009*"needs" + 0.008*"well" + 0.006*"3" + 0.005*"7" + 0.005*"plans" + 0.005*"provide" + 0.005*"progress" + 0.004*"Royal"
-2024-11-11 08:04:06,891 - topic #2 (0.333): 0.018*"’" + 0.012*"Greenwich" + 0.007*"well" + 0.006*"plans" + 0.006*"needs" + 0.004*"2024" + 0.004*"progress" + 0.004*"June" + 0.004*"Borough" + 0.004*"7"
-2024-11-11 08:04:06,891 - topic diff=0.759815, rho=1.000000
-2024-11-11 08:04:06,891 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1023, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:04:06.891727', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:04:07,786 - Inspection date 2024-06-03 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:04:07,787 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:07,787 - Inspection date 2024-06-03 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:04:07,787 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:07,787 - Inspection date 2024-06-03 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:04:07,787 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:07,787 - Inspection date 2024-06-03 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:04:07,787 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:07,788 - Inspection date 2024-06-03 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:04:07,788 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:07,788 - Inspection date 2024-06-03 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:04:07,788 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:20,810 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:04:20,812 - built Dictionary<1222 unique tokens: ["'s", '0161', '0300', '1', '10']...> from 1 documents (total 2748 corpus positions)
-2024-11-11 08:04:20,813 - Dictionary lifecycle event {'msg': 'built Dictionary<1222 unique tokens: ["\'s", \'0161\', \'0300\', \'1\', \'10\']...> from 1 documents (total 2748 corpus positions)', 'datetime': '2024-11-11T08:04:20.813012', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:04:20,814 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:04:20,814 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:04:20,814 - using serial LDA version on this node
-2024-11-11 08:04:20,814 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:04:20,815 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:04:20,818 - -8.098 per-word bound, 274.0 perplexity estimate based on a held-out corpus of 1 documents with 2748 words
-2024-11-11 08:04:20,818 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:04:20,820 - topic #0 (0.333): 0.023*"’" + 0.012*"Hackney" + 0.008*"needs" + 0.006*"need" + 0.005*"well" + 0.005*"12" + 0.005*"1" + 0.005*"effective" + 0.005*"carers" + 0.004*"timely"
-2024-11-11 08:04:20,820 - topic #1 (0.333): 0.012*"’" + 0.006*"Hackney" + 0.006*"needs" + 0.005*"well" + 0.005*"carers" + 0.004*"12" + 0.004*"practice" + 0.004*"need" + 0.004*"oversight" + 0.004*"progress"
-2024-11-11 08:04:20,820 - topic #2 (0.333): 0.014*"’" + 0.008*"needs" + 0.007*"Hackney" + 0.006*"carers" + 0.005*"well" + 0.005*"Leaders" + 0.004*"leaders" + 0.004*"practice" + 0.004*"understand" + 0.004*"offer"
-2024-11-11 08:04:20,820 - topic diff=0.810499, rho=1.000000
-2024-11-11 08:04:20,820 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1222, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:04:20.820720', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:04:21,734 - Inspection date 2024-07-01 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:04:21,734 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:21,734 - Inspection date 2024-07-01 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:04:21,734 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:21,735 - Inspection date 2024-07-01 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:04:21,735 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:21,735 - Inspection date 2024-07-01 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:04:21,735 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:21,735 - Inspection date 2024-07-01 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:04:21,735 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:21,735 - Inspection date 2024-07-01 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:04:21,735 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:34,667 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:04:34,670 - built Dictionary<1330 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2905 corpus positions)
-2024-11-11 08:04:34,670 - Dictionary lifecycle event {'msg': "built Dictionary<1330 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2905 corpus positions)", 'datetime': '2024-11-11T08:04:34.670555', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:04:34,671 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:04:34,672 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:04:34,672 - using serial LDA version on this node
-2024-11-11 08:04:34,672 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:04:34,672 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:04:34,676 - -8.203 per-word bound, 294.6 perplexity estimate based on a held-out corpus of 1 documents with 2905 words
-2024-11-11 08:04:34,676 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:04:34,678 - topic #0 (0.333): 0.014*"’" + 0.006*"well" + 0.005*"receive" + 0.005*"needs" + 0.005*"effective" + 0.005*"leaders" + 0.005*"Hammersmith" + 0.004*"Fulham" + 0.004*"protection" + 0.004*"timely"
-2024-11-11 08:04:34,678 - topic #1 (0.333): 0.015*"’" + 0.007*"well" + 0.006*"receive" + 0.005*"Fulham" + 0.005*"needs" + 0.005*"supported" + 0.004*"15" + 0.004*"Hammersmith" + 0.004*"leaders" + 0.004*"need"
-2024-11-11 08:04:34,678 - topic #2 (0.333): 0.016*"’" + 0.008*"well" + 0.005*"needs" + 0.005*"plans" + 0.005*"receive" + 0.005*"11" + 0.004*"practice" + 0.004*"Leaders" + 0.004*"2024" + 0.004*"March"
-2024-11-11 08:04:34,678 - topic diff=0.798118, rho=1.000000
-2024-11-11 08:04:34,679 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1330, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:04:34.679017', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:04:35,582 - Inspection date 2024-03-11 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:04:35,582 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:35,582 - Inspection date 2024-03-11 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:04:35,582 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:35,582 - Inspection date 2024-03-11 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:04:35,582 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:35,582 - Inspection date 2024-03-11 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:04:35,582 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:35,582 - Inspection date 2024-03-11 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:04:35,583 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:35,583 - Inspection date 2024-03-11 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:04:35,583 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:47,711 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:04:47,713 - built Dictionary<1252 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2620 corpus positions)
-2024-11-11 08:04:47,714 - Dictionary lifecycle event {'msg': "built Dictionary<1252 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2620 corpus positions)", 'datetime': '2024-11-11T08:04:47.714116', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:04:47,715 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:04:47,715 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:04:47,715 - using serial LDA version on this node
-2024-11-11 08:04:47,716 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:04:47,716 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:04:47,719 - -8.171 per-word bound, 288.2 perplexity estimate based on a held-out corpus of 1 documents with 2620 words
-2024-11-11 08:04:47,719 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:04:47,721 - topic #0 (0.333): 0.014*"’" + 0.008*"Haringey" + 0.006*"needs" + 0.006*"good" + 0.006*"plans" + 0.005*"well" + 0.005*"need" + 0.004*"education" + 0.004*"training" + 0.004*"supported"
-2024-11-11 08:04:47,721 - topic #1 (0.333): 0.016*"’" + 0.010*"Haringey" + 0.009*"needs" + 0.008*"plans" + 0.006*"well" + 0.006*"need" + 0.005*"good" + 0.004*"risk" + 0.004*"impact" + 0.004*"24"
-2024-11-11 08:04:47,721 - topic #2 (0.333): 0.016*"’" + 0.007*"needs" + 0.007*"Haringey" + 0.006*"plans" + 0.006*"progress" + 0.005*"well" + 0.005*"risk" + 0.005*"good" + 0.005*"supported" + 0.004*"timely"
-2024-11-11 08:04:47,721 - topic diff=0.771680, rho=1.000000
-2024-11-11 08:04:47,721 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1252, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:04:47.721814', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:04:48,617 - Inspection date 2023-02-13 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:04:48,617 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:48,618 - Inspection date 2023-02-13 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:04:48,618 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:48,618 - Inspection date 2023-02-13 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:04:48,618 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:48,618 - Inspection date 2023-02-13 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:04:48,618 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:48,618 - Inspection date 2023-02-13 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:04:48,618 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:48,618 - Inspection date 2023-02-13 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:04:48,618 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:56,584 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:04:56,586 - built Dictionary<942 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1732 corpus positions)
-2024-11-11 08:04:56,586 - Dictionary lifecycle event {'msg': "built Dictionary<942 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1732 corpus positions)", 'datetime': '2024-11-11T08:04:56.586319', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:04:56,587 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:04:56,587 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:04:56,587 - using serial LDA version on this node
-2024-11-11 08:04:56,587 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:04:56,587 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:04:56,590 - -7.972 per-word bound, 251.2 perplexity estimate based on a held-out corpus of 1 documents with 1732 words
-2024-11-11 08:04:56,590 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:04:56,592 - topic #0 (0.333): 0.014*"’" + 0.011*"good" + 0.009*"needs" + 0.009*"well" + 0.006*"impact" + 0.006*"protection" + 0.005*"need" + 0.005*"plans" + 0.005*"practice" + 0.004*"experiences"
-2024-11-11 08:04:56,592 - topic #1 (0.333): 0.012*"good" + 0.010*"’" + 0.009*"well" + 0.007*"needs" + 0.007*"early" + 0.006*"plans" + 0.005*"experiences" + 0.005*"practice" + 0.005*"need" + 0.005*"protection"
-2024-11-11 08:04:56,592 - topic #2 (0.333): 0.010*"’" + 0.007*"good" + 0.007*"needs" + 0.006*"well" + 0.005*"impact" + 0.004*"practice" + 0.004*"plans" + 0.004*"school" + 0.003*"need" + 0.003*"experiences"
-2024-11-11 08:04:56,592 - topic diff=0.701911, rho=1.000000
-2024-11-11 08:04:56,592 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=942, num_topics=3, decay=0.5, chunksize=2000> in 0.00s', 'datetime': '2024-11-11T08:04:56.592665', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:04:58,297 - Inspection date 2020-02-10 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:04:58,297 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:58,298 - Inspection date 2020-02-10 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:04:58,298 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:58,298 - Inspection date 2020-02-10 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:04:58,298 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:58,298 - Inspection date 2020-02-10 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:04:58,298 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:58,298 - Inspection date 2020-02-10 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:04:58,298 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:04:58,298 - Inspection date 2020-02-10 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:04:58,299 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:08,699 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:05:08,702 - built Dictionary<1069 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2243 corpus positions)
-2024-11-11 08:05:08,702 - Dictionary lifecycle event {'msg': "built Dictionary<1069 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2243 corpus positions)", 'datetime': '2024-11-11T08:05:08.702343', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:05:08,703 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:05:08,703 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:05:08,703 - using serial LDA version on this node
-2024-11-11 08:05:08,704 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:05:08,704 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:05:08,707 - -8.017 per-word bound, 259.0 perplexity estimate based on a held-out corpus of 1 documents with 2243 words
-2024-11-11 08:05:08,707 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:05:08,708 - topic #0 (0.333): 0.023*"’" + 0.013*"Havering" + 0.010*"quality" + 0.007*"plans" + 0.006*"effective" + 0.006*"oversight" + 0.005*"needs" + 0.005*"11" + 0.004*"22" + 0.004*"practice"
-2024-11-11 08:05:08,709 - topic #1 (0.333): 0.014*"’" + 0.011*"Havering" + 0.008*"plans" + 0.007*"quality" + 0.005*"oversight" + 0.004*"many" + 0.004*"effective" + 0.004*"22" + 0.004*"needs" + 0.004*"11"
-2024-11-11 08:05:08,709 - topic #2 (0.333): 0.011*"’" + 0.008*"Havering" + 0.006*"plans" + 0.006*"quality" + 0.004*"effective" + 0.004*"11" + 0.004*"needs" + 0.004*"December" + 0.004*"oversight" + 0.003*"education"
-2024-11-11 08:05:08,709 - topic diff=0.791224, rho=1.000000
-2024-11-11 08:05:08,709 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1069, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:05:08.709473', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:05:09,572 - Inspection date 2023-12-11 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:05:09,572 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:09,572 - Inspection date 2023-12-11 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:05:09,572 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:09,572 - Inspection date 2023-12-11 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:05:09,573 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:09,573 - Inspection date 2023-12-11 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:05:09,573 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:09,573 - Inspection date 2023-12-11 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:05:09,573 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:09,573 - Inspection date 2023-12-11 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:05:09,573 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:20,032 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:05:20,034 - built Dictionary<1161 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2511 corpus positions)
-2024-11-11 08:05:20,034 - Dictionary lifecycle event {'msg': "built Dictionary<1161 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2511 corpus positions)", 'datetime': '2024-11-11T08:05:20.034623', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:05:20,035 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:05:20,035 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:05:20,036 - using serial LDA version on this node
-2024-11-11 08:05:20,036 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:05:20,036 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:05:20,040 - -8.077 per-word bound, 270.0 perplexity estimate based on a held-out corpus of 1 documents with 2511 words
-2024-11-11 08:05:20,040 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:05:20,041 - topic #0 (0.333): 0.018*"’" + 0.011*"needs" + 0.008*"Hillingdon" + 0.008*"well" + 0.008*"plans" + 0.005*"team" + 0.004*"2" + 0.004*"leaders" + 0.004*"receive" + 0.004*"6"
-2024-11-11 08:05:20,041 - topic #1 (0.333): 0.017*"’" + 0.007*"well" + 0.007*"Hillingdon" + 0.007*"needs" + 0.007*"plans" + 0.005*"need" + 0.004*"6" + 0.004*"team" + 0.004*"2" + 0.003*"practice"
-2024-11-11 08:05:20,041 - topic #2 (0.333): 0.018*"’" + 0.009*"needs" + 0.008*"plans" + 0.008*"Hillingdon" + 0.007*"well" + 0.005*"team" + 0.004*"need" + 0.004*"2023" + 0.004*"experiences" + 0.004*"family"
-2024-11-11 08:05:20,041 - topic diff=0.792238, rho=1.000000
-2024-11-11 08:05:20,041 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1161, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:05:20.041913', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:05:20,936 - Inspection date 2023-10-02 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:05:20,936 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:20,936 - Inspection date 2023-10-02 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:05:20,937 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:20,937 - Inspection date 2023-10-02 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:05:20,937 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:20,937 - Inspection date 2023-10-02 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:05:20,937 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:20,937 - Inspection date 2023-10-02 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:05:20,937 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:20,938 - Inspection date 2023-10-02 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:05:20,938 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:31,705 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:05:31,707 - built Dictionary<1070 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2271 corpus positions)
-2024-11-11 08:05:31,707 - Dictionary lifecycle event {'msg': "built Dictionary<1070 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2271 corpus positions)", 'datetime': '2024-11-11T08:05:31.707826', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:05:31,708 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:05:31,708 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:05:31,709 - using serial LDA version on this node
-2024-11-11 08:05:31,709 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:05:31,709 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:05:31,713 - -8.006 per-word bound, 257.0 perplexity estimate based on a held-out corpus of 1 documents with 2271 words
-2024-11-11 08:05:31,713 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:05:31,714 - topic #0 (0.333): 0.017*"’" + 0.009*"well" + 0.008*"needs" + 0.007*"effective" + 0.005*"Hounslow" + 0.005*"timely" + 0.005*"plans" + 0.004*"strong" + 0.004*"16" + 0.004*"oversight"
-2024-11-11 08:05:31,714 - topic #1 (0.333): 0.023*"’" + 0.011*"needs" + 0.010*"well" + 0.007*"Hounslow" + 0.006*"timely" + 0.006*"effective" + 0.005*"plans" + 0.005*"senior" + 0.005*"progress" + 0.004*"20"
-2024-11-11 08:05:31,714 - topic #2 (0.333): 0.018*"’" + 0.013*"needs" + 0.010*"well" + 0.009*"effective" + 0.008*"Hounslow" + 0.007*"timely" + 0.006*"plans" + 0.005*"experiences" + 0.005*"strong" + 0.005*"16"
-2024-11-11 08:05:31,714 - topic diff=0.784634, rho=1.000000
-2024-11-11 08:05:31,714 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1070, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:05:31.714893', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:05:32,818 - Inspection date 2023-10-16 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:05:32,819 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:32,819 - Inspection date 2023-10-16 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:05:32,819 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:32,820 - Inspection date 2023-10-16 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:05:32,820 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:32,820 - Inspection date 2023-10-16 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:05:32,820 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:32,820 - Inspection date 2023-10-16 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:05:32,820 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:32,821 - Inspection date 2023-10-16 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:05:32,821 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:40,954 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:05:40,956 - built Dictionary<968 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1982 corpus positions)
-2024-11-11 08:05:40,956 - Dictionary lifecycle event {'msg': "built Dictionary<968 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1982 corpus positions)", 'datetime': '2024-11-11T08:05:40.956705', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:05:40,957 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:05:40,957 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:05:40,957 - using serial LDA version on this node
-2024-11-11 08:05:40,958 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:05:40,958 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:05:40,961 - -7.924 per-word bound, 242.9 perplexity estimate based on a held-out corpus of 1 documents with 1982 words
-2024-11-11 08:05:40,961 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:05:40,962 - topic #0 (0.333): 0.010*"’" + 0.010*"needs" + 0.007*"well" + 0.006*"plans" + 0.005*"good" + 0.005*"effective" + 0.005*"highly" + 0.005*"quality" + 0.004*"risk" + 0.004*"leaders"
-2024-11-11 08:05:40,963 - topic #1 (0.333): 0.014*"’" + 0.010*"well" + 0.009*"needs" + 0.006*"highly" + 0.006*"plans" + 0.005*"quality" + 0.005*"practice" + 0.005*"risk" + 0.005*"good" + 0.004*"effective"
-2024-11-11 08:05:40,963 - topic #2 (0.333): 0.013*"needs" + 0.013*"’" + 0.012*"well" + 0.007*"plans" + 0.007*"good" + 0.006*"leaders" + 0.006*"Islington" + 0.006*"quality" + 0.006*"highly" + 0.006*"effective"
-2024-11-11 08:05:40,963 - topic diff=0.745706, rho=1.000000
-2024-11-11 08:05:40,963 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=968, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:05:40.963515', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:05:42,635 - Inspection date 2020-03-09 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:05:42,635 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:42,635 - Inspection date 2020-03-09 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:05:42,635 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:42,635 - Inspection date 2020-03-09 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:05:42,635 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:42,636 - Inspection date 2020-03-09 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:05:42,636 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:42,636 - Inspection date 2020-03-09 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:05:42,636 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:42,636 - Inspection date 2020-03-09 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:05:42,636 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:53,079 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:05:53,083 - built Dictionary<976 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2090 corpus positions)
-2024-11-11 08:05:53,083 - Dictionary lifecycle event {'msg': "built Dictionary<976 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2090 corpus positions)", 'datetime': '2024-11-11T08:05:53.083770', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:05:53,085 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:05:53,085 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:05:53,086 - using serial LDA version on this node
-2024-11-11 08:05:53,086 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:05:53,086 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:05:53,092 - -7.908 per-word bound, 240.1 perplexity estimate based on a held-out corpus of 1 documents with 2090 words
-2024-11-11 08:05:53,092 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:05:53,094 - topic #0 (0.333): 0.015*"’" + 0.009*"well" + 0.009*"needs" + 0.007*"plans" + 0.007*"good" + 0.007*"Lambeth" + 0.006*"need" + 0.005*"4" + 0.005*"leaders" + 0.005*"progress"
-2024-11-11 08:05:53,094 - topic #1 (0.333): 0.012*"’" + 0.010*"needs" + 0.008*"well" + 0.007*"good" + 0.007*"plans" + 0.006*"Lambeth" + 0.006*"progress" + 0.005*"leaders" + 0.005*"4" + 0.005*"impact"
-2024-11-11 08:05:53,095 - topic #2 (0.333): 0.018*"’" + 0.008*"plans" + 0.007*"needs" + 0.007*"well" + 0.006*"need" + 0.006*"progress" + 0.006*"good" + 0.005*"Lambeth" + 0.005*"impact" + 0.005*"Leaders"
-2024-11-11 08:05:53,095 - topic diff=0.799817, rho=1.000000
-2024-11-11 08:05:53,095 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=976, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:05:53.095442', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:05:54,090 - Inspection date 2022-10-24 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:05:54,090 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:54,090 - Inspection date 2022-10-24 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:05:54,090 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:54,090 - Inspection date 2022-10-24 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:05:54,090 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:54,091 - Inspection date 2022-10-24 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:05:54,091 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:54,091 - Inspection date 2022-10-24 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:05:54,091 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:05:54,091 - Inspection date 2022-10-24 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:05:54,091 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:05,001 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:06:05,003 - built Dictionary<1115 unique tokens: ['00', '0161', '03', '0300', '1']...> from 1 documents (total 2352 corpus positions)
-2024-11-11 08:06:05,003 - Dictionary lifecycle event {'msg': "built Dictionary<1115 unique tokens: ['00', '0161', '03', '0300', '1']...> from 1 documents (total 2352 corpus positions)", 'datetime': '2024-11-11T08:06:05.003701', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:06:05,004 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:06:05,004 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:06:05,005 - using serial LDA version on this node
-2024-11-11 08:06:05,005 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:06:05,005 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:06:05,009 - -8.053 per-word bound, 265.6 perplexity estimate based on a held-out corpus of 1 documents with 2352 words
-2024-11-11 08:06:05,009 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:06:05,010 - topic #0 (0.333): 0.019*"’" + 0.009*"well" + 0.008*"plans" + 0.007*"needs" + 0.007*"effective" + 0.006*"progress" + 0.005*"Lewisham" + 0.005*"4" + 0.005*"need" + 0.005*"good"
-2024-11-11 08:06:05,011 - topic #1 (0.333): 0.015*"’" + 0.009*"needs" + 0.008*"well" + 0.007*"Lewisham" + 0.006*"plans" + 0.005*"effective" + 0.004*"leaders" + 0.004*"15" + 0.004*"good" + 0.004*"ensure"
-2024-11-11 08:06:05,011 - topic #2 (0.333): 0.017*"’" + 0.007*"well" + 0.006*"effective" + 0.006*"4" + 0.006*"Lewisham" + 0.005*"needs" + 0.005*"plans" + 0.005*"good" + 0.005*"arrangements" + 0.004*"practice"
-2024-11-11 08:06:05,011 - topic diff=0.772756, rho=1.000000
-2024-11-11 08:06:05,011 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1115, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:06:05.011359', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:06:05,990 - Inspection date 2023-12-04 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:06:05,990 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:05,990 - Inspection date 2023-12-04 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:06:05,990 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:05,990 - Inspection date 2023-12-04 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:06:05,990 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:05,990 - Inspection date 2023-12-04 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:06:05,991 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:05,991 - Inspection date 2023-12-04 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:06:05,991 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:05,991 - Inspection date 2023-12-04 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:06:05,991 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:15,012 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:06:15,014 - built Dictionary<1015 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2032 corpus positions)
-2024-11-11 08:06:15,014 - Dictionary lifecycle event {'msg': "built Dictionary<1015 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2032 corpus positions)", 'datetime': '2024-11-11T08:06:15.014552', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:06:15,015 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:06:15,015 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:06:15,015 - using serial LDA version on this node
-2024-11-11 08:06:15,016 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:06:15,016 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:06:15,019 - -7.987 per-word bound, 253.6 perplexity estimate based on a held-out corpus of 1 documents with 2032 words
-2024-11-11 08:06:15,019 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:06:15,020 - topic #0 (0.333): 0.016*"’" + 0.009*"well" + 0.007*"Merton" + 0.006*"plans" + 0.005*"needs" + 0.005*"good" + 0.005*"family" + 0.004*"28" + 0.004*"risk" + 0.004*"ensure"
-2024-11-11 08:06:15,020 - topic #1 (0.333): 0.015*"’" + 0.006*"well" + 0.005*"Merton" + 0.004*"needs" + 0.004*"progress" + 0.004*"including" + 0.003*"2022" + 0.003*"health" + 0.003*"good" + 0.003*"February"
-2024-11-11 08:06:15,021 - topic #2 (0.333): 0.015*"’" + 0.008*"well" + 0.007*"needs" + 0.006*"Merton" + 0.005*"family" + 0.005*"progress" + 0.004*"plans" + 0.004*"ensure" + 0.004*"leaders" + 0.004*"4"
-2024-11-11 08:06:15,021 - topic diff=0.758675, rho=1.000000
-2024-11-11 08:06:15,021 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1015, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:06:15.021286', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:06:15,794 - Inspection date 2022-02-28 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:06:15,795 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:15,795 - Inspection date 2022-02-28 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:06:15,795 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:15,795 - Inspection date 2022-02-28 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:06:15,795 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:15,795 - Inspection date 2022-02-28 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:06:15,795 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:15,796 - Inspection date 2022-02-28 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:06:15,796 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:15,796 - Inspection date 2022-02-28 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:06:15,796 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:26,915 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:06:26,917 - built Dictionary<1153 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2540 corpus positions)
-2024-11-11 08:06:26,917 - Dictionary lifecycle event {'msg': "built Dictionary<1153 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2540 corpus positions)", 'datetime': '2024-11-11T08:06:26.917770', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:06:26,918 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:06:26,919 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:06:26,919 - using serial LDA version on this node
-2024-11-11 08:06:26,919 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:06:26,919 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:06:26,923 - -8.049 per-word bound, 264.8 perplexity estimate based on a held-out corpus of 1 documents with 2540 words
-2024-11-11 08:06:26,923 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:06:26,924 - topic #0 (0.333): 0.014*"’" + 0.008*"needs" + 0.006*"practice" + 0.006*"progress" + 0.006*"effective" + 0.005*"good" + 0.005*"Newham" + 0.005*"plans" + 0.004*"receive" + 0.004*"ensure"
-2024-11-11 08:06:26,924 - topic #1 (0.333): 0.024*"’" + 0.009*"needs" + 0.008*"Newham" + 0.007*"effective" + 0.007*"plans" + 0.006*"progress" + 0.006*"need" + 0.006*"practice" + 0.005*"good" + 0.005*"18"
-2024-11-11 08:06:26,925 - topic #2 (0.333): 0.015*"’" + 0.007*"Newham" + 0.007*"need" + 0.006*"practice" + 0.006*"plans" + 0.005*"needs" + 0.005*"progress" + 0.004*"including" + 0.004*"Leaders" + 0.004*"effective"
-2024-11-11 08:06:26,925 - topic diff=0.783890, rho=1.000000
-2024-11-11 08:06:26,925 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1153, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:06:26.925286', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:06:27,854 - Inspection date 2022-07-18 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:06:27,854 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:27,855 - Inspection date 2022-07-18 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:06:27,855 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:27,855 - Inspection date 2022-07-18 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:06:27,855 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:27,855 - Inspection date 2022-07-18 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:06:27,855 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:27,855 - Inspection date 2022-07-18 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:06:27,855 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:27,856 - Inspection date 2022-07-18 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:06:27,856 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:38,154 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:06:38,156 - built Dictionary<1204 unique tokens: ['0', '0161', '0300', '1', '10']...> from 1 documents (total 2389 corpus positions)
-2024-11-11 08:06:38,156 - Dictionary lifecycle event {'msg': "built Dictionary<1204 unique tokens: ['0', '0161', '0300', '1', '10']...> from 1 documents (total 2389 corpus positions)", 'datetime': '2024-11-11T08:06:38.156844', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:06:38,157 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:06:38,158 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:06:38,158 - using serial LDA version on this node
-2024-11-11 08:06:38,158 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:06:38,158 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:06:38,162 - -8.169 per-word bound, 287.7 perplexity estimate based on a held-out corpus of 1 documents with 2389 words
-2024-11-11 08:06:38,162 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:06:38,163 - topic #0 (0.333): 0.013*"’" + 0.007*"Redbridge" + 0.006*"needs" + 0.005*"leaders" + 0.005*"family" + 0.005*"supported" + 0.005*"practice" + 0.005*"parents" + 0.005*"carers" + 0.004*"protection"
-2024-11-11 08:06:38,164 - topic #1 (0.333): 0.016*"’" + 0.008*"Redbridge" + 0.006*"practice" + 0.005*"needs" + 0.005*"leaders" + 0.005*"family" + 0.005*"carers" + 0.004*"risk" + 0.004*"effective" + 0.004*"supported"
-2024-11-11 08:06:38,164 - topic #2 (0.333): 0.013*"’" + 0.006*"Redbridge" + 0.005*"carers" + 0.005*"supported" + 0.004*"risk" + 0.004*"early" + 0.004*"10" + 0.004*"14" + 0.004*"practice" + 0.004*"needs"
-2024-11-11 08:06:38,164 - topic diff=0.752432, rho=1.000000
-2024-11-11 08:06:38,164 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1204, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:06:38.164510', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:06:39,047 - Inspection date 2024-06-10 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:06:39,047 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:39,047 - Inspection date 2024-06-10 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:06:39,047 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:39,047 - Inspection date 2024-06-10 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:06:39,047 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:39,048 - Inspection date 2024-06-10 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:06:39,048 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:39,048 - Inspection date 2024-06-10 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:06:39,048 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:39,048 - Inspection date 2024-06-10 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:06:39,048 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:47,537 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:06:47,539 - built Dictionary<968 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1818 corpus positions)
-2024-11-11 08:06:47,539 - Dictionary lifecycle event {'msg': "built Dictionary<968 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1818 corpus positions)", 'datetime': '2024-11-11T08:06:47.539543', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:06:47,540 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:06:47,540 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:06:47,540 - using serial LDA version on this node
-2024-11-11 08:06:47,541 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:06:47,541 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:06:47,544 - -7.984 per-word bound, 253.2 perplexity estimate based on a held-out corpus of 1 documents with 1818 words
-2024-11-11 08:06:47,544 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:06:47,545 - topic #0 (0.333): 0.015*"’" + 0.013*"well" + 0.007*"Richmond" + 0.007*"needs" + 0.006*"need" + 0.005*"good" + 0.005*"additional" + 0.005*"team" + 0.005*"supported" + 0.004*"ensure"
-2024-11-11 08:06:47,545 - topic #1 (0.333): 0.016*"’" + 0.010*"well" + 0.009*"Richmond" + 0.007*"needs" + 0.007*"supported" + 0.006*"team" + 0.005*"good" + 0.005*"ensure" + 0.005*"need" + 0.004*"31"
-2024-11-11 08:06:47,545 - topic #2 (0.333): 0.014*"’" + 0.009*"well" + 0.008*"needs" + 0.008*"Richmond" + 0.006*"supported" + 0.006*"good" + 0.006*"need" + 0.006*"team" + 0.005*"4" + 0.005*"strong"
-2024-11-11 08:06:47,545 - topic diff=0.728075, rho=1.000000
-2024-11-11 08:06:47,546 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=968, num_topics=3, decay=0.5, chunksize=2000> in 0.00s', 'datetime': '2024-11-11T08:06:47.546075', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:06:48,349 - Inspection date 2022-01-31 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:06:48,349 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:48,350 - Inspection date 2022-01-31 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:06:48,350 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:48,350 - Inspection date 2022-01-31 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:06:48,350 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:48,350 - Inspection date 2022-01-31 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:06:48,350 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:48,350 - Inspection date 2022-01-31 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:06:48,350 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:48,351 - Inspection date 2022-01-31 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:06:48,351 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:57,723 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:06:57,725 - built Dictionary<945 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1878 corpus positions)
-2024-11-11 08:06:57,725 - Dictionary lifecycle event {'msg': "built Dictionary<945 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1878 corpus positions)", 'datetime': '2024-11-11T08:06:57.725599', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:06:57,726 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:06:57,726 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:06:57,726 - using serial LDA version on this node
-2024-11-11 08:06:57,727 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:06:57,727 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:06:57,731 - -7.920 per-word bound, 242.2 perplexity estimate based on a held-out corpus of 1 documents with 1878 words
-2024-11-11 08:06:57,731 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:06:57,733 - topic #0 (0.333): 0.021*"’" + 0.011*"Southwark" + 0.008*"good" + 0.008*"well" + 0.007*"need" + 0.007*"needs" + 0.006*"progress" + 0.006*"strong" + 0.005*"ensure" + 0.005*"plans"
-2024-11-11 08:06:57,733 - topic #1 (0.333): 0.012*"’" + 0.007*"Southwark" + 0.006*"well" + 0.005*"good" + 0.005*"progress" + 0.005*"plans" + 0.005*"Leaders" + 0.004*"needs" + 0.004*"need" + 0.004*"30"
-2024-11-11 08:06:57,733 - topic #2 (0.333): 0.019*"’" + 0.010*"needs" + 0.009*"Southwark" + 0.009*"good" + 0.008*"well" + 0.006*"plans" + 0.006*"Leaders" + 0.006*"progress" + 0.006*"effective" + 0.006*"leaders"
-2024-11-11 08:06:57,734 - topic diff=0.739442, rho=1.000000
-2024-11-11 08:06:57,734 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=945, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:06:57.734225', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:06:58,587 - Inspection date 2022-09-26 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:06:58,587 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:58,587 - Inspection date 2022-09-26 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:06:58,587 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:58,588 - Inspection date 2022-09-26 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:06:58,588 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:58,588 - Inspection date 2022-09-26 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:06:58,588 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:58,588 - Inspection date 2022-09-26 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:06:58,588 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:06:58,588 - Inspection date 2022-09-26 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:06:58,588 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:07:06,911 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:07:06,913 - built Dictionary<976 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1847 corpus positions)
-2024-11-11 08:07:06,913 - Dictionary lifecycle event {'msg': "built Dictionary<976 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1847 corpus positions)", 'datetime': '2024-11-11T08:07:06.913560', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:07:06,914 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:07:06,914 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:07:06,914 - using serial LDA version on this node
-2024-11-11 08:07:06,915 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:07:06,915 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:07:06,918 - -7.985 per-word bound, 253.4 perplexity estimate based on a held-out corpus of 1 documents with 1847 words
-2024-11-11 08:07:06,918 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:07:06,919 - topic #0 (0.333): 0.012*"’" + 0.008*"Sutton" + 0.005*"well" + 0.005*"needs" + 0.005*"progress" + 0.005*"good" + 0.004*"6" + 0.004*"need" + 0.004*"10" + 0.004*"effective"
-2024-11-11 08:07:06,919 - topic #1 (0.333): 0.020*"’" + 0.008*"well" + 0.006*"needs" + 0.006*"receive" + 0.005*"effective" + 0.005*"progress" + 0.005*"Sutton" + 0.005*"good" + 0.004*"10" + 0.004*"leaders"
-2024-11-11 08:07:06,919 - topic #2 (0.333): 0.017*"’" + 0.007*"well" + 0.006*"needs" + 0.005*"receive" + 0.005*"progress" + 0.005*"6" + 0.005*"Sutton" + 0.004*"effective" + 0.004*"good" + 0.004*"2021"
-2024-11-11 08:07:06,919 - topic diff=0.728106, rho=1.000000
-2024-11-11 08:07:06,919 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=976, num_topics=3, decay=0.5, chunksize=2000> in 0.00s', 'datetime': '2024-11-11T08:07:06.919969', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:07:08,728 - Inspection date 2021-12-06 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:07:08,729 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:07:08,729 - Inspection date 2021-12-06 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:07:08,729 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:07:08,729 - Inspection date 2021-12-06 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:07:08,729 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:07:08,729 - Inspection date 2021-12-06 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:07:08,729 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:07:08,730 - Inspection date 2021-12-06 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:07:08,730 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:07:08,730 - Inspection date 2021-12-06 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:07:08,730 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:07:19,308 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:07:19,311 - built Dictionary<1194 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2465 corpus positions)
-2024-11-11 08:07:19,311 - Dictionary lifecycle event {'msg': "built Dictionary<1194 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2465 corpus positions)", 'datetime': '2024-11-11T08:07:19.311426', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:07:19,312 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:07:19,312 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:07:19,312 - using serial LDA version on this node
-2024-11-11 08:07:19,313 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:07:19,313 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:07:19,316 - -8.134 per-word bound, 281.0 perplexity estimate based on a held-out corpus of 1 documents with 2465 words
-2024-11-11 08:07:19,317 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:07:19,318 - topic #0 (0.333): 0.015*"’" + 0.006*"good" + 0.006*"plans" + 0.005*"‘" + 0.005*"effective" + 0.005*"need" + 0.005*"progress" + 0.004*"well" + 0.004*"early" + 0.004*"protection"
-2024-11-11 08:07:19,318 - topic #1 (0.333): 0.015*"’" + 0.008*"good" + 0.008*"effective" + 0.007*"practice" + 0.007*"plans" + 0.006*"‘" + 0.006*"need" + 0.006*"well" + 0.005*"needs" + 0.005*"early"
-2024-11-11 08:07:19,318 - topic #2 (0.333): 0.014*"’" + 0.006*"well" + 0.005*"progress" + 0.005*"good" + 0.005*"plans" + 0.005*"effective" + 0.005*"‘" + 0.004*"carers" + 0.004*"practice" + 0.004*"early"
-2024-11-11 08:07:19,318 - topic diff=0.779806, rho=1.000000
-2024-11-11 08:07:19,318 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1194, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:07:19.318875', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:07:20,183 - Inspection date 2019-06-10 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:07:20,184 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:07:20,184 - Inspection date 2019-06-10 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:07:20,184 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:07:20,184 - Inspection date 2019-06-10 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:07:20,184 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:07:20,185 - Inspection date 2019-06-10 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:07:20,185 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:07:20,185 - Inspection date 2019-06-10 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:07:20,185 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:07:20,185 - Inspection date 2019-06-10 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:07:20,185 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:07:39,965 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:07:39,967 - built Dictionary<1061 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2398 corpus positions)
-2024-11-11 08:07:39,967 - Dictionary lifecycle event {'msg': "built Dictionary<1061 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2398 corpus positions)", 'datetime': '2024-11-11T08:07:39.967909', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:07:39,968 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:07:39,969 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:07:39,969 - using serial LDA version on this node
-2024-11-11 08:07:39,969 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:07:39,969 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:07:39,972 - -7.957 per-word bound, 248.5 perplexity estimate based on a held-out corpus of 1 documents with 2398 words
-2024-11-11 08:07:39,973 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:07:39,974 - topic #0 (0.333): 0.015*"’" + 0.010*"well" + 0.008*"needs" + 0.007*"Waltham" + 0.006*"plans" + 0.005*"Forest" + 0.004*"12" + 0.004*"effective" + 0.004*"8" + 0.004*"2024"
-2024-11-11 08:07:39,974 - topic #1 (0.333): 0.019*"’" + 0.011*"needs" + 0.008*"well" + 0.006*"plans" + 0.006*"progress" + 0.005*"leaders" + 0.005*"Forest" + 0.004*"2024" + 0.004*"Leaders" + 0.004*"protection"
-2024-11-11 08:07:39,974 - topic #2 (0.333): 0.020*"’" + 0.009*"needs" + 0.007*"plans" + 0.007*"well" + 0.006*"Waltham" + 0.006*"Forest" + 0.005*"Leaders" + 0.005*"12" + 0.005*"8" + 0.005*"leaders"
-2024-11-11 08:07:39,974 - topic diff=0.787220, rho=1.000000
-2024-11-11 08:07:39,974 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1061, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:07:39.974823', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:07:40,947 - Inspection date 2024-07-08 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:07:40,947 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:07:40,947 - Inspection date 2024-07-08 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:07:40,947 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:07:40,947 - Inspection date 2024-07-08 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:07:40,947 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:07:40,948 - Inspection date 2024-07-08 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:07:40,948 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:07:40,948 - Inspection date 2024-07-08 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:07:40,948 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:07:40,948 - Inspection date 2024-07-08 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:07:40,948 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:07:49,648 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:07:49,649 - built Dictionary<884 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1772 corpus positions)
-2024-11-11 08:07:49,650 - Dictionary lifecycle event {'msg': "built Dictionary<884 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1772 corpus positions)", 'datetime': '2024-11-11T08:07:49.650043', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:07:49,650 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:07:49,651 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:07:49,651 - using serial LDA version on this node
-2024-11-11 08:07:49,651 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:07:49,651 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:07:49,654 - -7.848 per-word bound, 230.5 perplexity estimate based on a held-out corpus of 1 documents with 1772 words
-2024-11-11 08:07:49,654 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:07:49,655 - topic #0 (0.333): 0.013*"’" + 0.006*"progress" + 0.006*"needs" + 0.005*"practice" + 0.005*"supported" + 0.005*"well" + 0.005*"team" + 0.004*"7" + 0.004*"protection" + 0.004*"quality"
-2024-11-11 08:07:49,656 - topic #1 (0.333): 0.012*"’" + 0.007*"well" + 0.006*"Wandsworth" + 0.005*"effective" + 0.005*"needs" + 0.005*"protection" + 0.005*"progress" + 0.005*"Senior" + 0.005*"practice" + 0.004*"7"
-2024-11-11 08:07:49,656 - topic #2 (0.333): 0.010*"’" + 0.007*"well" + 0.006*"ensure" + 0.006*"Senior" + 0.006*"receive" + 0.005*"protection" + 0.005*"quality" + 0.005*"effective" + 0.005*"Wandsworth" + 0.005*"progress"
-2024-11-11 08:07:49,656 - topic diff=0.744072, rho=1.000000
-2024-11-11 08:07:49,656 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=884, num_topics=3, decay=0.5, chunksize=2000> in 0.00s', 'datetime': '2024-11-11T08:07:49.656421', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:07:50,513 - Inspection date 2022-11-07 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:07:50,513 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:07:50,513 - Inspection date 2022-11-07 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:07:50,513 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:07:50,514 - Inspection date 2022-11-07 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:07:50,514 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:07:50,514 - Inspection date 2022-11-07 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:07:50,514 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:07:50,514 - Inspection date 2022-11-07 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:07:50,514 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:07:50,514 - Inspection date 2022-11-07 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:07:50,514 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:07:59,379 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:07:59,381 - built Dictionary<1136 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2101 corpus positions)
-2024-11-11 08:07:59,381 - Dictionary lifecycle event {'msg': "built Dictionary<1136 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2101 corpus positions)", 'datetime': '2024-11-11T08:07:59.381836', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:07:59,382 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:07:59,382 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:07:59,383 - using serial LDA version on this node
-2024-11-11 08:07:59,383 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:07:59,383 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:07:59,387 - -8.155 per-word bound, 285.0 perplexity estimate based on a held-out corpus of 1 documents with 2101 words
-2024-11-11 08:07:59,387 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:07:59,388 - topic #0 (0.333): 0.014*"’" + 0.009*"practice" + 0.006*"needs" + 0.006*"highly" + 0.005*"well" + 0.004*"across" + 0.004*"family" + 0.003*"skilled" + 0.003*"quality" + 0.003*"high"
-2024-11-11 08:07:59,388 - topic #1 (0.333): 0.012*"’" + 0.006*"highly" + 0.006*"practice" + 0.005*"well" + 0.005*"needs" + 0.004*"many" + 0.004*"across" + 0.003*"Westminster" + 0.003*"high" + 0.003*"family"
-2024-11-11 08:07:59,388 - topic #2 (0.333): 0.012*"’" + 0.006*"needs" + 0.005*"highly" + 0.005*"well" + 0.004*"practice" + 0.004*"many" + 0.004*"plans" + 0.004*"number" + 0.003*"shared" + 0.003*"across"
-2024-11-11 08:07:59,388 - topic diff=0.689375, rho=1.000000
-2024-11-11 08:07:59,389 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1136, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:07:59.388986', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:08:00,575 - Inspection date 2019-09-09 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:08:00,576 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:00,576 - Inspection date 2019-09-09 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:08:00,576 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:00,576 - Inspection date 2019-09-09 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:08:00,577 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:00,577 - Inspection date 2019-09-09 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:08:00,577 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:00,577 - Inspection date 2019-09-09 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:08:00,577 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:00,577 - Inspection date 2019-09-09 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:08:00,577 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:12,140 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:08:12,142 - built Dictionary<1199 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2593 corpus positions)
-2024-11-11 08:08:12,142 - Dictionary lifecycle event {'msg': "built Dictionary<1199 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2593 corpus positions)", 'datetime': '2024-11-11T08:08:12.142636', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:08:12,143 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:08:12,143 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:08:12,144 - using serial LDA version on this node
-2024-11-11 08:08:12,144 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:08:12,144 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:08:12,148 - -8.107 per-word bound, 275.7 perplexity estimate based on a held-out corpus of 1 documents with 2593 words
-2024-11-11 08:08:12,148 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:08:12,149 - topic #0 (0.333): 0.022*"’" + 0.006*"plans" + 0.006*"needs" + 0.005*"effective" + 0.005*"receive" + 0.005*"good" + 0.005*"Luton" + 0.005*"progress" + 0.005*"11" + 0.005*"2022"
-2024-11-11 08:08:12,149 - topic #1 (0.333): 0.017*"’" + 0.009*"need" + 0.007*"needs" + 0.007*"Luton" + 0.006*"effective" + 0.005*"good" + 0.005*"impact" + 0.005*"take" + 0.005*"ensure" + 0.004*"Leaders"
-2024-11-11 08:08:12,150 - topic #2 (0.333): 0.012*"’" + 0.007*"plans" + 0.005*"needs" + 0.005*"Luton" + 0.005*"progress" + 0.005*"good" + 0.005*"impact" + 0.005*"need" + 0.005*"effective" + 0.005*"ensure"
-2024-11-11 08:08:12,150 - topic diff=0.790414, rho=1.000000
-2024-11-11 08:08:12,150 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1199, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:08:12.150284', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:08:13,025 - Inspection date 2022-07-11 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:08:13,025 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:13,025 - Inspection date 2022-07-11 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:08:13,025 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:13,025 - Inspection date 2022-07-11 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:08:13,025 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:13,025 - Inspection date 2022-07-11 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:08:13,025 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:13,026 - Inspection date 2022-07-11 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:08:13,026 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:13,026 - Inspection date 2022-07-11 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:08:13,026 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:23,165 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:08:23,166 - built Dictionary<871 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1938 corpus positions)
-2024-11-11 08:08:23,167 - Dictionary lifecycle event {'msg': "built Dictionary<871 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1938 corpus positions)", 'datetime': '2024-11-11T08:08:23.167148', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:08:23,168 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:08:23,168 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:08:23,168 - using serial LDA version on this node
-2024-11-11 08:08:23,168 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:08:23,168 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:08:23,171 - -7.770 per-word bound, 218.3 perplexity estimate based on a held-out corpus of 1 documents with 1938 words
-2024-11-11 08:08:23,171 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:08:23,172 - topic #0 (0.333): 0.020*"’" + 0.012*"Manchester" + 0.008*"needs" + 0.007*"well" + 0.007*"supported" + 0.006*"quality" + 0.006*"effective" + 0.006*"always" + 0.006*"protection" + 0.006*"plans"
-2024-11-11 08:08:23,173 - topic #1 (0.333): 0.026*"’" + 0.011*"needs" + 0.011*"Manchester" + 0.008*"well" + 0.007*"always" + 0.007*"supported" + 0.006*"plans" + 0.006*"education" + 0.006*"progress" + 0.005*"disabled"
-2024-11-11 08:08:23,173 - topic #2 (0.333): 0.013*"’" + 0.007*"needs" + 0.006*"Manchester" + 0.005*"supported" + 0.005*"always" + 0.005*"well" + 0.004*"protection" + 0.004*"effective" + 0.004*"quality" + 0.004*"March"
-2024-11-11 08:08:23,173 - topic diff=0.829725, rho=1.000000
-2024-11-11 08:08:23,173 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=871, num_topics=3, decay=0.5, chunksize=2000> in 0.00s', 'datetime': '2024-11-11T08:08:23.173549', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:08:23,977 - Inspection date 2022-03-21 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:08:23,978 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:23,978 - Inspection date 2022-03-21 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:08:23,978 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:23,978 - Inspection date 2022-03-21 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:08:23,978 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:23,978 - Inspection date 2022-03-21 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:08:23,978 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:23,979 - Inspection date 2022-03-21 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:08:23,979 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:23,979 - Inspection date 2022-03-21 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:08:23,979 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:34,723 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:08:34,725 - built Dictionary<922 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1857 corpus positions)
-2024-11-11 08:08:34,725 - Dictionary lifecycle event {'msg': "built Dictionary<922 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1857 corpus positions)", 'datetime': '2024-11-11T08:08:34.725792', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:08:34,726 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:08:34,726 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:08:34,726 - using serial LDA version on this node
-2024-11-11 08:08:34,727 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:08:34,727 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:08:34,730 - -7.891 per-word bound, 237.3 perplexity estimate based on a held-out corpus of 1 documents with 1857 words
-2024-11-11 08:08:34,730 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:08:34,731 - topic #0 (0.333): 0.014*"’" + 0.008*"Medway" + 0.007*"quality" + 0.006*"well" + 0.006*"practice" + 0.005*"impact" + 0.005*"Senior" + 0.005*"oversight" + 0.005*"experiences" + 0.005*"leaders"
-2024-11-11 08:08:34,731 - topic #1 (0.333): 0.019*"’" + 0.009*"Medway" + 0.009*"well" + 0.008*"practice" + 0.007*"quality" + 0.006*"leaders" + 0.006*"needs" + 0.006*"experiences" + 0.005*"risk" + 0.005*"good"
-2024-11-11 08:08:34,731 - topic #2 (0.333): 0.014*"’" + 0.010*"Medway" + 0.010*"practice" + 0.008*"quality" + 0.007*"oversight" + 0.007*"needs" + 0.007*"well" + 0.007*"leaders" + 0.006*"impact" + 0.006*"improve"
-2024-11-11 08:08:34,731 - topic diff=0.769883, rho=1.000000
-2024-11-11 08:08:34,732 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=922, num_topics=3, decay=0.5, chunksize=2000> in 0.00s', 'datetime': '2024-11-11T08:08:34.732005', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:08:35,588 - Inspection date 2023-07-17 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:08:35,588 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:35,589 - Inspection date 2023-07-17 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:08:35,589 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:35,589 - Inspection date 2023-07-17 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:08:35,589 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:35,589 - Inspection date 2023-07-17 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:08:35,589 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:35,589 - Inspection date 2023-07-17 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:08:35,589 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:35,589 - Inspection date 2023-07-17 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:08:35,589 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:47,846 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:08:47,848 - built Dictionary<1068 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2278 corpus positions)
-2024-11-11 08:08:47,848 - Dictionary lifecycle event {'msg': "built Dictionary<1068 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2278 corpus positions)", 'datetime': '2024-11-11T08:08:47.848896', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:08:47,849 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:08:47,849 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:08:47,850 - using serial LDA version on this node
-2024-11-11 08:08:47,850 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:08:47,850 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:08:47,853 - -8.000 per-word bound, 256.0 perplexity estimate based on a held-out corpus of 1 documents with 2278 words
-2024-11-11 08:08:47,854 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:08:47,855 - topic #0 (0.333): 0.015*"’" + 0.008*"Middlesbrough" + 0.007*"needs" + 0.007*"plans" + 0.007*"well" + 0.006*"effective" + 0.006*"practice" + 0.005*"progress" + 0.005*"2023" + 0.005*"13"
-2024-11-11 08:08:47,855 - topic #1 (0.333): 0.014*"’" + 0.007*"plans" + 0.007*"effective" + 0.006*"well" + 0.006*"Middlesbrough" + 0.005*"needs" + 0.005*"place" + 0.005*"progress" + 0.005*"practice" + 0.005*"risk"
-2024-11-11 08:08:47,855 - topic #2 (0.333): 0.011*"’" + 0.007*"effective" + 0.006*"plans" + 0.006*"well" + 0.006*"Middlesbrough" + 0.005*"needs" + 0.005*"March" + 0.005*"practice" + 0.005*"progress" + 0.005*"good"
-2024-11-11 08:08:47,855 - topic diff=0.779671, rho=1.000000
-2024-11-11 08:08:47,855 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1068, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:08:47.855720', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:08:48,711 - Inspection date 2023-03-13 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:08:48,711 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:48,711 - Inspection date 2023-03-13 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:08:48,711 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:48,711 - Inspection date 2023-03-13 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:08:48,711 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:48,712 - Inspection date 2023-03-13 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:08:48,712 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:48,712 - Inspection date 2023-03-13 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:08:48,712 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:48,712 - Inspection date 2023-03-13 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:08:48,712 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:08:59,299 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:08:59,301 - built Dictionary<1101 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2328 corpus positions)
-2024-11-11 08:08:59,301 - Dictionary lifecycle event {'msg': "built Dictionary<1101 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2328 corpus positions)", 'datetime': '2024-11-11T08:08:59.301870', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:08:59,302 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:08:59,303 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:08:59,303 - using serial LDA version on this node
-2024-11-11 08:08:59,303 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:08:59,303 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:08:59,307 - -8.037 per-word bound, 262.6 perplexity estimate based on a held-out corpus of 1 documents with 2328 words
-2024-11-11 08:08:59,307 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:08:59,308 - topic #0 (0.333): 0.013*"’" + 0.006*"well" + 0.005*"Keynes" + 0.005*"5" + 0.005*"Milton" + 0.005*"need" + 0.005*"practice" + 0.005*"leaders" + 0.005*"25" + 0.004*"plans"
-2024-11-11 08:08:59,308 - topic #1 (0.333): 0.017*"’" + 0.007*"Milton" + 0.006*"Keynes" + 0.005*"well" + 0.005*"October" + 0.005*"good" + 0.005*"need" + 0.005*"effective" + 0.004*"education" + 0.004*"25"
-2024-11-11 08:08:59,308 - topic #2 (0.333): 0.014*"’" + 0.006*"Keynes" + 0.006*"need" + 0.006*"well" + 0.005*"practice" + 0.005*"Milton" + 0.005*"good" + 0.005*"plans" + 0.004*"25" + 0.004*"leaders"
-2024-11-11 08:08:59,308 - topic diff=0.777800, rho=1.000000
-2024-11-11 08:08:59,308 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1101, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:08:59.308866', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:09:00,278 - Inspection date 2021-10-25 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:09:00,278 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:00,279 - Inspection date 2021-10-25 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:09:00,279 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:00,279 - Inspection date 2021-10-25 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:09:00,279 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:00,279 - Inspection date 2021-10-25 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:09:00,279 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:00,279 - Inspection date 2021-10-25 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:09:00,279 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:00,279 - Inspection date 2021-10-25 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:09:00,279 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:09,812 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:09:09,814 - built Dictionary<956 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2076 corpus positions)
-2024-11-11 08:09:09,814 - Dictionary lifecycle event {'msg': "built Dictionary<956 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2076 corpus positions)", 'datetime': '2024-11-11T08:09:09.814193', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:09:09,815 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:09:09,815 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:09:09,815 - using serial LDA version on this node
-2024-11-11 08:09:09,815 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:09:09,815 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:09:09,818 - -7.875 per-word bound, 234.8 perplexity estimate based on a held-out corpus of 1 documents with 2076 words
-2024-11-11 08:09:09,818 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:09:09,820 - topic #0 (0.333): 0.018*"’" + 0.010*"plans" + 0.009*"Newcastle" + 0.008*"needs" + 0.007*"protection" + 0.007*"well" + 0.006*"good" + 0.006*"making" + 0.006*"ensure" + 0.006*"progress"
-2024-11-11 08:09:09,820 - topic #1 (0.333): 0.016*"’" + 0.011*"plans" + 0.007*"well" + 0.007*"protection" + 0.006*"needs" + 0.006*"good" + 0.006*"progress" + 0.006*"Newcastle" + 0.006*"need" + 0.005*"management"
-2024-11-11 08:09:09,820 - topic #2 (0.333): 0.012*"’" + 0.009*"plans" + 0.009*"needs" + 0.007*"good" + 0.006*"10" + 0.006*"protection" + 0.006*"Newcastle" + 0.005*"ensure" + 0.005*"progress" + 0.005*"response"
-2024-11-11 08:09:09,820 - topic diff=0.781062, rho=1.000000
-2024-11-11 08:09:09,820 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=956, num_topics=3, decay=0.5, chunksize=2000> in 0.00s', 'datetime': '2024-11-11T08:09:09.820676', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:09:10,895 - Inspection date 2021-11-29 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:09:10,896 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:10,896 - Inspection date 2021-11-29 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:09:10,896 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:10,896 - Inspection date 2021-11-29 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:09:10,896 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:10,896 - Inspection date 2021-11-29 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:09:10,897 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:10,897 - Inspection date 2021-11-29 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:09:10,897 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:10,897 - Inspection date 2021-11-29 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:09:10,897 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:22,237 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:09:22,239 - built Dictionary<1221 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2655 corpus positions)
-2024-11-11 08:09:22,239 - Dictionary lifecycle event {'msg': "built Dictionary<1221 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2655 corpus positions)", 'datetime': '2024-11-11T08:09:22.239818', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:09:22,240 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:09:22,241 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:09:22,241 - using serial LDA version on this node
-2024-11-11 08:09:22,241 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:09:22,241 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:09:22,245 - -8.121 per-word bound, 278.3 perplexity estimate based on a held-out corpus of 1 documents with 2655 words
-2024-11-11 08:09:22,245 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:09:22,246 - topic #0 (0.333): 0.016*"’" + 0.009*"well" + 0.009*"Norfolk" + 0.007*"carers" + 0.006*"needs" + 0.005*"practice" + 0.005*"supported" + 0.005*"progress" + 0.005*"plans" + 0.004*"including"
-2024-11-11 08:09:22,247 - topic #1 (0.333): 0.016*"’" + 0.007*"carers" + 0.006*"well" + 0.006*"needs" + 0.006*"Norfolk" + 0.005*"information" + 0.005*"range" + 0.004*"supported" + 0.004*"plans" + 0.004*"18"
-2024-11-11 08:09:22,247 - topic #2 (0.333): 0.018*"’" + 0.008*"Norfolk" + 0.008*"well" + 0.006*"practice" + 0.006*"supported" + 0.005*"needs" + 0.005*"effective" + 0.005*"including" + 0.004*"18" + 0.004*"leaders"
-2024-11-11 08:09:22,247 - topic diff=0.776615, rho=1.000000
-2024-11-11 08:09:22,247 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1221, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:09:22.247499', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:09:23,356 - Inspection date 2022-11-07 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:09:23,357 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:23,357 - Inspection date 2022-11-07 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:09:23,357 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:23,357 - Inspection date 2022-11-07 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:09:23,357 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:23,357 - Inspection date 2022-11-07 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:09:23,357 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:23,358 - Inspection date 2022-11-07 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:09:23,358 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:23,358 - Inspection date 2022-11-07 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:09:23,358 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:33,423 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:09:33,426 - built Dictionary<958 unique tokens: ['0161', '021', '0300', '1', '10']...> from 1 documents (total 2045 corpus positions)
-2024-11-11 08:09:33,427 - Dictionary lifecycle event {'msg': "built Dictionary<958 unique tokens: ['0161', '021', '0300', '1', '10']...> from 1 documents (total 2045 corpus positions)", 'datetime': '2024-11-11T08:09:33.427159', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:09:33,428 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:09:33,429 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:09:33,429 - using serial LDA version on this node
-2024-11-11 08:09:33,429 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:09:33,429 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:09:33,435 - -7.892 per-word bound, 237.5 perplexity estimate based on a held-out corpus of 1 documents with 2045 words
-2024-11-11 08:09:33,435 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:09:33,437 - topic #0 (0.333): 0.017*"’" + 0.010*"practice" + 0.007*"planning" + 0.007*"risk" + 0.007*"leaders" + 0.006*"need" + 0.006*"needs" + 0.005*"many" + 0.005*"oversight" + 0.005*"Lincolnshire"
-2024-11-11 08:09:33,437 - topic #1 (0.333): 0.014*"’" + 0.008*"needs" + 0.006*"practice" + 0.006*"leaders" + 0.006*"risk" + 0.006*"many" + 0.005*"planning" + 0.005*"quality" + 0.005*"need" + 0.005*"Council"
-2024-11-11 08:09:33,438 - topic #2 (0.333): 0.010*"’" + 0.007*"risk" + 0.006*"leaders" + 0.006*"practice" + 0.005*"planning" + 0.004*"North" + 0.004*"needs" + 0.004*"delay" + 0.004*"East" + 0.004*"Council"
-2024-11-11 08:09:33,438 - topic diff=0.781502, rho=1.000000
-2024-11-11 08:09:33,438 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=958, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:09:33.438395', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:09:34,300 - Inspection date 2021-10-04 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:09:34,301 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:34,301 - Inspection date 2021-10-04 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:09:34,301 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:34,301 - Inspection date 2021-10-04 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:09:34,301 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:34,301 - Inspection date 2021-10-04 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:09:34,301 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:34,302 - Inspection date 2021-10-04 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:09:34,302 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:34,302 - Inspection date 2021-10-04 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:09:34,302 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:43,382 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:09:43,384 - built Dictionary<1092 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2174 corpus positions)
-2024-11-11 08:09:43,384 - Dictionary lifecycle event {'msg': "built Dictionary<1092 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2174 corpus positions)", 'datetime': '2024-11-11T08:09:43.384716', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:09:43,385 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:09:43,385 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:09:43,386 - using serial LDA version on this node
-2024-11-11 08:09:43,386 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:09:43,386 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:09:43,389 - -8.068 per-word bound, 268.4 perplexity estimate based on a held-out corpus of 1 documents with 2174 words
-2024-11-11 08:09:43,389 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:09:43,391 - topic #0 (0.333): 0.024*"’" + 0.007*"‘" + 0.006*"well" + 0.005*"approach" + 0.005*"Lincolnshire" + 0.005*"North" + 0.005*"family" + 0.005*"need" + 0.005*"10" + 0.004*"council"
-2024-11-11 08:09:43,391 - topic #1 (0.333): 0.018*"’" + 0.006*"‘" + 0.006*"10" + 0.006*"family" + 0.005*"leaders" + 0.004*"well" + 0.004*"needs" + 0.004*"North" + 0.004*"practice" + 0.004*"need"
-2024-11-11 08:09:43,391 - topic #2 (0.333): 0.018*"’" + 0.008*"‘" + 0.007*"family" + 0.006*"Lincolnshire" + 0.006*"leaders" + 0.006*"North" + 0.005*"approach" + 0.005*"need" + 0.005*"team" + 0.005*"2022"
-2024-11-11 08:09:43,391 - topic diff=0.750721, rho=1.000000
-2024-11-11 08:09:43,391 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1092, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:09:43.391741', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:09:44,636 - Inspection date 2022-10-10 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:09:44,637 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:44,637 - Inspection date 2022-10-10 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:09:44,637 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:44,638 - Inspection date 2022-10-10 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:09:44,638 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:44,638 - Inspection date 2022-10-10 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:09:44,638 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:44,638 - Inspection date 2022-10-10 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:09:44,638 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:44,639 - Inspection date 2022-10-10 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:09:44,639 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:54,518 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:09:54,522 - built Dictionary<1076 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2204 corpus positions)
-2024-11-11 08:09:54,522 - Dictionary lifecycle event {'msg': "built Dictionary<1076 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2204 corpus positions)", 'datetime': '2024-11-11T08:09:54.522476', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:09:54,524 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:09:54,524 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:09:54,524 - using serial LDA version on this node
-2024-11-11 08:09:54,525 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:09:54,525 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:09:54,531 - -8.035 per-word bound, 262.2 perplexity estimate based on a held-out corpus of 1 documents with 2204 words
-2024-11-11 08:09:54,531 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:09:54,533 - topic #0 (0.333): 0.015*"’" + 0.008*"Northamptonshire" + 0.006*"North" + 0.005*"quality" + 0.005*"impact" + 0.005*"well" + 0.004*"needs" + 0.004*"need" + 0.004*"practice" + 0.004*"plans"
-2024-11-11 08:09:54,534 - topic #1 (0.333): 0.015*"’" + 0.008*"North" + 0.007*"well" + 0.007*"Northamptonshire" + 0.006*"practice" + 0.006*"NCT" + 0.006*"quality" + 0.005*"needs" + 0.005*"Leaders" + 0.005*"need"
-2024-11-11 08:09:54,534 - topic #2 (0.333): 0.019*"’" + 0.009*"Northamptonshire" + 0.006*"well" + 0.005*"North" + 0.005*"quality" + 0.005*"2022" + 0.005*"e" + 0.005*"Leaders" + 0.005*"3" + 0.005*"October"
-2024-11-11 08:09:54,534 - topic diff=0.748712, rho=1.000000
-2024-11-11 08:09:54,534 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1076, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:09:54.534672', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:09:55,505 - Inspection date 2022-10-03 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:09:55,506 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:55,506 - Inspection date 2022-10-03 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:09:55,506 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:55,506 - Inspection date 2022-10-03 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:09:55,506 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:55,506 - Inspection date 2022-10-03 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:09:55,506 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:55,507 - Inspection date 2022-10-03 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:09:55,507 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:09:55,507 - Inspection date 2022-10-03 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:09:55,507 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:10:07,164 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:10:07,166 - built Dictionary<1219 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2902 corpus positions)
-2024-11-11 08:10:07,166 - Dictionary lifecycle event {'msg': "built Dictionary<1219 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2902 corpus positions)", 'datetime': '2024-11-11T08:10:07.166652', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:10:07,167 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:10:07,167 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:10:07,168 - using serial LDA version on this node
-2024-11-11 08:10:07,168 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:10:07,168 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:10:07,172 - -8.069 per-word bound, 268.5 perplexity estimate based on a held-out corpus of 1 documents with 2902 words
-2024-11-11 08:10:07,172 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:10:07,173 - topic #0 (0.333): 0.013*"’" + 0.007*"quality" + 0.007*"needs" + 0.005*"always" + 0.005*"North" + 0.005*"Somerset" + 0.004*"risk" + 0.004*"number" + 0.004*"plans" + 0.004*"need"
-2024-11-11 08:10:07,173 - topic #1 (0.333): 0.017*"’" + 0.007*"number" + 0.006*"quality" + 0.006*"needs" + 0.006*"Somerset" + 0.006*"North" + 0.005*"always" + 0.005*"practice" + 0.005*"impact" + 0.005*"progress"
-2024-11-11 08:10:07,173 - topic #2 (0.333): 0.019*"’" + 0.008*"quality" + 0.007*"needs" + 0.006*"always" + 0.006*"practice" + 0.006*"risk" + 0.006*"Somerset" + 0.006*"North" + 0.006*"well" + 0.006*"experienced"
-2024-11-11 08:10:07,173 - topic diff=0.835630, rho=1.000000
-2024-11-11 08:10:07,174 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1219, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:10:07.174089', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:10:09,136 - Inspection date 2023-03-13 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:10:09,136 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:10:09,136 - Inspection date 2023-03-13 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:10:09,136 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:10:09,136 - Inspection date 2023-03-13 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:10:09,136 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:10:09,137 - Inspection date 2023-03-13 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:10:09,137 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:10:09,137 - Inspection date 2023-03-13 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:10:09,137 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:10:09,137 - Inspection date 2023-03-13 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:10:09,137 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:10:20,820 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:10:20,823 - built Dictionary<1273 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2518 corpus positions)
-2024-11-11 08:10:20,823 - Dictionary lifecycle event {'msg': "built Dictionary<1273 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2518 corpus positions)", 'datetime': '2024-11-11T08:10:20.823248', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:10:20,824 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:10:20,824 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:10:20,824 - using serial LDA version on this node
-2024-11-11 08:10:20,825 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:10:20,825 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:10:20,828 - -8.222 per-word bound, 298.6 perplexity estimate based on a held-out corpus of 1 documents with 2518 words
-2024-11-11 08:10:20,828 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:10:20,830 - topic #0 (0.333): 0.014*"’" + 0.007*"well" + 0.005*"quality" + 0.005*"leaders" + 0.005*"needs" + 0.004*"clear" + 0.004*"way" + 0.004*"impact" + 0.004*"make" + 0.004*"good"
-2024-11-11 08:10:20,830 - topic #1 (0.333): 0.019*"’" + 0.008*"well" + 0.005*"leaders" + 0.005*"need" + 0.005*"make" + 0.004*"needs" + 0.004*"quality" + 0.004*"impact" + 0.004*"get" + 0.003*"experiences"
-2024-11-11 08:10:20,830 - topic #2 (0.333): 0.015*"’" + 0.006*"need" + 0.006*"leaders" + 0.005*"early" + 0.005*"well" + 0.005*"quality" + 0.005*"make" + 0.005*"impact" + 0.004*"progress" + 0.004*"needs"
-2024-11-11 08:10:20,830 - topic diff=0.731830, rho=1.000000
-2024-11-11 08:10:20,830 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1273, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:10:20.830787', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:10:21,800 - Inspection date 2020-03-09 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:10:21,800 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:10:21,800 - Inspection date 2020-03-09 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:10:21,800 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:10:21,800 - Inspection date 2020-03-09 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:10:21,800 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:10:21,800 - Inspection date 2020-03-09 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:10:21,800 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:10:21,801 - Inspection date 2020-03-09 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:10:21,801 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:10:21,801 - Inspection date 2020-03-09 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:10:21,801 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:10:33,804 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:10:33,807 - built Dictionary<1259 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2759 corpus positions)
-2024-11-11 08:10:33,807 - Dictionary lifecycle event {'msg': "built Dictionary<1259 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2759 corpus positions)", 'datetime': '2024-11-11T08:10:33.807239', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:10:33,808 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:10:33,808 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:10:33,808 - using serial LDA version on this node
-2024-11-11 08:10:33,809 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:10:33,809 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:10:33,813 - -8.150 per-word bound, 284.0 perplexity estimate based on a held-out corpus of 1 documents with 2759 words
-2024-11-11 08:10:33,813 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:10:33,814 - topic #0 (0.333): 0.025*"’" + 0.009*"well" + 0.007*"Yorkshire" + 0.006*"practice" + 0.006*"North" + 0.006*"needs" + 0.005*"3" + 0.005*"family" + 0.005*"supported" + 0.004*"ensure"
-2024-11-11 08:10:33,814 - topic #1 (0.333): 0.019*"’" + 0.009*"well" + 0.006*"family" + 0.006*"Yorkshire" + 0.006*"North" + 0.006*"practice" + 0.005*"needs" + 0.005*"‘" + 0.004*"2023" + 0.004*"effective"
-2024-11-11 08:10:33,814 - topic #2 (0.333): 0.016*"’" + 0.006*"North" + 0.006*"well" + 0.005*"‘" + 0.005*"needs" + 0.005*"practice" + 0.005*"family" + 0.004*"7" + 0.004*"need" + 0.004*"Yorkshire"
-2024-11-11 08:10:33,814 - topic diff=0.804233, rho=1.000000
-2024-11-11 08:10:33,815 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1259, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:10:33.814994', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:10:34,754 - Inspection date 2023-07-03 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:10:34,754 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:10:34,754 - Inspection date 2023-07-03 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:10:34,754 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:10:34,754 - Inspection date 2023-07-03 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:10:34,755 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:10:34,755 - Inspection date 2023-07-03 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:10:34,755 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:10:34,755 - Inspection date 2023-07-03 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:10:34,755 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:10:34,755 - Inspection date 2023-07-03 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:10:34,755 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:10:47,485 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:10:47,488 - built Dictionary<1218 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2884 corpus positions)
-2024-11-11 08:10:47,488 - Dictionary lifecycle event {'msg': "built Dictionary<1218 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2884 corpus positions)", 'datetime': '2024-11-11T08:10:47.488125', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:10:47,489 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:10:47,489 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:10:47,489 - using serial LDA version on this node
-2024-11-11 08:10:47,490 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:10:47,490 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:10:47,493 - -8.071 per-word bound, 268.8 perplexity estimate based on a held-out corpus of 1 documents with 2884 words
-2024-11-11 08:10:47,493 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:10:47,495 - topic #0 (0.333): 0.018*"’" + 0.008*"family" + 0.008*"leaders" + 0.007*"needs" + 0.006*"well" + 0.006*"strong" + 0.005*"practice" + 0.005*"Northumberland" + 0.005*"experiences" + 0.004*"within"
-2024-11-11 08:10:47,495 - topic #1 (0.333): 0.015*"’" + 0.008*"family" + 0.007*"experiences" + 0.006*"well" + 0.005*"needs" + 0.005*"leaders" + 0.005*"strong" + 0.005*"effective" + 0.004*"2024" + 0.004*"24"
-2024-11-11 08:10:47,495 - topic #2 (0.333): 0.022*"’" + 0.007*"Northumberland" + 0.007*"strong" + 0.007*"needs" + 0.006*"family" + 0.006*"experiences" + 0.005*"leaders" + 0.005*"provide" + 0.005*"progress" + 0.005*"plans"
-2024-11-11 08:10:47,495 - topic diff=0.837349, rho=1.000000
-2024-11-11 08:10:47,495 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1218, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:10:47.495631', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:10:48,408 - Inspection date 2024-05-20 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:10:48,409 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:10:48,409 - Inspection date 2024-05-20 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:10:48,409 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:10:48,409 - Inspection date 2024-05-20 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:10:48,409 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:10:48,409 - Inspection date 2024-05-20 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:10:48,410 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:10:48,410 - Inspection date 2024-05-20 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:10:48,410 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:10:48,410 - Inspection date 2024-05-20 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:10:48,410 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:10:59,874 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:10:59,876 - built Dictionary<1092 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2316 corpus positions)
-2024-11-11 08:10:59,877 - Dictionary lifecycle event {'msg': "built Dictionary<1092 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2316 corpus positions)", 'datetime': '2024-11-11T08:10:59.877040', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:10:59,878 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:10:59,878 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:10:59,878 - using serial LDA version on this node
-2024-11-11 08:10:59,878 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:10:59,878 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:10:59,882 - -8.026 per-word bound, 260.7 perplexity estimate based on a held-out corpus of 1 documents with 2316 words
-2024-11-11 08:10:59,882 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:10:59,883 - topic #0 (0.333): 0.014*"’" + 0.009*"needs" + 0.007*"plans" + 0.006*"Nottingham" + 0.005*"impact" + 0.005*"oversight" + 0.005*"effective" + 0.005*"City" + 0.005*"practice" + 0.005*"However"
-2024-11-11 08:10:59,883 - topic #1 (0.333): 0.017*"’" + 0.008*"needs" + 0.007*"effective" + 0.006*"Nottingham" + 0.005*"July" + 0.004*"protection" + 0.004*"plans" + 0.004*"11" + 0.004*"risk" + 0.004*"2022"
-2024-11-11 08:10:59,883 - topic #2 (0.333): 0.009*"’" + 0.006*"needs" + 0.004*"impact" + 0.004*"11" + 0.004*"City" + 0.004*"However" + 0.004*"oversight" + 0.004*"plans" + 0.004*"Nottingham" + 0.004*"2022"
-2024-11-11 08:10:59,883 - topic diff=0.772219, rho=1.000000
-2024-11-11 08:10:59,884 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1092, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:10:59.884066', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:11:00,795 - Inspection date None / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:11:00,795 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:11:00,795 - Inspection date None / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:11:00,795 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:11:00,796 - Inspection date None / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:11:00,796 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:11:00,796 - Inspection date None / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:11:00,796 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:11:00,796 - Inspection date None / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:11:00,796 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:11:00,796 - Inspection date None / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:11:00,796 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:11:11,966 - adding document #0 to Dictionary<0 unique tokens: []>
-2024-11-11 08:11:11,968 - built Dictionary<1048 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2129 corpus positions)
-2024-11-11 08:11:11,968 - Dictionary lifecycle event {'msg': "built Dictionary<1048 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2129 corpus positions)", 'datetime': '2024-11-11T08:11:11.968919', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:11:11,969 - using symmetric alpha at 0.3333333333333333
-2024-11-11 08:11:11,969 - using symmetric eta at 0.3333333333333333
-2024-11-11 08:11:11,970 - using serial LDA version on this node
-2024-11-11 08:11:11,970 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
-2024-11-11 08:11:11,970 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
-2024-11-11 08:11:11,973 - -8.006 per-word bound, 257.1 perplexity estimate based on a held-out corpus of 1 documents with 2129 words
-2024-11-11 08:11:11,973 - PROGRESS: pass 0, at document #1/1
-2024-11-11 08:11:11,975 - topic #0 (0.333): 0.014*"’" + 0.009*"needs" + 0.009*"well" + 0.006*"plans" + 0.005*"Nottinghamshire" + 0.004*"effective" + 0.004*"County" + 0.004*"Leaders" + 0.004*"2024" + 0.004*"20"
-2024-11-11 08:11:11,975 - topic #1 (0.333): 0.014*"’" + 0.009*"well" + 0.008*"needs" + 0.007*"Nottinghamshire" + 0.006*"plans" + 0.005*"practice" + 0.005*"Council" + 0.004*"progress" + 0.004*"benefit" + 0.004*"2024"
-2024-11-11 08:11:11,975 - topic #2 (0.333): 0.023*"’" + 0.009*"well" + 0.008*"needs" + 0.007*"Nottinghamshire" + 0.006*"Leaders" + 0.006*"effective" + 0.005*"leaders" + 0.005*"plans" + 0.005*"24" + 0.005*"practice"
-2024-11-11 08:11:11,975 - topic diff=0.762421, rho=1.000000
-2024-11-11 08:11:11,975 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1048, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-11T08:11:11.975615', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
-2024-11-11 08:11:12,845 - Inspection date 2024-05-20 / Column 'overall_effectiveness' not found in the DataFrame.
-2024-11-11 08:11:12,845 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:11:12,845 - Inspection date 2024-05-20 / Column 'impact_of_leaders' not found in the DataFrame.
-2024-11-11 08:11:12,845 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:11:12,846 - Inspection date 2024-05-20 / Column 'help_and_protection' not found in the DataFrame.
-2024-11-11 08:11:12,846 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:11:12,846 - Inspection date 2024-05-20 / Column 'in_care' not found in the DataFrame.
-2024-11-11 08:11:12,846 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:11:12,846 - Inspection date 2024-05-20 / Column 'care_leavers' not found in the DataFrame.
-2024-11-11 08:11:12,846 - Index(['judgement', 'grade'], dtype='object')
-2024-11-11 08:11:12,846 - Inspection date 2024-05-20 / Column 'in_care_and_care_leavers' not found in the DataFrame.
-2024-11-11 08:11:12,846 - Index(['judgement', 'grade'], dtype='object')
-
\ No newline at end of file
+2024-11-18 09:29:26,957 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:29:26,959 - built Dictionary<1216 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2696 corpus positions)
+2024-11-18 09:29:26,962 - Dictionary lifecycle event {'msg': "built Dictionary<1216 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2696 corpus positions)", 'datetime': '2024-11-18T09:29:26.960204', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:29:26,963 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:29:26,963 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:29:26,963 - using serial LDA version on this node
+2024-11-18 09:29:26,964 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:29:26,964 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:29:26,968 - -8.106 per-word bound, 275.5 perplexity estimate based on a held-out corpus of 1 documents with 2696 words
+2024-11-18 09:29:26,968 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:29:26,970 - topic #0 (0.333): 0.017*"’" + 0.009*"needs" + 0.006*"within" + 0.006*"Barnsley" + 0.006*"leaders" + 0.005*"senior" + 0.005*"practice" + 0.004*"quality" + 0.004*"response" + 0.004*"plans"
+2024-11-18 09:29:26,970 - topic #1 (0.333): 0.017*"’" + 0.007*"leaders" + 0.007*"within" + 0.007*"practice" + 0.006*"needs" + 0.005*"11" + 0.005*"Barnsley" + 0.005*"plans" + 0.004*"response" + 0.004*"progress"
+2024-11-18 09:29:26,970 - topic #2 (0.333): 0.022*"’" + 0.008*"leaders" + 0.008*"needs" + 0.006*"practice" + 0.005*"Barnsley" + 0.005*"within" + 0.004*"2023" + 0.004*"plans" + 0.004*"15" + 0.004*"family"
+2024-11-18 09:29:26,971 - topic diff=0.795455, rho=1.000000
+2024-11-18 09:29:26,971 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1216, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:29:26.971151', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:29:26,973 - Failed to import jpype dependencies. Fallback to subprocess.
+2024-11-18 09:29:26,973 - No module named 'jpype'
+2024-11-18 09:29:29,334 - Inspection date 2023-09-11 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:29:29,334 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:29:29,334 - Inspection date 2023-09-11 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:29:29,335 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:29:29,335 - Inspection date 2023-09-11 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:29:29,335 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:29:29,335 - Inspection date 2023-09-11 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:29:29,335 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:29:29,336 - Inspection date 2023-09-11 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:29:29,336 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:29:29,336 - Inspection date 2023-09-11 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:29:29,336 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:29:37,458 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:29:37,460 - built Dictionary<1048 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2085 corpus positions)
+2024-11-18 09:29:37,460 - Dictionary lifecycle event {'msg': "built Dictionary<1048 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2085 corpus positions)", 'datetime': '2024-11-18T09:29:37.460874', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:29:37,461 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:29:37,461 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:29:37,462 - using serial LDA version on this node
+2024-11-18 09:29:37,462 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:29:37,462 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:29:37,465 - -8.025 per-word bound, 260.5 perplexity estimate based on a held-out corpus of 1 documents with 2085 words
+2024-11-18 09:29:37,465 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:29:37,467 - topic #0 (0.333): 0.021*"’" + 0.008*"well" + 0.006*"plans" + 0.005*"needs" + 0.005*"receive" + 0.005*"4" + 0.005*"practice" + 0.005*"East" + 0.005*"leaders" + 0.004*"28"
+2024-11-18 09:29:37,467 - topic #1 (0.333): 0.019*"’" + 0.009*"well" + 0.007*"needs" + 0.007*"practice" + 0.005*"leaders" + 0.005*"effective" + 0.005*"plans" + 0.005*"North" + 0.005*"East" + 0.005*"impact"
+2024-11-18 09:29:37,467 - topic #2 (0.333): 0.013*"’" + 0.009*"well" + 0.006*"needs" + 0.005*"practice" + 0.005*"Bath" + 0.005*"clear" + 0.004*"effective" + 0.004*"leaders" + 0.004*"Somerset" + 0.004*"plans"
+2024-11-18 09:29:37,467 - topic diff=0.747388, rho=1.000000
+2024-11-18 09:29:37,467 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1048, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:29:37.467710', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:29:38,277 - Inspection date 2022-02-28 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:29:38,277 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:29:38,277 - Inspection date 2022-02-28 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:29:38,278 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:29:38,278 - Inspection date 2022-02-28 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:29:38,278 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:29:38,278 - Inspection date 2022-02-28 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:29:38,278 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:29:38,278 - Inspection date 2022-02-28 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:29:38,278 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:29:38,279 - Inspection date 2022-02-28 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:29:38,279 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:29:49,519 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:29:49,522 - built Dictionary<1202 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2585 corpus positions)
+2024-11-18 09:29:49,522 - Dictionary lifecycle event {'msg': "built Dictionary<1202 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2585 corpus positions)", 'datetime': '2024-11-18T09:29:49.522373', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:29:49,523 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:29:49,523 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:29:49,523 - using serial LDA version on this node
+2024-11-18 09:29:49,524 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:29:49,524 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:29:49,528 - -8.113 per-word bound, 276.8 perplexity estimate based on a held-out corpus of 1 documents with 2585 words
+2024-11-18 09:29:49,528 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:29:49,529 - topic #0 (0.333): 0.021*"’" + 0.007*"needs" + 0.006*"well" + 0.006*"ensure" + 0.005*"supported" + 0.005*"plans" + 0.005*"made" + 0.005*"progress" + 0.004*"Bedford" + 0.004*"need"
+2024-11-18 09:29:49,529 - topic #1 (0.333): 0.019*"’" + 0.007*"ensure" + 0.006*"needs" + 0.006*"good" + 0.006*"well" + 0.006*"Bedford" + 0.005*"plans" + 0.005*"2021" + 0.005*"supported" + 0.005*"progress"
+2024-11-18 09:29:49,530 - topic #2 (0.333): 0.016*"’" + 0.007*"needs" + 0.005*"ensure" + 0.005*"Bedford" + 0.005*"well" + 0.005*"Borough" + 0.005*"family" + 0.005*"education" + 0.004*"progress" + 0.004*"supported"
+2024-11-18 09:29:49,530 - topic diff=0.788710, rho=1.000000
+2024-11-18 09:29:49,530 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1202, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:29:49.530321', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:29:50,349 - Inspection date 2021-11-15 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:29:50,349 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:29:50,349 - Inspection date 2021-11-15 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:29:50,349 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:29:50,350 - Inspection date 2021-11-15 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:29:50,350 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:29:50,350 - Inspection date 2021-11-15 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:29:50,350 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:29:50,350 - Inspection date 2021-11-15 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:29:50,350 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:29:50,350 - Inspection date 2021-11-15 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:29:50,350 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:01,021 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:30:01,023 - built Dictionary<1065 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2378 corpus positions)
+2024-11-18 09:30:01,023 - Dictionary lifecycle event {'msg': "built Dictionary<1065 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2378 corpus positions)", 'datetime': '2024-11-18T09:30:01.023628', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:30:01,024 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:30:01,024 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:30:01,025 - using serial LDA version on this node
+2024-11-18 09:30:01,025 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:30:01,025 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:30:01,028 - -7.971 per-word bound, 250.9 perplexity estimate based on a held-out corpus of 1 documents with 2378 words
+2024-11-18 09:30:01,029 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:30:01,030 - topic #0 (0.333): 0.011*"’" + 0.007*"effective" + 0.006*"needs" + 0.005*"well" + 0.005*"2023" + 0.005*"Birmingham" + 0.005*"plans" + 0.005*"3" + 0.005*"leaders" + 0.004*"trust"
+2024-11-18 09:30:01,030 - topic #1 (0.333): 0.011*"’" + 0.007*"effective" + 0.007*"needs" + 0.006*"Birmingham" + 0.006*"well" + 0.005*"trust" + 0.004*"progress" + 0.004*"plans" + 0.004*"2023" + 0.004*"risk"
+2024-11-18 09:30:01,030 - topic #2 (0.333): 0.020*"’" + 0.013*"needs" + 0.008*"well" + 0.007*"plans" + 0.006*"appropriate" + 0.006*"progress" + 0.006*"trust" + 0.006*"effective" + 0.006*"Birmingham" + 0.005*"risk"
+2024-11-18 09:30:01,030 - topic diff=0.801598, rho=1.000000
+2024-11-18 09:30:01,030 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1065, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:30:01.030833', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:30:02,068 - Inspection date 2023-02-20 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:30:02,069 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:02,069 - Inspection date 2023-02-20 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:30:02,069 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:02,069 - Inspection date 2023-02-20 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:30:02,069 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:02,070 - Inspection date 2023-02-20 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:30:02,070 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:02,070 - Inspection date 2023-02-20 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:30:02,070 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:02,070 - Inspection date 2023-02-20 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:30:02,071 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:12,863 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:30:12,865 - built Dictionary<1055 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2353 corpus positions)
+2024-11-18 09:30:12,865 - Dictionary lifecycle event {'msg': "built Dictionary<1055 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2353 corpus positions)", 'datetime': '2024-11-18T09:30:12.865900', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:30:12,866 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:30:12,867 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:30:12,867 - using serial LDA version on this node
+2024-11-18 09:30:12,867 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:30:12,867 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:30:12,871 - -7.960 per-word bound, 248.9 perplexity estimate based on a held-out corpus of 1 documents with 2353 words
+2024-11-18 09:30:12,871 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:30:12,872 - topic #0 (0.333): 0.014*"’" + 0.008*"Darwen" + 0.008*"practice" + 0.007*"impact" + 0.007*"needs" + 0.007*"quality" + 0.006*"Blackburn" + 0.006*"well" + 0.006*"planning" + 0.005*"February"
+2024-11-18 09:30:12,872 - topic #1 (0.333): 0.013*"’" + 0.008*"needs" + 0.007*"Blackburn" + 0.006*"practice" + 0.006*"quality" + 0.006*"well" + 0.005*"Darwen" + 0.005*"effective" + 0.005*"result" + 0.005*"planning"
+2024-11-18 09:30:12,872 - topic #2 (0.333): 0.015*"’" + 0.007*"needs" + 0.007*"quality" + 0.007*"practice" + 0.006*"well" + 0.006*"Blackburn" + 0.006*"impact" + 0.005*"means" + 0.005*"plans" + 0.005*"need"
+2024-11-18 09:30:12,872 - topic diff=0.813713, rho=1.000000
+2024-11-18 09:30:12,873 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1055, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:30:12.873072', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:30:13,800 - Inspection date 2022-01-24 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:30:13,800 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:13,801 - Inspection date 2022-01-24 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:30:13,801 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:13,801 - Inspection date 2022-01-24 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:30:13,801 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:13,801 - Inspection date 2022-01-24 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:30:13,801 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:13,801 - Inspection date 2022-01-24 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:30:13,802 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:13,802 - Inspection date 2022-01-24 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:30:13,802 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:24,503 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:30:24,505 - built Dictionary<1037 unique tokens: ['0', '0161', '030', '0300', '1']...> from 1 documents (total 2392 corpus positions)
+2024-11-18 09:30:24,505 - Dictionary lifecycle event {'msg': "built Dictionary<1037 unique tokens: ['0', '0161', '030', '0300', '1']...> from 1 documents (total 2392 corpus positions)", 'datetime': '2024-11-18T09:30:24.505817', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:30:24,506 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:30:24,506 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:30:24,507 - using serial LDA version on this node
+2024-11-18 09:30:24,507 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:30:24,507 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:30:24,511 - -7.923 per-word bound, 242.7 perplexity estimate based on a held-out corpus of 1 documents with 2392 words
+2024-11-18 09:30:24,511 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:30:24,512 - topic #0 (0.333): 0.018*"’" + 0.008*"well" + 0.008*"Blackpool" + 0.007*"needs" + 0.005*"16" + 0.005*"supported" + 0.005*"effective" + 0.005*"plans" + 0.005*"5" + 0.005*"practice"
+2024-11-18 09:30:24,512 - topic #1 (0.333): 0.015*"’" + 0.010*"needs" + 0.009*"well" + 0.006*"effective" + 0.006*"Blackpool" + 0.006*"practice" + 0.005*"quality" + 0.005*"progress" + 0.005*"good" + 0.005*"timely"
+2024-11-18 09:30:24,512 - topic #2 (0.333): 0.017*"’" + 0.013*"needs" + 0.010*"well" + 0.008*"Blackpool" + 0.005*"plans" + 0.005*"effective" + 0.005*"supported" + 0.005*"team" + 0.005*"16" + 0.005*"progress"
+2024-11-18 09:30:24,512 - topic diff=0.826382, rho=1.000000
+2024-11-18 09:30:24,512 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1037, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:30:24.512853', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:30:25,458 - Inspection date 2022-12-05 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:30:25,458 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:25,458 - Inspection date 2022-12-05 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:30:25,459 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:25,459 - Inspection date 2022-12-05 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:30:25,459 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:25,459 - Inspection date 2022-12-05 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:30:25,459 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:25,459 - Inspection date 2022-12-05 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:30:25,459 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:25,459 - Inspection date 2022-12-05 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:30:25,459 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:35,322 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:30:35,324 - built Dictionary<972 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2055 corpus positions)
+2024-11-18 09:30:35,324 - Dictionary lifecycle event {'msg': "built Dictionary<972 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2055 corpus positions)", 'datetime': '2024-11-18T09:30:35.324373', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:30:35,325 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:30:35,325 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:30:35,325 - using serial LDA version on this node
+2024-11-18 09:30:35,325 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:30:35,326 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:30:35,329 - -7.912 per-word bound, 240.9 perplexity estimate based on a held-out corpus of 1 documents with 2055 words
+2024-11-18 09:30:35,329 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:30:35,330 - topic #0 (0.333): 0.019*"’" + 0.007*"plans" + 0.007*"well" + 0.006*"needs" + 0.006*"Bolton" + 0.005*"supported" + 0.005*"need" + 0.004*"September" + 0.004*"response" + 0.004*"effective"
+2024-11-18 09:30:35,330 - topic #1 (0.333): 0.022*"’" + 0.011*"needs" + 0.010*"well" + 0.009*"Bolton" + 0.008*"plans" + 0.007*"planning" + 0.006*"11" + 0.005*"need" + 0.005*"supported" + 0.005*"strong"
+2024-11-18 09:30:35,331 - topic #2 (0.333): 0.014*"’" + 0.009*"needs" + 0.009*"Bolton" + 0.006*"plans" + 0.006*"well" + 0.005*"supported" + 0.005*"strong" + 0.005*"timely" + 0.004*"need" + 0.004*"planning"
+2024-11-18 09:30:35,331 - topic diff=0.785748, rho=1.000000
+2024-11-18 09:30:35,331 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=972, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:30:35.331221', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:30:36,322 - Inspection date 2023-09-11 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:30:36,322 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:36,322 - Inspection date 2023-09-11 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:30:36,322 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:36,322 - Inspection date 2023-09-11 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:30:36,322 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:36,322 - Inspection date 2023-09-11 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:30:36,323 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:36,323 - Inspection date 2023-09-11 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:30:36,323 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:36,323 - Inspection date 2023-09-11 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:30:36,323 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:45,224 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:30:45,226 - built Dictionary<1035 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2004 corpus positions)
+2024-11-18 09:30:45,226 - Dictionary lifecycle event {'msg': "built Dictionary<1035 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2004 corpus positions)", 'datetime': '2024-11-18T09:30:45.226701', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:30:45,227 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:30:45,227 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:30:45,227 - using serial LDA version on this node
+2024-11-18 09:30:45,228 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:30:45,228 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:30:45,231 - -8.032 per-word bound, 261.8 perplexity estimate based on a held-out corpus of 1 documents with 2004 words
+2024-11-18 09:30:45,231 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:30:45,233 - topic #0 (0.333): 0.013*"’" + 0.006*"quality" + 0.005*"Bournemouth" + 0.005*"practice" + 0.005*"Poole" + 0.004*"impact" + 0.004*"17" + 0.004*"December" + 0.004*"6" + 0.004*"time"
+2024-11-18 09:30:45,233 - topic #1 (0.333): 0.021*"’" + 0.007*"practice" + 0.007*"progress" + 0.006*"quality" + 0.005*"Christchurch" + 0.005*"6" + 0.005*"right" + 0.005*"time" + 0.005*"17" + 0.005*"risk"
+2024-11-18 09:30:45,233 - topic #2 (0.333): 0.017*"’" + 0.007*"quality" + 0.005*"Poole" + 0.005*"risk" + 0.004*"well" + 0.004*"Bournemouth" + 0.004*"practice" + 0.004*"time" + 0.004*"impact" + 0.004*"Christchurch"
+2024-11-18 09:30:45,233 - topic diff=0.763004, rho=1.000000
+2024-11-18 09:30:45,233 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1035, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:30:45.233691', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:30:48,215 - Inspection date 2021-12-06 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:30:48,216 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:48,216 - Inspection date 2021-12-06 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:30:48,216 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:48,216 - Inspection date 2021-12-06 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:30:48,216 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:48,216 - Inspection date 2021-12-06 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:30:48,216 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:48,216 - Inspection date 2021-12-06 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:30:48,217 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:48,217 - Inspection date 2021-12-06 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:30:48,217 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:58,104 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:30:58,106 - built Dictionary<900 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1846 corpus positions)
+2024-11-18 09:30:58,106 - Dictionary lifecycle event {'msg': "built Dictionary<900 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1846 corpus positions)", 'datetime': '2024-11-18T09:30:58.106358', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:30:58,107 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:30:58,107 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:30:58,107 - using serial LDA version on this node
+2024-11-18 09:30:58,107 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:30:58,107 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:30:58,110 - -7.851 per-word bound, 230.8 perplexity estimate based on a held-out corpus of 1 documents with 1846 words
+2024-11-18 09:30:58,111 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:30:58,112 - topic #0 (0.333): 0.016*"’" + 0.008*"Forest" + 0.008*"effective" + 0.007*"risk" + 0.006*"plans" + 0.006*"good" + 0.006*"quality" + 0.006*"progress" + 0.006*"13" + 0.006*"Bracknell"
+2024-11-18 09:30:58,112 - topic #1 (0.333): 0.015*"’" + 0.008*"Bracknell" + 0.007*"risk" + 0.007*"needs" + 0.006*"Forest" + 0.006*"well" + 0.006*"need" + 0.006*"leaders" + 0.006*"quality" + 0.006*"good"
+2024-11-18 09:30:58,112 - topic #2 (0.333): 0.018*"’" + 0.007*"needs" + 0.006*"Bracknell" + 0.006*"quality" + 0.006*"good" + 0.005*"Forest" + 0.005*"plans" + 0.005*"provided" + 0.005*"positive" + 0.005*"risk"
+2024-11-18 09:30:58,112 - topic diff=0.760617, rho=1.000000
+2024-11-18 09:30:58,112 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=900, num_topics=3, decay=0.5, chunksize=2000> in 0.00s', 'datetime': '2024-11-18T09:30:58.112855', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:30:58,945 - Inspection date 2022-06-13 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:30:58,945 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:58,945 - Inspection date 2022-06-13 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:30:58,945 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:58,945 - Inspection date 2022-06-13 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:30:58,946 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:58,946 - Inspection date 2022-06-13 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:30:58,946 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:58,946 - Inspection date 2022-06-13 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:30:58,946 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:30:58,946 - Inspection date 2022-06-13 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:30:58,946 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:09,198 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:31:09,201 - built Dictionary<1124 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2249 corpus positions)
+2024-11-18 09:31:09,201 - Dictionary lifecycle event {'msg': "built Dictionary<1124 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2249 corpus positions)", 'datetime': '2024-11-18T09:31:09.201286', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:31:09,202 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:31:09,202 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:31:09,202 - using serial LDA version on this node
+2024-11-18 09:31:09,203 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:31:09,203 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:31:09,206 - -8.090 per-word bound, 272.5 perplexity estimate based on a held-out corpus of 1 documents with 2249 words
+2024-11-18 09:31:09,206 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:31:09,208 - topic #0 (0.333): 0.010*"’" + 0.006*"well" + 0.006*"Brighton" + 0.005*"practice" + 0.005*"needs" + 0.005*"experiences" + 0.004*"Hove" + 0.004*"11" + 0.004*"receive" + 0.003*"15"
+2024-11-18 09:31:09,208 - topic #1 (0.333): 0.020*"’" + 0.008*"well" + 0.007*"practice" + 0.007*"Hove" + 0.007*"Brighton" + 0.006*"needs" + 0.006*"progress" + 0.006*"relationships" + 0.006*"experiences" + 0.005*"family"
+2024-11-18 09:31:09,208 - topic #2 (0.333): 0.015*"’" + 0.008*"needs" + 0.007*"Hove" + 0.007*"well" + 0.006*"relationships" + 0.005*"Brighton" + 0.005*"progress" + 0.005*"experiences" + 0.005*"practice" + 0.004*"receive"
+2024-11-18 09:31:09,208 - topic diff=0.760041, rho=1.000000
+2024-11-18 09:31:09,208 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1124, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:31:09.208952', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:31:10,086 - Inspection date None / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:31:10,086 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:10,087 - Inspection date None / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:31:10,087 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:10,087 - Inspection date None / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:31:10,087 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:10,087 - Inspection date None / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:31:10,087 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:10,088 - Inspection date None / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:31:10,088 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:10,088 - Inspection date None / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:31:10,088 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:23,345 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:31:23,347 - built Dictionary<1151 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2647 corpus positions)
+2024-11-18 09:31:23,348 - Dictionary lifecycle event {'msg': "built Dictionary<1151 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2647 corpus positions)", 'datetime': '2024-11-18T09:31:23.348189', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:31:23,349 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:31:23,349 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:31:23,349 - using serial LDA version on this node
+2024-11-18 09:31:23,350 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:31:23,350 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:31:23,353 - -8.032 per-word bound, 261.8 perplexity estimate based on a held-out corpus of 1 documents with 2647 words
+2024-11-18 09:31:23,354 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:31:23,355 - topic #0 (0.333): 0.023*"’" + 0.009*"well" + 0.008*"Bristol" + 0.008*"needs" + 0.007*"good" + 0.006*"health" + 0.006*"progress" + 0.005*"plans" + 0.005*"leaders" + 0.005*"need"
+2024-11-18 09:31:23,355 - topic #1 (0.333): 0.018*"’" + 0.009*"good" + 0.007*"well" + 0.007*"Bristol" + 0.007*"needs" + 0.005*"receive" + 0.005*"16" + 0.004*"arrangements" + 0.004*"need" + 0.004*"ensure"
+2024-11-18 09:31:23,355 - topic #2 (0.333): 0.016*"’" + 0.010*"well" + 0.008*"needs" + 0.007*"good" + 0.007*"Bristol" + 0.005*"always" + 0.005*"progress" + 0.005*"leaders" + 0.004*"need" + 0.004*"health"
+2024-11-18 09:31:23,355 - topic diff=0.818573, rho=1.000000
+2024-11-18 09:31:23,355 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1151, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:31:23.355931', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:31:24,172 - Inspection date 2023-01-16 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:31:24,172 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:24,173 - Inspection date 2023-01-16 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:31:24,173 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:24,173 - Inspection date 2023-01-16 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:31:24,173 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:24,173 - Inspection date 2023-01-16 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:31:24,173 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:24,173 - Inspection date 2023-01-16 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:31:24,173 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:24,174 - Inspection date 2023-01-16 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:31:24,174 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:34,715 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:31:34,717 - built Dictionary<1263 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2404 corpus positions)
+2024-11-18 09:31:34,718 - Dictionary lifecycle event {'msg': "built Dictionary<1263 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2404 corpus positions)", 'datetime': '2024-11-18T09:31:34.718090', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:31:34,719 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:31:34,719 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:31:34,719 - using serial LDA version on this node
+2024-11-18 09:31:34,719 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:31:34,720 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:31:34,723 - -8.240 per-word bound, 302.2 perplexity estimate based on a held-out corpus of 1 documents with 2404 words
+2024-11-18 09:31:34,724 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:31:34,725 - topic #0 (0.333): 0.013*"’" + 0.006*"17" + 0.005*"number" + 0.005*"Buckinghamshire" + 0.005*"plans" + 0.005*"December" + 0.004*"6" + 0.004*"well" + 0.004*"practice" + 0.003*"protection"
+2024-11-18 09:31:34,725 - topic #1 (0.333): 0.013*"’" + 0.005*"Buckinghamshire" + 0.005*"number" + 0.005*"plans" + 0.004*"protection" + 0.004*"many" + 0.004*"17" + 0.004*"teams" + 0.003*"2021" + 0.003*"6"
+2024-11-18 09:31:34,725 - topic #2 (0.333): 0.015*"’" + 0.005*"plans" + 0.005*"many" + 0.004*"protection" + 0.004*"2021" + 0.004*"6" + 0.004*"needs" + 0.004*"small" + 0.004*"practice" + 0.004*"number"
+2024-11-18 09:31:34,725 - topic diff=0.721901, rho=1.000000
+2024-11-18 09:31:34,726 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1263, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:31:34.725985', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:31:35,583 - Inspection date 2021-12-06 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:31:35,583 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:35,583 - Inspection date 2021-12-06 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:31:35,588 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:35,588 - Inspection date 2021-12-06 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:31:35,588 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:35,588 - Inspection date 2021-12-06 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:31:35,588 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:35,589 - Inspection date 2021-12-06 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:31:35,589 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:35,589 - Inspection date 2021-12-06 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:31:35,589 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:45,992 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:31:45,994 - built Dictionary<1076 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2427 corpus positions)
+2024-11-18 09:31:45,994 - Dictionary lifecycle event {'msg': "built Dictionary<1076 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2427 corpus positions)", 'datetime': '2024-11-18T09:31:45.994845', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:31:45,995 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:31:45,995 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:31:45,996 - using serial LDA version on this node
+2024-11-18 09:31:45,996 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:31:45,996 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:31:46,000 - -7.973 per-word bound, 251.2 perplexity estimate based on a held-out corpus of 1 documents with 2427 words
+2024-11-18 09:31:46,000 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:31:46,001 - topic #0 (0.333): 0.009*"’" + 0.007*"needs" + 0.006*"team" + 0.006*"protection" + 0.006*"2021" + 0.006*"practice" + 0.005*"quality" + 0.005*"Bury" + 0.004*"impact" + 0.004*"need"
+2024-11-18 09:31:46,001 - topic #1 (0.333): 0.013*"’" + 0.007*"protection" + 0.007*"needs" + 0.006*"2021" + 0.006*"impact" + 0.006*"practice" + 0.005*"need" + 0.005*"delay" + 0.005*"Bury" + 0.004*"November"
+2024-11-18 09:31:46,001 - topic #2 (0.333): 0.011*"’" + 0.007*"2021" + 0.006*"team" + 0.005*"protection" + 0.005*"risk" + 0.005*"need" + 0.005*"needs" + 0.005*"practice" + 0.005*"timely" + 0.005*"October"
+2024-11-18 09:31:46,001 - topic diff=0.802631, rho=1.000000
+2024-11-18 09:31:46,002 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1076, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:31:46.002043', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:31:46,868 - Inspection date 2021-10-25 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:31:46,868 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:46,868 - Inspection date 2021-10-25 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:31:46,868 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:46,868 - Inspection date 2021-10-25 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:31:46,868 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:46,869 - Inspection date 2021-10-25 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:31:46,869 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:46,869 - Inspection date 2021-10-25 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:31:46,869 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:46,869 - Inspection date 2021-10-25 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:31:46,869 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:57,408 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:31:57,411 - built Dictionary<1109 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2389 corpus positions)
+2024-11-18 09:31:57,411 - Dictionary lifecycle event {'msg': "built Dictionary<1109 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2389 corpus positions)", 'datetime': '2024-11-18T09:31:57.411276', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:31:57,412 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:31:57,412 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:31:57,412 - using serial LDA version on this node
+2024-11-18 09:31:57,412 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:31:57,413 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:31:57,416 - -8.024 per-word bound, 260.3 perplexity estimate based on a held-out corpus of 1 documents with 2389 words
+2024-11-18 09:31:57,416 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:31:57,417 - topic #0 (0.333): 0.019*"’" + 0.010*"needs" + 0.009*"Calderdale" + 0.006*"ensure" + 0.006*"plans" + 0.005*"well" + 0.005*"experiences" + 0.005*"information" + 0.005*"parents" + 0.005*"progress"
+2024-11-18 09:31:57,418 - topic #1 (0.333): 0.011*"’" + 0.008*"needs" + 0.006*"well" + 0.006*"Calderdale" + 0.005*"plans" + 0.005*"progress" + 0.005*"ensure" + 0.004*"parents" + 0.004*"risk" + 0.004*"information"
+2024-11-18 09:31:57,418 - topic #2 (0.333): 0.026*"’" + 0.010*"needs" + 0.009*"Calderdale" + 0.006*"well" + 0.006*"progress" + 0.006*"risk" + 0.006*"plans" + 0.006*"19" + 0.005*"ensure" + 0.005*"parents"
+2024-11-18 09:31:57,418 - topic diff=0.792774, rho=1.000000
+2024-11-18 09:31:57,418 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1109, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:31:57.418490', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:31:58,404 - Inspection date 2024-02-19 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:31:58,405 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:58,405 - Inspection date 2024-02-19 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:31:58,405 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:58,405 - Inspection date 2024-02-19 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:31:58,405 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:58,405 - Inspection date 2024-02-19 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:31:58,405 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:58,405 - Inspection date 2024-02-19 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:31:58,405 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:31:58,406 - Inspection date 2024-02-19 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:31:58,406 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:09,821 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:32:09,823 - built Dictionary<1082 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2339 corpus positions)
+2024-11-18 09:32:09,823 - Dictionary lifecycle event {'msg': "built Dictionary<1082 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2339 corpus positions)", 'datetime': '2024-11-18T09:32:09.823416', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:32:09,824 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:32:09,824 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:32:09,824 - using serial LDA version on this node
+2024-11-18 09:32:09,825 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:32:09,825 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:32:09,828 - -8.004 per-word bound, 256.7 perplexity estimate based on a held-out corpus of 1 documents with 2339 words
+2024-11-18 09:32:09,828 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:32:09,830 - topic #0 (0.333): 0.018*"’" + 0.007*"Cambridgeshire" + 0.007*"leaders" + 0.007*"needs" + 0.005*"response" + 0.005*"good" + 0.005*"effective" + 0.005*"leadership" + 0.005*"practice" + 0.004*"2024"
+2024-11-18 09:32:09,830 - topic #1 (0.333): 0.012*"’" + 0.007*"needs" + 0.006*"leaders" + 0.005*"good" + 0.005*"Cambridgeshire" + 0.005*"well" + 0.005*"effective" + 0.004*"leadership" + 0.004*"However" + 0.004*"quality"
+2024-11-18 09:32:09,830 - topic #2 (0.333): 0.019*"’" + 0.006*"Cambridgeshire" + 0.006*"needs" + 0.006*"leaders" + 0.005*"quality" + 0.005*"good" + 0.005*"clear" + 0.005*"2024" + 0.005*"4" + 0.005*"well"
+2024-11-18 09:32:09,830 - topic diff=0.783401, rho=1.000000
+2024-11-18 09:32:09,830 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1082, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:32:09.830762', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:32:10,823 - Inspection date 2024-03-04 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:32:10,823 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:10,823 - Inspection date 2024-03-04 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:32:10,823 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:10,824 - Inspection date 2024-03-04 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:32:10,824 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:10,824 - Inspection date 2024-03-04 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:32:10,824 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:10,824 - Inspection date 2024-03-04 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:32:10,824 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:10,824 - Inspection date 2024-03-04 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:32:10,824 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:20,380 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:32:20,382 - built Dictionary<1030 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2199 corpus positions)
+2024-11-18 09:32:20,382 - Dictionary lifecycle event {'msg': "built Dictionary<1030 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2199 corpus positions)", 'datetime': '2024-11-18T09:32:20.382727', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:32:20,383 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:32:20,383 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:32:20,384 - using serial LDA version on this node
+2024-11-18 09:32:20,384 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:32:20,384 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:32:20,387 - -7.965 per-word bound, 249.9 perplexity estimate based on a held-out corpus of 1 documents with 2199 words
+2024-11-18 09:32:20,387 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:32:20,389 - topic #0 (0.333): 0.016*"’" + 0.010*"well" + 0.006*"need" + 0.006*"carers" + 0.006*"needs" + 0.005*"good" + 0.005*"plans" + 0.005*"Bedfordshire" + 0.005*"information" + 0.005*"protection"
+2024-11-18 09:32:20,389 - topic #1 (0.333): 0.015*"’" + 0.007*"well" + 0.007*"needs" + 0.007*"good" + 0.007*"need" + 0.006*"progress" + 0.005*"carers" + 0.005*"plans" + 0.004*"early" + 0.004*"number"
+2024-11-18 09:32:20,389 - topic #2 (0.333): 0.017*"’" + 0.010*"well" + 0.008*"needs" + 0.007*"plans" + 0.006*"carers" + 0.006*"good" + 0.006*"need" + 0.006*"Central" + 0.006*"progress" + 0.005*"Bedfordshire"
+2024-11-18 09:32:20,389 - topic diff=0.783257, rho=1.000000
+2024-11-18 09:32:20,389 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1030, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:32:20.389661', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:32:21,202 - Inspection date 2022-01-17 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:32:21,202 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:21,203 - Inspection date 2022-01-17 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:32:21,203 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:21,203 - Inspection date 2022-01-17 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:32:21,203 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:21,203 - Inspection date 2022-01-17 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:32:21,203 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:21,203 - Inspection date 2022-01-17 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:32:21,204 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:21,204 - Inspection date 2022-01-17 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:32:21,204 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:32,071 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:32:32,073 - built Dictionary<1051 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2272 corpus positions)
+2024-11-18 09:32:32,073 - Dictionary lifecycle event {'msg': "built Dictionary<1051 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2272 corpus positions)", 'datetime': '2024-11-18T09:32:32.073619', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:32:32,074 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:32:32,074 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:32:32,074 - using serial LDA version on this node
+2024-11-18 09:32:32,075 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:32:32,075 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:32:32,078 - -7.978 per-word bound, 252.1 perplexity estimate based on a held-out corpus of 1 documents with 2272 words
+2024-11-18 09:32:32,078 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:32:32,080 - topic #0 (0.333): 0.014*"’" + 0.008*"needs" + 0.007*"plans" + 0.007*"quality" + 0.007*"2024" + 0.006*"well" + 0.005*"need" + 0.005*"practice" + 0.005*"East" + 0.005*"access"
+2024-11-18 09:32:32,080 - topic #1 (0.333): 0.013*"’" + 0.008*"2024" + 0.008*"practice" + 0.007*"well" + 0.007*"needs" + 0.006*"Cheshire" + 0.006*"plans" + 0.005*"means" + 0.005*"leaders" + 0.005*"East"
+2024-11-18 09:32:32,080 - topic #2 (0.333): 0.011*"’" + 0.007*"2024" + 0.007*"needs" + 0.007*"plans" + 0.006*"East" + 0.006*"practice" + 0.006*"well" + 0.006*"quality" + 0.006*"leaders" + 0.005*"Cheshire"
+2024-11-18 09:32:32,080 - topic diff=0.775576, rho=1.000000
+2024-11-18 09:32:32,080 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1051, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:32:32.080552', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:32:32,940 - Inspection date 2024-02-26 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:32:32,940 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:32,941 - Inspection date 2024-02-26 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:32:32,941 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:32,941 - Inspection date 2024-02-26 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:32:32,941 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:32,941 - Inspection date 2024-02-26 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:32:32,941 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:32,941 - Inspection date 2024-02-26 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:32:32,941 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:32,942 - Inspection date 2024-02-26 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:32:32,942 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:43,382 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:32:43,384 - built Dictionary<1010 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2203 corpus positions)
+2024-11-18 09:32:43,384 - Dictionary lifecycle event {'msg': "built Dictionary<1010 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2203 corpus positions)", 'datetime': '2024-11-18T09:32:43.384872', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:32:43,385 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:32:43,385 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:32:43,386 - using serial LDA version on this node
+2024-11-18 09:32:43,386 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:32:43,386 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:32:43,390 - -7.929 per-word bound, 243.7 perplexity estimate based on a held-out corpus of 1 documents with 2203 words
+2024-11-18 09:32:43,390 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:32:43,391 - topic #0 (0.333): 0.016*"’" + 0.005*"well" + 0.005*"needs" + 0.005*"Cheshire" + 0.005*"2024" + 0.004*"meetings" + 0.004*"good" + 0.004*"plans" + 0.004*"15" + 0.004*"impact"
+2024-11-18 09:32:43,391 - topic #1 (0.333): 0.011*"’" + 0.006*"needs" + 0.006*"plans" + 0.005*"well" + 0.005*"good" + 0.005*"impact" + 0.004*"Chester" + 0.004*"19" + 0.004*"progress" + 0.004*"protection"
+2024-11-18 09:32:43,391 - topic #2 (0.333): 0.018*"’" + 0.007*"progress" + 0.007*"well" + 0.007*"needs" + 0.006*"West" + 0.006*"plans" + 0.005*"access" + 0.005*"impact" + 0.005*"practice" + 0.005*"Chester"
+2024-11-18 09:32:43,391 - topic diff=0.793646, rho=1.000000
+2024-11-18 09:32:43,391 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1010, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:32:43.391970', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:32:44,272 - Inspection date 2024-07-15 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:32:44,272 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:44,272 - Inspection date 2024-07-15 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:32:44,272 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:44,272 - Inspection date 2024-07-15 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:32:44,272 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:44,272 - Inspection date 2024-07-15 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:32:44,272 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:44,272 - Inspection date 2024-07-15 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:32:44,273 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:44,273 - Inspection date 2024-07-15 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:32:44,273 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:55,150 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:32:55,152 - built Dictionary<1164 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2639 corpus positions)
+2024-11-18 09:32:55,152 - Dictionary lifecycle event {'msg': "built Dictionary<1164 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2639 corpus positions)", 'datetime': '2024-11-18T09:32:55.152921', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:32:55,154 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:32:55,154 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:32:55,154 - using serial LDA version on this node
+2024-11-18 09:32:55,154 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:32:55,154 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:32:55,158 - -8.054 per-word bound, 265.7 perplexity estimate based on a held-out corpus of 1 documents with 2639 words
+2024-11-18 09:32:55,158 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:32:55,160 - topic #0 (0.333): 0.013*"’" + 0.006*"plans" + 0.004*"Bradford" + 0.004*"need" + 0.004*"◼" + 0.004*"needs" + 0.004*"Borough" + 0.004*"changes" + 0.004*"2" + 0.004*"risk"
+2024-11-18 09:32:55,160 - topic #1 (0.333): 0.023*"’" + 0.007*"plans" + 0.005*"needs" + 0.005*"2" + 0.005*"Bradford" + 0.005*"risk" + 0.005*"need" + 0.005*"quality" + 0.005*"December" + 0.005*"practice"
+2024-11-18 09:32:55,160 - topic #2 (0.333): 0.023*"’" + 0.006*"plans" + 0.006*"21" + 0.005*"2022" + 0.005*"impact" + 0.005*"City" + 0.004*"Borough" + 0.004*"many" + 0.004*"Bradford" + 0.004*"Council"
+2024-11-18 09:32:55,160 - topic diff=0.813579, rho=1.000000
+2024-11-18 09:32:55,160 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1164, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:32:55.160819', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:32:56,011 - Inspection date 2022-11-21 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:32:56,011 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:56,011 - Inspection date 2022-11-21 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:32:56,011 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:56,011 - Inspection date 2022-11-21 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:32:56,011 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:56,011 - Inspection date 2022-11-21 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:32:56,012 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:56,012 - Inspection date 2022-11-21 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:32:56,012 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:32:56,012 - Inspection date 2022-11-21 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:32:56,012 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:06,443 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:33:06,445 - built Dictionary<1105 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2273 corpus positions)
+2024-11-18 09:33:06,445 - Dictionary lifecycle event {'msg': "built Dictionary<1105 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2273 corpus positions)", 'datetime': '2024-11-18T09:33:06.445644', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:33:06,446 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:33:06,446 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:33:06,447 - using serial LDA version on this node
+2024-11-18 09:33:06,447 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:33:06,447 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:33:06,450 - -8.063 per-word bound, 267.3 perplexity estimate based on a held-out corpus of 1 documents with 2273 words
+2024-11-18 09:33:06,451 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:33:06,452 - topic #0 (0.333): 0.017*"’" + 0.008*"City" + 0.008*"London" + 0.006*"well" + 0.005*"needs" + 0.005*"progress" + 0.004*"experiences" + 0.004*"practice" + 0.003*"27" + 0.003*"effective"
+2024-11-18 09:33:06,452 - topic #1 (0.333): 0.024*"’" + 0.011*"City" + 0.010*"well" + 0.008*"London" + 0.006*"needs" + 0.006*"plans" + 0.005*"practice" + 0.005*"effective" + 0.005*"strong" + 0.005*"progress"
+2024-11-18 09:33:06,452 - topic #2 (0.333): 0.024*"’" + 0.009*"City" + 0.008*"needs" + 0.006*"London" + 0.006*"well" + 0.006*"practice" + 0.005*"progress" + 0.005*"plans" + 0.005*"2024" + 0.004*"experiences"
+2024-11-18 09:33:06,452 - topic diff=0.765607, rho=1.000000
+2024-11-18 09:33:06,452 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1105, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:33:06.452976', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:33:07,316 - Inspection date 2024-09-23 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:33:07,316 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:07,316 - Inspection date 2024-09-23 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:33:07,316 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:07,316 - Inspection date 2024-09-23 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:33:07,317 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:07,317 - Inspection date 2024-09-23 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:33:07,317 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:07,317 - Inspection date 2024-09-23 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:33:07,317 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:07,317 - Inspection date 2024-09-23 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:33:07,317 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:16,906 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:33:16,908 - built Dictionary<1007 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2281 corpus positions)
+2024-11-18 09:33:16,909 - Dictionary lifecycle event {'msg': "built Dictionary<1007 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2281 corpus positions)", 'datetime': '2024-11-18T09:33:16.909062', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:33:16,910 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:33:16,910 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:33:16,910 - using serial LDA version on this node
+2024-11-18 09:33:16,910 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:33:16,910 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:33:16,914 - -7.903 per-word bound, 239.4 perplexity estimate based on a held-out corpus of 1 documents with 2281 words
+2024-11-18 09:33:16,914 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:33:16,915 - topic #0 (0.333): 0.018*"’" + 0.009*"Wakefield" + 0.008*"well" + 0.008*"quality" + 0.008*"leaders" + 0.007*"November" + 0.007*"good" + 0.006*"effective" + 0.006*"plans" + 0.006*"19"
+2024-11-18 09:33:16,915 - topic #1 (0.333): 0.015*"’" + 0.007*"Wakefield" + 0.007*"November" + 0.006*"quality" + 0.006*"good" + 0.005*"plans" + 0.005*"leaders" + 0.005*"effective" + 0.005*"well" + 0.005*"practice"
+2024-11-18 09:33:16,915 - topic #2 (0.333): 0.017*"’" + 0.008*"well" + 0.008*"leaders" + 0.008*"effective" + 0.007*"quality" + 0.007*"Wakefield" + 0.006*"November" + 0.006*"progress" + 0.006*"good" + 0.006*"practice"
+2024-11-18 09:33:16,915 - topic diff=0.801995, rho=1.000000
+2024-11-18 09:33:16,915 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1007, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:33:16.915966', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:33:17,749 - Inspection date 2021-11-08 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:33:17,749 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:17,749 - Inspection date 2021-11-08 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:33:17,749 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:17,750 - Inspection date 2021-11-08 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:33:17,750 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:17,750 - Inspection date 2021-11-08 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:33:17,750 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:17,750 - Inspection date 2021-11-08 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:33:17,750 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:17,750 - Inspection date 2021-11-08 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:33:17,750 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:26,735 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:33:26,736 - built Dictionary<909 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1855 corpus positions)
+2024-11-18 09:33:26,737 - Dictionary lifecycle event {'msg': "built Dictionary<909 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1855 corpus positions)", 'datetime': '2024-11-18T09:33:26.737016', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:33:26,737 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:33:26,737 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:33:26,738 - using serial LDA version on this node
+2024-11-18 09:33:26,738 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:33:26,738 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:33:26,741 - -7.863 per-word bound, 232.8 perplexity estimate based on a held-out corpus of 1 documents with 1855 words
+2024-11-18 09:33:26,741 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:33:26,742 - topic #0 (0.333): 0.020*"’" + 0.009*"needs" + 0.007*"quality" + 0.006*"March" + 0.006*"ensure" + 0.005*"well" + 0.005*"supported" + 0.005*"practice" + 0.005*"effective" + 0.005*"education"
+2024-11-18 09:33:26,743 - topic #1 (0.333): 0.011*"’" + 0.007*"March" + 0.006*"ensure" + 0.006*"quality" + 0.006*"needs" + 0.006*"However" + 0.006*"effective" + 0.005*"7" + 0.005*"plans" + 0.005*"York"
+2024-11-18 09:33:26,743 - topic #2 (0.333): 0.011*"’" + 0.008*"March" + 0.007*"quality" + 0.007*"effective" + 0.006*"needs" + 0.006*"York" + 0.005*"plans" + 0.005*"training" + 0.005*"good" + 0.005*"However"
+2024-11-18 09:33:26,743 - topic diff=0.764890, rho=1.000000
+2024-11-18 09:33:26,743 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=909, num_topics=3, decay=0.5, chunksize=2000> in 0.00s', 'datetime': '2024-11-18T09:33:26.743341', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:33:27,545 - Inspection date 2022-03-07 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:33:27,545 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:27,545 - Inspection date 2022-03-07 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:33:27,546 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:27,546 - Inspection date 2022-03-07 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:33:27,546 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:27,546 - Inspection date 2022-03-07 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:33:27,546 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:27,546 - Inspection date 2022-03-07 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:33:27,546 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:27,546 - Inspection date 2022-03-07 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:33:27,547 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:37,216 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:33:37,218 - built Dictionary<1053 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2351 corpus positions)
+2024-11-18 09:33:37,218 - Dictionary lifecycle event {'msg': "built Dictionary<1053 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2351 corpus positions)", 'datetime': '2024-11-18T09:33:37.218786', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:33:37,219 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:33:37,219 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:33:37,220 - using serial LDA version on this node
+2024-11-18 09:33:37,220 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:33:37,220 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:33:37,223 - -7.957 per-word bound, 248.5 perplexity estimate based on a held-out corpus of 1 documents with 2351 words
+2024-11-18 09:33:37,224 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:33:37,225 - topic #0 (0.333): 0.019*"’" + 0.008*"needs" + 0.006*"well" + 0.006*"Cornwall" + 0.006*"receive" + 0.006*"need" + 0.006*"effective" + 0.005*"risk" + 0.005*"supported" + 0.005*"approach"
+2024-11-18 09:33:37,225 - topic #1 (0.333): 0.020*"’" + 0.011*"needs" + 0.008*"Cornwall" + 0.007*"need" + 0.006*"well" + 0.005*"receive" + 0.005*"1" + 0.005*"5" + 0.005*"2024" + 0.005*"oversight"
+2024-11-18 09:33:37,225 - topic #2 (0.333): 0.015*"’" + 0.008*"Cornwall" + 0.007*"need" + 0.007*"needs" + 0.006*"well" + 0.004*"homes" + 0.004*"1" + 0.004*"effective" + 0.004*"progress" + 0.004*"receive"
+2024-11-18 09:33:37,225 - topic diff=0.796286, rho=1.000000
+2024-11-18 09:33:37,225 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1053, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:33:37.225935', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:33:38,081 - Inspection date 2024-07-01 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:33:38,081 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:38,082 - Inspection date 2024-07-01 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:33:38,082 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:38,082 - Inspection date 2024-07-01 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:33:38,082 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:38,082 - Inspection date 2024-07-01 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:33:38,082 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:38,082 - Inspection date 2024-07-01 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:33:38,082 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:38,083 - Inspection date 2024-07-01 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:33:38,083 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:45,463 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:33:45,465 - built Dictionary<754 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1521 corpus positions)
+2024-11-18 09:33:45,465 - Dictionary lifecycle event {'msg': "built Dictionary<754 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1521 corpus positions)", 'datetime': '2024-11-18T09:33:45.465278', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:33:45,466 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:33:45,466 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:33:45,466 - using serial LDA version on this node
+2024-11-18 09:33:45,466 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:33:45,466 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:33:45,469 - -7.691 per-word bound, 206.6 perplexity estimate based on a held-out corpus of 1 documents with 1521 words
+2024-11-18 09:33:45,469 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:33:45,470 - topic #0 (0.333): 0.021*"’" + 0.013*"Scilly" + 0.011*"Isles" + 0.008*"needs" + 0.008*"need" + 0.007*"information" + 0.007*"practice" + 0.007*"place" + 0.006*"quality" + 0.005*"protection"
+2024-11-18 09:33:45,470 - topic #1 (0.333): 0.022*"’" + 0.013*"Isles" + 0.010*"practice" + 0.009*"information" + 0.009*"Scilly" + 0.006*"need" + 0.006*"risks" + 0.006*"place" + 0.006*"protection" + 0.005*"2023"
+2024-11-18 09:33:45,470 - topic #2 (0.333): 0.020*"’" + 0.013*"Scilly" + 0.012*"Isles" + 0.010*"information" + 0.009*"need" + 0.008*"protection" + 0.008*"practice" + 0.007*"needs" + 0.006*"11" + 0.006*"quality"
+2024-11-18 09:33:45,470 - topic diff=0.752926, rho=1.000000
+2024-11-18 09:33:45,470 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=754, num_topics=3, decay=0.5, chunksize=2000> in 0.00s', 'datetime': '2024-11-18T09:33:45.470941', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:33:46,331 - Inspection date 2023-07-11 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:33:46,331 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:46,332 - Inspection date 2023-07-11 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:33:46,332 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:46,332 - Inspection date 2023-07-11 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:33:46,332 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:46,333 - Inspection date 2023-07-11 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:33:46,333 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:46,333 - Inspection date 2023-07-11 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:33:46,333 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:46,333 - Inspection date 2023-07-11 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:33:46,334 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:57,181 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:33:57,184 - built Dictionary<938 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2074 corpus positions)
+2024-11-18 09:33:57,185 - Dictionary lifecycle event {'msg': "built Dictionary<938 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2074 corpus positions)", 'datetime': '2024-11-18T09:33:57.185268', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:33:57,187 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:33:57,187 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:33:57,187 - using serial LDA version on this node
+2024-11-18 09:33:57,188 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:33:57,188 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:33:57,193 - -7.847 per-word bound, 230.2 perplexity estimate based on a held-out corpus of 1 documents with 2074 words
+2024-11-18 09:33:57,193 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:33:57,194 - topic #0 (0.333): 0.018*"’" + 0.008*"Coventry" + 0.008*"well" + 0.007*"needs" + 0.007*"strong" + 0.007*"plans" + 0.006*"family" + 0.006*"supported" + 0.005*"20" + 0.005*"need"
+2024-11-18 09:33:57,195 - topic #1 (0.333): 0.016*"’" + 0.008*"well" + 0.007*"supported" + 0.007*"Coventry" + 0.005*"family" + 0.005*"need" + 0.005*"needs" + 0.004*"plans" + 0.004*"strong" + 0.004*"20"
+2024-11-18 09:33:57,195 - topic #2 (0.333): 0.022*"’" + 0.009*"needs" + 0.009*"Coventry" + 0.008*"well" + 0.007*"supported" + 0.006*"plans" + 0.006*"family" + 0.005*"need" + 0.005*"PAs" + 0.005*"strong"
+2024-11-18 09:33:57,195 - topic diff=0.803928, rho=1.000000
+2024-11-18 09:33:57,195 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=938, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:33:57.195568', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:33:58,123 - Inspection date 2022-06-20 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:33:58,123 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:58,124 - Inspection date 2022-06-20 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:33:58,124 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:58,124 - Inspection date 2022-06-20 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:33:58,124 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:58,124 - Inspection date 2022-06-20 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:33:58,124 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:58,125 - Inspection date 2022-06-20 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:33:58,125 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:33:58,125 - Inspection date 2022-06-20 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:33:58,125 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:11,384 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:34:11,387 - built Dictionary<1195 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2653 corpus positions)
+2024-11-18 09:34:11,387 - Dictionary lifecycle event {'msg': "built Dictionary<1195 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2653 corpus positions)", 'datetime': '2024-11-18T09:34:11.387273', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:34:11,389 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:34:11,389 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:34:11,390 - using serial LDA version on this node
+2024-11-18 09:34:11,390 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:34:11,390 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:34:11,396 - -8.085 per-word bound, 271.5 perplexity estimate based on a held-out corpus of 1 documents with 2653 words
+2024-11-18 09:34:11,396 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:34:11,398 - topic #0 (0.333): 0.018*"’" + 0.009*"well" + 0.007*"leaders" + 0.007*"needs" + 0.006*"Darlington" + 0.006*"practice" + 0.005*"October" + 0.005*"effective" + 0.005*"education" + 0.005*"quality"
+2024-11-18 09:34:11,398 - topic #1 (0.333): 0.022*"’" + 0.008*"well" + 0.008*"October" + 0.007*"practice" + 0.006*"needs" + 0.006*"Darlington" + 0.006*"leaders" + 0.005*"quality" + 0.004*"effective" + 0.004*"need"
+2024-11-18 09:34:11,398 - topic #2 (0.333): 0.014*"’" + 0.007*"October" + 0.006*"leaders" + 0.006*"needs" + 0.006*"practice" + 0.005*"well" + 0.004*"plans" + 0.004*"effective" + 0.004*"supported" + 0.004*"Darlington"
+2024-11-18 09:34:11,398 - topic diff=0.796905, rho=1.000000
+2024-11-18 09:34:11,398 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1195, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:34:11.398760', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:34:12,335 - Inspection date 2022-10-10 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:34:12,336 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:12,336 - Inspection date 2022-10-10 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:34:12,336 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:12,336 - Inspection date 2022-10-10 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:34:12,336 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:12,336 - Inspection date 2022-10-10 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:34:12,336 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:12,336 - Inspection date 2022-10-10 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:34:12,337 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:12,337 - Inspection date 2022-10-10 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:34:12,337 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:23,830 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:34:23,832 - built Dictionary<1121 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2396 corpus positions)
+2024-11-18 09:34:23,832 - Dictionary lifecycle event {'msg': "built Dictionary<1121 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2396 corpus positions)", 'datetime': '2024-11-18T09:34:23.832700', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:34:23,833 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:34:23,833 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:34:23,834 - using serial LDA version on this node
+2024-11-18 09:34:23,834 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:34:23,834 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:34:23,838 - -8.047 per-word bound, 264.5 perplexity estimate based on a held-out corpus of 1 documents with 2396 words
+2024-11-18 09:34:23,838 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:34:23,839 - topic #0 (0.333): 0.017*"’" + 0.008*"needs" + 0.008*"receive" + 0.006*"Derby" + 0.006*"quality" + 0.006*"good" + 0.006*"well" + 0.006*"need" + 0.006*"plans" + 0.006*"progress"
+2024-11-18 09:34:23,839 - topic #1 (0.333): 0.024*"’" + 0.010*"needs" + 0.008*"Derby" + 0.006*"well" + 0.006*"progress" + 0.006*"appropriate" + 0.006*"receive" + 0.006*"quality" + 0.005*"good" + 0.005*"plans"
+2024-11-18 09:34:23,840 - topic #2 (0.333): 0.022*"’" + 0.010*"needs" + 0.007*"Derby" + 0.007*"quality" + 0.007*"leaders" + 0.006*"plans" + 0.005*"need" + 0.005*"ensure" + 0.005*"21" + 0.004*"receive"
+2024-11-18 09:34:23,840 - topic diff=0.770589, rho=1.000000
+2024-11-18 09:34:23,840 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1121, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:34:23.840296', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:34:24,738 - Inspection date 2022-03-21 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:34:24,739 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:24,739 - Inspection date 2022-03-21 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:34:24,739 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:24,739 - Inspection date 2022-03-21 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:34:24,739 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:24,739 - Inspection date 2022-03-21 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:34:24,739 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:24,739 - Inspection date 2022-03-21 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:34:24,739 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:24,739 - Inspection date 2022-03-21 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:34:24,740 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:33,915 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:34:33,917 - built Dictionary<1046 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2035 corpus positions)
+2024-11-18 09:34:33,917 - Dictionary lifecycle event {'msg': "built Dictionary<1046 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2035 corpus positions)", 'datetime': '2024-11-18T09:34:33.917432', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:34:33,918 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:34:33,918 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:34:33,918 - using serial LDA version on this node
+2024-11-18 09:34:33,919 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:34:33,919 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:34:33,922 - -8.037 per-word bound, 262.6 perplexity estimate based on a held-out corpus of 1 documents with 2035 words
+2024-11-18 09:34:33,922 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:34:33,923 - topic #0 (0.333): 0.013*"’" + 0.007*"well" + 0.006*"Derbyshire" + 0.005*"leaders" + 0.005*"number" + 0.005*"needs" + 0.005*"10" + 0.004*"plans" + 0.004*"effective" + 0.004*"good"
+2024-11-18 09:34:33,923 - topic #1 (0.333): 0.013*"’" + 0.009*"well" + 0.007*"Derbyshire" + 0.005*"positive" + 0.005*"need" + 0.005*"education" + 0.005*"10" + 0.004*"good" + 0.004*"quality" + 0.004*"November"
+2024-11-18 09:34:33,924 - topic #2 (0.333): 0.015*"’" + 0.008*"well" + 0.006*"Derbyshire" + 0.006*"plans" + 0.005*"effective" + 0.005*"needs" + 0.005*"health" + 0.005*"positive" + 0.005*"practice" + 0.004*"30"
+2024-11-18 09:34:33,924 - topic diff=0.738504, rho=1.000000
+2024-11-18 09:34:33,924 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1046, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:34:33.924350', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:34:34,816 - Inspection date 2023-10-30 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:34:34,816 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:34,816 - Inspection date 2023-10-30 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:34:34,817 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:34,817 - Inspection date 2023-10-30 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:34:34,817 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:34,817 - Inspection date 2023-10-30 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:34:34,817 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:34,817 - Inspection date 2023-10-30 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:34:34,817 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:34,817 - Inspection date 2023-10-30 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:34:34,817 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:45,398 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:34:45,401 - built Dictionary<1175 unique tokens: ['0161', '0300', '1', '1,000', '10']...> from 1 documents (total 2313 corpus positions)
+2024-11-18 09:34:45,401 - Dictionary lifecycle event {'msg': "built Dictionary<1175 unique tokens: ['0161', '0300', '1', '1,000', '10']...> from 1 documents (total 2313 corpus positions)", 'datetime': '2024-11-18T09:34:45.401236', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:34:45,402 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:34:45,402 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:34:45,402 - using serial LDA version on this node
+2024-11-18 09:34:45,403 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:34:45,403 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:34:45,406 - -8.149 per-word bound, 283.8 perplexity estimate based on a held-out corpus of 1 documents with 2313 words
+2024-11-18 09:34:45,407 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:34:45,408 - topic #0 (0.333): 0.008*"’" + 0.006*"leaders" + 0.006*"well" + 0.005*"risk" + 0.004*"progress" + 0.004*"health" + 0.004*"protection" + 0.004*"need" + 0.004*"needs" + 0.004*"practice"
+2024-11-18 09:34:45,408 - topic #1 (0.333): 0.011*"’" + 0.006*"well" + 0.005*"health" + 0.005*"risk" + 0.005*"progress" + 0.005*"Devon" + 0.004*"leaders" + 0.004*"case" + 0.004*"areas" + 0.004*"protection"
+2024-11-18 09:34:45,408 - topic #2 (0.333): 0.008*"’" + 0.005*"well" + 0.004*"health" + 0.004*"time" + 0.004*"risk" + 0.004*"including" + 0.004*"progress" + 0.004*"plans" + 0.004*"quality" + 0.003*"information"
+2024-11-18 09:34:45,408 - topic diff=0.734563, rho=1.000000
+2024-11-18 09:34:45,408 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1175, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:34:45.408948', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:34:46,367 - Inspection date 2020-01-20 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:34:46,368 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:46,368 - Inspection date 2020-01-20 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:34:46,368 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:46,368 - Inspection date 2020-01-20 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:34:46,368 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:46,368 - Inspection date 2020-01-20 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:34:46,368 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:46,369 - Inspection date 2020-01-20 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:34:46,369 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:46,369 - Inspection date 2020-01-20 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:34:46,369 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:56,776 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:34:56,778 - built Dictionary<1175 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2429 corpus positions)
+2024-11-18 09:34:56,778 - Dictionary lifecycle event {'msg': "built Dictionary<1175 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2429 corpus positions)", 'datetime': '2024-11-18T09:34:56.778839', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:34:56,779 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:34:56,780 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:34:56,780 - using serial LDA version on this node
+2024-11-18 09:34:56,780 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:34:56,780 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:34:56,784 - -8.110 per-word bound, 276.2 perplexity estimate based on a held-out corpus of 1 documents with 2429 words
+2024-11-18 09:34:56,784 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:34:56,785 - topic #0 (0.333): 0.020*"’" + 0.006*"leaders" + 0.005*"well" + 0.005*"information" + 0.005*"Doncaster" + 0.005*"progress" + 0.004*"many" + 0.004*"arrangements" + 0.004*"receive" + 0.004*"quality"
+2024-11-18 09:34:56,786 - topic #1 (0.333): 0.024*"’" + 0.009*"well" + 0.006*"Doncaster" + 0.006*"quality" + 0.005*"records" + 0.005*"oversight" + 0.005*"plans" + 0.005*"progress" + 0.005*"Trust" + 0.005*"many"
+2024-11-18 09:34:56,786 - topic #2 (0.333): 0.012*"’" + 0.006*"Doncaster" + 0.005*"records" + 0.005*"many" + 0.005*"arrangements" + 0.004*"plans" + 0.004*"25" + 0.004*"information" + 0.004*"progress" + 0.004*"protection"
+2024-11-18 09:34:56,786 - topic diff=0.786649, rho=1.000000
+2024-11-18 09:34:56,786 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1175, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:34:56.786432', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:34:58,568 - Inspection date 2022-02-14 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:34:58,568 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:58,568 - Inspection date 2022-02-14 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:34:58,569 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:58,569 - Inspection date 2022-02-14 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:34:58,569 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:58,569 - Inspection date 2022-02-14 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:34:58,569 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:58,569 - Inspection date 2022-02-14 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:34:58,569 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:34:58,569 - Inspection date 2022-02-14 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:34:58,569 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:06,551 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:35:06,553 - built Dictionary<1067 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1942 corpus positions)
+2024-11-18 09:35:06,554 - Dictionary lifecycle event {'msg': "built Dictionary<1067 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1942 corpus positions)", 'datetime': '2024-11-18T09:35:06.554062', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:35:06,555 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:35:06,555 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:35:06,555 - using serial LDA version on this node
+2024-11-18 09:35:06,555 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:35:06,555 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:35:06,559 - -8.103 per-word bound, 275.0 perplexity estimate based on a held-out corpus of 1 documents with 1942 words
+2024-11-18 09:35:06,559 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:35:06,560 - topic #0 (0.333): 0.019*"’" + 0.008*"Dorset" + 0.007*"good" + 0.007*"well" + 0.005*"arrangements" + 0.005*"impact" + 0.005*"needs" + 0.004*"change" + 0.004*"October" + 0.004*"27"
+2024-11-18 09:35:06,560 - topic #1 (0.333): 0.010*"’" + 0.008*"Dorset" + 0.005*"good" + 0.004*"8" + 0.004*"well" + 0.004*"arrangements" + 0.004*"needs" + 0.004*"quality" + 0.004*"27" + 0.004*"including"
+2024-11-18 09:35:06,561 - topic #2 (0.333): 0.009*"’" + 0.007*"Dorset" + 0.005*"good" + 0.005*"well" + 0.004*"leaders" + 0.004*"needs" + 0.004*"8" + 0.004*"quality" + 0.004*"supported" + 0.004*"arrangements"
+2024-11-18 09:35:06,561 - topic diff=0.732369, rho=1.000000
+2024-11-18 09:35:06,561 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1067, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:35:06.561229', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:35:07,402 - Inspection date 2021-09-27 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:35:07,402 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:07,402 - Inspection date 2021-09-27 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:35:07,402 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:07,403 - Inspection date 2021-09-27 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:35:07,403 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:07,403 - Inspection date 2021-09-27 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:35:07,403 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:07,403 - Inspection date 2021-09-27 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:35:07,403 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:07,403 - Inspection date 2021-09-27 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:35:07,403 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:17,284 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:35:17,286 - built Dictionary<1050 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2138 corpus positions)
+2024-11-18 09:35:17,287 - Dictionary lifecycle event {'msg': "built Dictionary<1050 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2138 corpus positions)", 'datetime': '2024-11-18T09:35:17.287070', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:35:17,288 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:35:17,288 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:35:17,288 - using serial LDA version on this node
+2024-11-18 09:35:17,288 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:35:17,288 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:35:17,292 - -8.011 per-word bound, 258.0 perplexity estimate based on a held-out corpus of 1 documents with 2138 words
+2024-11-18 09:35:17,292 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:35:17,293 - topic #0 (0.333): 0.017*"’" + 0.011*"needs" + 0.007*"Dudley" + 0.005*"well" + 0.005*"However" + 0.005*"always" + 0.005*"plans" + 0.005*"oversight" + 0.005*"quality" + 0.004*"31"
+2024-11-18 09:35:17,293 - topic #1 (0.333): 0.015*"’" + 0.014*"needs" + 0.008*"Dudley" + 0.006*"arrangements" + 0.005*"well" + 0.005*"always" + 0.004*"plans" + 0.004*"enough" + 0.004*"oversight" + 0.004*"2022"
+2024-11-18 09:35:17,293 - topic #2 (0.333): 0.013*"’" + 0.009*"Dudley" + 0.008*"needs" + 0.006*"plans" + 0.005*"arrangements" + 0.005*"well" + 0.005*"always" + 0.005*"ensure" + 0.005*"quality" + 0.004*"November"
+2024-11-18 09:35:17,294 - topic diff=0.754603, rho=1.000000
+2024-11-18 09:35:17,294 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1050, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:35:17.294128', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:35:18,153 - Inspection date 2022-10-31 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:35:18,153 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:18,153 - Inspection date 2022-10-31 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:35:18,154 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:18,154 - Inspection date 2022-10-31 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:35:18,154 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:18,154 - Inspection date 2022-10-31 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:35:18,154 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:18,154 - Inspection date 2022-10-31 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:35:18,155 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:18,155 - Inspection date 2022-10-31 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:35:18,155 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:28,976 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:35:28,978 - built Dictionary<1051 unique tokens: ['0', '0161', '0300', '1', '10']...> from 1 documents (total 2278 corpus positions)
+2024-11-18 09:35:28,979 - Dictionary lifecycle event {'msg': "built Dictionary<1051 unique tokens: ['0', '0161', '0300', '1', '10']...> from 1 documents (total 2278 corpus positions)", 'datetime': '2024-11-18T09:35:28.979134', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:35:28,980 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:35:28,980 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:35:28,980 - using serial LDA version on this node
+2024-11-18 09:35:28,981 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:35:28,981 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:35:28,984 - -7.978 per-word bound, 252.2 perplexity estimate based on a held-out corpus of 1 documents with 2278 words
+2024-11-18 09:35:28,985 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:35:28,986 - topic #0 (0.333): 0.015*"’" + 0.012*"needs" + 0.008*"well" + 0.007*"Durham" + 0.007*"plans" + 0.006*"May" + 0.005*"ensure" + 0.005*"practice" + 0.005*"risks" + 0.005*"supported"
+2024-11-18 09:35:28,986 - topic #1 (0.333): 0.015*"’" + 0.009*"May" + 0.008*"needs" + 0.007*"Durham" + 0.007*"plans" + 0.006*"ensure" + 0.006*"well" + 0.005*"leaders" + 0.005*"practice" + 0.004*"family"
+2024-11-18 09:35:28,986 - topic #2 (0.333): 0.012*"’" + 0.011*"needs" + 0.006*"ensure" + 0.006*"Durham" + 0.006*"well" + 0.006*"May" + 0.006*"plans" + 0.005*"practice" + 0.004*"10" + 0.004*"family"
+2024-11-18 09:35:28,986 - topic diff=0.775707, rho=1.000000
+2024-11-18 09:35:28,986 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1051, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:35:28.986930', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:35:29,953 - Inspection date 2022-05-09 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:35:29,953 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:29,953 - Inspection date 2022-05-09 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:35:29,953 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:29,953 - Inspection date 2022-05-09 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:35:29,954 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:29,954 - Inspection date 2022-05-09 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:35:29,954 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:29,954 - Inspection date 2022-05-09 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:35:29,954 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:29,954 - Inspection date 2022-05-09 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:35:29,954 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:39,838 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:35:39,840 - built Dictionary<972 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2014 corpus positions)
+2024-11-18 09:35:39,840 - Dictionary lifecycle event {'msg': "built Dictionary<972 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2014 corpus positions)", 'datetime': '2024-11-18T09:35:39.840842', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:35:39,841 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:35:39,841 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:35:39,842 - using serial LDA version on this node
+2024-11-18 09:35:39,842 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:35:39,842 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:35:39,845 - -7.927 per-word bound, 243.3 perplexity estimate based on a held-out corpus of 1 documents with 2014 words
+2024-11-18 09:35:39,845 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:35:39,847 - topic #0 (0.333): 0.018*"’" + 0.009*"well" + 0.007*"plans" + 0.007*"progress" + 0.006*"needs" + 0.006*"Riding" + 0.006*"East" + 0.005*"10" + 0.004*"partners" + 0.004*"quality"
+2024-11-18 09:35:39,847 - topic #1 (0.333): 0.018*"’" + 0.011*"needs" + 0.010*"plans" + 0.009*"well" + 0.007*"progress" + 0.006*"East" + 0.006*"education" + 0.006*"Riding" + 0.005*"practice" + 0.005*"30"
+2024-11-18 09:35:39,847 - topic #2 (0.333): 0.011*"’" + 0.010*"needs" + 0.007*"plans" + 0.006*"Riding" + 0.006*"well" + 0.006*"East" + 0.005*"progress" + 0.005*"partners" + 0.005*"good" + 0.005*"10"
+2024-11-18 09:35:39,847 - topic diff=0.781359, rho=1.000000
+2024-11-18 09:35:39,847 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=972, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:35:39.847680', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:35:40,705 - Inspection date 2023-01-30 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:35:40,705 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:40,705 - Inspection date 2023-01-30 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:35:40,705 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:40,705 - Inspection date 2023-01-30 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:35:40,705 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:40,706 - Inspection date 2023-01-30 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:35:40,706 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:40,706 - Inspection date 2023-01-30 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:35:40,706 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:40,706 - Inspection date 2023-01-30 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:35:40,706 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:50,727 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:35:50,729 - built Dictionary<1111 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2220 corpus positions)
+2024-11-18 09:35:50,729 - Dictionary lifecycle event {'msg': "built Dictionary<1111 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2220 corpus positions)", 'datetime': '2024-11-18T09:35:50.729375', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:35:50,730 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:35:50,730 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:35:50,730 - using serial LDA version on this node
+2024-11-18 09:35:50,731 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:35:50,731 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:35:50,734 - -8.085 per-word bound, 271.6 perplexity estimate based on a held-out corpus of 1 documents with 2220 words
+2024-11-18 09:35:50,734 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:35:50,736 - topic #0 (0.333): 0.015*"’" + 0.009*"well" + 0.009*"East" + 0.008*"plans" + 0.007*"Sussex" + 0.007*"needs" + 0.006*"impact" + 0.005*"experiences" + 0.005*"including" + 0.005*"11"
+2024-11-18 09:35:50,736 - topic #1 (0.333): 0.019*"’" + 0.009*"well" + 0.008*"needs" + 0.008*"progress" + 0.007*"plans" + 0.006*"including" + 0.006*"impact" + 0.006*"Sussex" + 0.005*"East" + 0.005*"effective"
+2024-11-18 09:35:50,736 - topic #2 (0.333): 0.014*"’" + 0.010*"well" + 0.007*"plans" + 0.007*"needs" + 0.006*"progress" + 0.006*"including" + 0.006*"Sussex" + 0.005*"East" + 0.005*"provide" + 0.004*"relationships"
+2024-11-18 09:35:50,736 - topic diff=0.755786, rho=1.000000
+2024-11-18 09:35:50,736 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1111, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:35:50.736589', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:35:51,678 - Inspection date 2023-12-11 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:35:51,678 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:51,678 - Inspection date 2023-12-11 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:35:51,679 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:51,679 - Inspection date 2023-12-11 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:35:51,679 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:51,679 - Inspection date 2023-12-11 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:35:51,679 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:51,679 - Inspection date 2023-12-11 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:35:51,679 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:35:51,679 - Inspection date 2023-12-11 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:35:51,679 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:36:13,847 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:36:13,849 - built Dictionary<1142 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2686 corpus positions)
+2024-11-18 09:36:13,849 - Dictionary lifecycle event {'msg': "built Dictionary<1142 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2686 corpus positions)", 'datetime': '2024-11-18T09:36:13.849886', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:36:13,851 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:36:13,851 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:36:13,851 - using serial LDA version on this node
+2024-11-18 09:36:13,852 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:36:13,852 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:36:13,855 - -8.006 per-word bound, 257.0 perplexity estimate based on a held-out corpus of 1 documents with 2686 words
+2024-11-18 09:36:13,855 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:36:13,857 - topic #0 (0.333): 0.015*"’" + 0.007*"progress" + 0.006*"well" + 0.005*"needs" + 0.005*"Essex" + 0.004*"family" + 0.004*"quality" + 0.004*"helped" + 0.004*"supported" + 0.004*"impact"
+2024-11-18 09:36:13,857 - topic #1 (0.333): 0.023*"’" + 0.008*"plans" + 0.007*"well" + 0.007*"needs" + 0.006*"family" + 0.006*"progress" + 0.006*"risk" + 0.005*"Essex" + 0.005*"‘" + 0.005*"practice"
+2024-11-18 09:36:13,857 - topic #2 (0.333): 0.013*"’" + 0.007*"well" + 0.006*"progress" + 0.006*"needs" + 0.005*"understand" + 0.005*"new" + 0.005*"experiences" + 0.005*"plans" + 0.005*"30" + 0.004*"need"
+2024-11-18 09:36:13,857 - topic diff=0.805862, rho=1.000000
+2024-11-18 09:36:13,857 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1142, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:36:13.857806', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:36:14,752 - Inspection date 2023-06-26 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:36:14,752 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:36:14,753 - Inspection date 2023-06-26 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:36:14,753 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:36:14,753 - Inspection date 2023-06-26 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:36:14,753 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:36:14,753 - Inspection date 2023-06-26 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:36:14,753 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:36:14,753 - Inspection date 2023-06-26 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:36:14,754 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:36:14,754 - Inspection date 2023-06-26 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:36:14,754 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:36:24,606 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:36:24,608 - built Dictionary<1112 unique tokens: ['0161', '0300', '0–19', '1', '10']...> from 1 documents (total 2356 corpus positions)
+2024-11-18 09:36:24,608 - Dictionary lifecycle event {'msg': "built Dictionary<1112 unique tokens: ['0161', '0300', '0–19', '1', '10']...> from 1 documents (total 2356 corpus positions)", 'datetime': '2024-11-18T09:36:24.608821', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:36:24,610 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:36:24,610 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:36:24,610 - using serial LDA version on this node
+2024-11-18 09:36:24,610 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:36:24,610 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:36:24,614 - -8.039 per-word bound, 263.0 perplexity estimate based on a held-out corpus of 1 documents with 2356 words
+2024-11-18 09:36:24,614 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:36:24,615 - topic #0 (0.333): 0.016*"’" + 0.009*"effective" + 0.008*"practice" + 0.008*"good" + 0.007*"quality" + 0.007*"needs" + 0.006*"timely" + 0.005*"well" + 0.005*"team" + 0.005*"plans"
+2024-11-18 09:36:24,616 - topic #1 (0.333): 0.012*"’" + 0.008*"effective" + 0.007*"good" + 0.006*"practice" + 0.006*"needs" + 0.006*"well" + 0.005*"improve" + 0.005*"quality" + 0.004*"focus" + 0.004*"timely"
+2024-11-18 09:36:24,616 - topic #2 (0.333): 0.012*"’" + 0.007*"effective" + 0.006*"quality" + 0.006*"well" + 0.005*"need" + 0.005*"timely" + 0.005*"plans" + 0.004*"good" + 0.004*"improve" + 0.004*"needs"
+2024-11-18 09:36:24,616 - topic diff=0.765424, rho=1.000000
+2024-11-18 09:36:24,616 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1112, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:36:24.616465', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:36:25,517 - Inspection date 2019-04-29 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:36:25,517 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:36:25,517 - Inspection date 2019-04-29 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:36:25,518 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:36:25,518 - Inspection date 2019-04-29 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:36:25,518 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:36:25,518 - Inspection date 2019-04-29 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:36:25,518 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:36:25,518 - Inspection date 2019-04-29 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:36:25,518 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:36:25,518 - Inspection date 2019-04-29 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:36:25,518 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:36:36,049 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:36:36,051 - built Dictionary<1161 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2579 corpus positions)
+2024-11-18 09:36:36,051 - Dictionary lifecycle event {'msg': "built Dictionary<1161 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2579 corpus positions)", 'datetime': '2024-11-18T09:36:36.051770', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:36:36,052 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:36:36,053 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:36:36,053 - using serial LDA version on this node
+2024-11-18 09:36:36,053 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:36:36,053 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:36:36,057 - -8.056 per-word bound, 266.0 perplexity estimate based on a held-out corpus of 1 documents with 2579 words
+2024-11-18 09:36:36,057 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:36:36,058 - topic #0 (0.333): 0.015*"’" + 0.008*"needs" + 0.008*"plans" + 0.006*"2022" + 0.005*"February" + 0.005*"well" + 0.005*"progress" + 0.005*"effective" + 0.005*"experienced" + 0.004*"leaders"
+2024-11-18 09:36:36,058 - topic #1 (0.333): 0.019*"’" + 0.009*"needs" + 0.007*"2022" + 0.007*"February" + 0.006*"Gloucestershire" + 0.006*"plans" + 0.005*"18" + 0.005*"timely" + 0.005*"progress" + 0.005*"appropriate"
+2024-11-18 09:36:36,059 - topic #2 (0.333): 0.018*"’" + 0.008*"February" + 0.008*"needs" + 0.007*"2022" + 0.007*"well" + 0.006*"plans" + 0.005*"family" + 0.005*"good" + 0.005*"experienced" + 0.005*"leaders"
+2024-11-18 09:36:36,059 - topic diff=0.820073, rho=1.000000
+2024-11-18 09:36:36,059 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1161, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:36:36.059229', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:36:36,977 - Inspection date 2022-02-07 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:36:36,977 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:36:36,978 - Inspection date 2022-02-07 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:36:36,978 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:36:36,978 - Inspection date 2022-02-07 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:36:36,979 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:36:36,979 - Inspection date 2022-02-07 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:36:36,979 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:36:36,979 - Inspection date 2022-02-07 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:36:36,979 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:36:36,980 - Inspection date 2022-02-07 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:36:36,980 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:36:49,140 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:36:49,143 - built Dictionary<1172 unique tokens: ['00', '0161', '03', '0300', '1']...> from 1 documents (total 2652 corpus positions)
+2024-11-18 09:36:49,143 - Dictionary lifecycle event {'msg': "built Dictionary<1172 unique tokens: ['00', '0161', '03', '0300', '1']...> from 1 documents (total 2652 corpus positions)", 'datetime': '2024-11-18T09:36:49.143590', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:36:49,144 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:36:49,144 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:36:49,145 - using serial LDA version on this node
+2024-11-18 09:36:49,145 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:36:49,145 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:36:49,149 - -8.051 per-word bound, 265.1 perplexity estimate based on a held-out corpus of 1 documents with 2652 words
+2024-11-18 09:36:49,149 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:36:49,150 - topic #0 (0.333): 0.016*"’" + 0.007*"Halton" + 0.007*"needs" + 0.007*"many" + 0.007*"quality" + 0.005*"need" + 0.005*"Leaders" + 0.005*"including" + 0.004*"experiences" + 0.004*"24"
+2024-11-18 09:36:49,150 - topic #1 (0.333): 0.017*"’" + 0.007*"needs" + 0.006*"including" + 0.006*"13" + 0.005*"Halton" + 0.005*"plans" + 0.005*"protection" + 0.005*"quality" + 0.005*"many" + 0.005*"need"
+2024-11-18 09:36:49,150 - topic #2 (0.333): 0.012*"’" + 0.007*"needs" + 0.006*"quality" + 0.005*"many" + 0.005*"including" + 0.005*"lack" + 0.005*"need" + 0.005*"recently" + 0.005*"protection" + 0.005*"Halton"
+2024-11-18 09:36:49,151 - topic diff=0.798039, rho=1.000000
+2024-11-18 09:36:49,151 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1172, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:36:49.151138', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:36:49,969 - Inspection date 2024-05-13 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:36:49,969 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:36:49,970 - Inspection date 2024-05-13 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:36:49,970 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:36:49,970 - Inspection date 2024-05-13 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:36:49,970 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:36:49,970 - Inspection date 2024-05-13 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:36:49,970 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:36:49,970 - Inspection date 2024-05-13 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:36:49,970 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:36:49,970 - Inspection date 2024-05-13 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:36:49,970 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:00,585 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:37:00,587 - built Dictionary<1092 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2524 corpus positions)
+2024-11-18 09:37:00,588 - Dictionary lifecycle event {'msg': "built Dictionary<1092 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2524 corpus positions)", 'datetime': '2024-11-18T09:37:00.588195', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:37:00,589 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:37:00,589 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:37:00,589 - using serial LDA version on this node
+2024-11-18 09:37:00,590 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:37:00,590 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:37:00,593 - -7.977 per-word bound, 251.9 perplexity estimate based on a held-out corpus of 1 documents with 2524 words
+2024-11-18 09:37:00,593 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:37:00,595 - topic #0 (0.333): 0.013*"’" + 0.009*"well" + 0.007*"new" + 0.007*"family" + 0.007*"plans" + 0.006*"progress" + 0.005*"practice" + 0.005*"10" + 0.005*"2024" + 0.005*"parents"
+2024-11-18 09:37:00,595 - topic #1 (0.333): 0.016*"’" + 0.008*"new" + 0.007*"family" + 0.007*"well" + 0.006*"quality" + 0.006*"receive" + 0.005*"plans" + 0.005*"progress" + 0.005*"Hampshire" + 0.005*"carers"
+2024-11-18 09:37:00,595 - topic #2 (0.333): 0.020*"’" + 0.007*"plans" + 0.007*"family" + 0.007*"progress" + 0.006*"quality" + 0.005*"well" + 0.005*"needs" + 0.005*"new" + 0.005*"achieve" + 0.005*"carers"
+2024-11-18 09:37:00,595 - topic diff=0.809876, rho=1.000000
+2024-11-18 09:37:00,595 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1092, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:37:00.595705', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:37:01,483 - Inspection date 2024-06-10 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:37:01,483 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:01,483 - Inspection date 2024-06-10 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:37:01,483 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:01,483 - Inspection date 2024-06-10 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:37:01,484 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:01,484 - Inspection date 2024-06-10 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:37:01,484 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:01,484 - Inspection date 2024-06-10 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:37:01,484 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:01,484 - Inspection date 2024-06-10 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:37:01,484 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:13,362 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:37:13,364 - built Dictionary<1171 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2584 corpus positions)
+2024-11-18 09:37:13,364 - Dictionary lifecycle event {'msg': "built Dictionary<1171 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2584 corpus positions)", 'datetime': '2024-11-18T09:37:13.364609', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:37:13,365 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:37:13,365 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:37:13,366 - using serial LDA version on this node
+2024-11-18 09:37:13,366 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:37:13,366 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:37:13,370 - -8.073 per-word bound, 269.2 perplexity estimate based on a held-out corpus of 1 documents with 2584 words
+2024-11-18 09:37:13,370 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:37:13,371 - topic #0 (0.333): 0.019*"’" + 0.008*"needs" + 0.007*"March" + 0.006*"well" + 0.006*"Hartlepool" + 0.006*"leaders" + 0.005*"effective" + 0.005*"plans" + 0.004*"supported" + 0.004*"practice"
+2024-11-18 09:37:13,371 - topic #1 (0.333): 0.017*"’" + 0.008*"Hartlepool" + 0.006*"March" + 0.006*"well" + 0.005*"leaders" + 0.004*"18" + 0.004*"needs" + 0.004*"clear" + 0.004*"ensure" + 0.004*"strong"
+2024-11-18 09:37:13,372 - topic #2 (0.333): 0.022*"’" + 0.008*"March" + 0.008*"needs" + 0.007*"Hartlepool" + 0.005*"leaders" + 0.005*"need" + 0.005*"well" + 0.005*"strong" + 0.005*"18" + 0.005*"clear"
+2024-11-18 09:37:13,372 - topic diff=0.794238, rho=1.000000
+2024-11-18 09:37:13,372 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1171, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:37:13.372293', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:37:14,321 - Inspection date 2024-03-18 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:37:14,322 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:14,322 - Inspection date 2024-03-18 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:37:14,322 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:14,322 - Inspection date 2024-03-18 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:37:14,322 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:14,323 - Inspection date 2024-03-18 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:37:14,323 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:14,323 - Inspection date 2024-03-18 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:37:14,323 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:14,323 - Inspection date 2024-03-18 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:37:14,323 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:25,281 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:37:25,284 - built Dictionary<1142 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2531 corpus positions)
+2024-11-18 09:37:25,284 - Dictionary lifecycle event {'msg': "built Dictionary<1142 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2531 corpus positions)", 'datetime': '2024-11-18T09:37:25.284317', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:37:25,285 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:37:25,285 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:37:25,285 - using serial LDA version on this node
+2024-11-18 09:37:25,286 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:37:25,286 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:37:25,289 - -8.044 per-word bound, 264.0 perplexity estimate based on a held-out corpus of 1 documents with 2531 words
+2024-11-18 09:37:25,290 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:37:25,291 - topic #0 (0.333): 0.018*"’" + 0.006*"Herefordshire" + 0.005*"lack" + 0.005*"needs" + 0.005*"quality" + 0.004*"practice" + 0.004*"carers" + 0.004*"18" + 0.004*"29" + 0.004*"impact"
+2024-11-18 09:37:25,291 - topic #1 (0.333): 0.017*"’" + 0.006*"practice" + 0.005*"impact" + 0.005*"many" + 0.005*"Herefordshire" + 0.005*"progress" + 0.005*"lack" + 0.005*"needs" + 0.005*"plans" + 0.004*"2022"
+2024-11-18 09:37:25,291 - topic #2 (0.333): 0.016*"’" + 0.006*"practice" + 0.005*"Herefordshire" + 0.005*"impact" + 0.004*"lack" + 0.004*"July" + 0.004*"needs" + 0.004*"plans" + 0.004*"many" + 0.004*"management"
+2024-11-18 09:37:25,291 - topic diff=0.790623, rho=1.000000
+2024-11-18 09:37:25,291 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1142, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:37:25.291868', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:37:26,085 - Inspection date 2022-07-18 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:37:26,086 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:26,086 - Inspection date 2022-07-18 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:37:26,086 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:26,086 - Inspection date 2022-07-18 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:37:26,086 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:26,086 - Inspection date 2022-07-18 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:37:26,086 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:26,087 - Inspection date 2022-07-18 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:37:26,087 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:26,087 - Inspection date 2022-07-18 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:37:26,087 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:37,075 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:37:37,078 - built Dictionary<1192 unique tokens: ['0161', '0300', '1', '10', '100']...> from 1 documents (total 2456 corpus positions)
+2024-11-18 09:37:37,078 - Dictionary lifecycle event {'msg': "built Dictionary<1192 unique tokens: ['0161', '0300', '1', '10', '100']...> from 1 documents (total 2456 corpus positions)", 'datetime': '2024-11-18T09:37:37.078321', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:37:37,079 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:37:37,079 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:37:37,079 - using serial LDA version on this node
+2024-11-18 09:37:37,080 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:37:37,080 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:37:37,084 - -8.131 per-word bound, 280.3 perplexity estimate based on a held-out corpus of 1 documents with 2456 words
+2024-11-18 09:37:37,084 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:37:37,085 - topic #0 (0.333): 0.028*"’" + 0.007*"Hertfordshire" + 0.007*"needs" + 0.006*"receive" + 0.006*"well" + 0.005*"23" + 0.005*"plans" + 0.005*"positive" + 0.004*"need" + 0.004*"2023"
+2024-11-18 09:37:37,085 - topic #1 (0.333): 0.017*"’" + 0.007*"well" + 0.005*"Hertfordshire" + 0.005*"needs" + 0.004*"‘" + 0.004*"plans" + 0.004*"risk" + 0.004*"receive" + 0.003*"Leaders" + 0.003*"education"
+2024-11-18 09:37:37,085 - topic #2 (0.333): 0.019*"’" + 0.006*"Hertfordshire" + 0.006*"well" + 0.005*"needs" + 0.005*"plans" + 0.004*"27" + 0.004*"January" + 0.004*"receive" + 0.004*"leaders" + 0.004*"family"
+2024-11-18 09:37:37,085 - topic diff=0.804188, rho=1.000000
+2024-11-18 09:37:37,086 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1192, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:37:37.085985', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:37:38,712 - Inspection date 2023-01-23 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:37:38,713 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:38,713 - Inspection date 2023-01-23 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:37:38,713 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:38,713 - Inspection date 2023-01-23 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:37:38,713 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:38,714 - Inspection date 2023-01-23 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:37:38,714 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:38,714 - Inspection date 2023-01-23 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:37:38,714 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:38,714 - Inspection date 2023-01-23 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:37:38,714 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:48,708 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:37:48,710 - built Dictionary<976 unique tokens: ['0161', '0300', '1', '10', '10-year']...> from 1 documents (total 1934 corpus positions)
+2024-11-18 09:37:48,710 - Dictionary lifecycle event {'msg': "built Dictionary<976 unique tokens: ['0161', '0300', '1', '10', '10-year']...> from 1 documents (total 1934 corpus positions)", 'datetime': '2024-11-18T09:37:48.710261', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:37:48,711 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:37:48,711 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:37:48,711 - using serial LDA version on this node
+2024-11-18 09:37:48,711 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:37:48,711 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:37:48,715 - -7.953 per-word bound, 247.8 perplexity estimate based on a held-out corpus of 1 documents with 1934 words
+2024-11-18 09:37:48,715 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:37:48,716 - topic #0 (0.333): 0.020*"’" + 0.009*"leaders" + 0.006*"well" + 0.006*"Isle" + 0.005*"Wight" + 0.005*"Senior" + 0.005*"needs" + 0.005*"improve" + 0.005*"plans" + 0.005*"3"
+2024-11-18 09:37:48,716 - topic #1 (0.333): 0.018*"’" + 0.007*"leaders" + 0.006*"protection" + 0.006*"needs" + 0.005*"practice" + 0.005*"progress" + 0.005*"supported" + 0.005*"well" + 0.005*"October" + 0.005*"PAs"
+2024-11-18 09:37:48,716 - topic #2 (0.333): 0.015*"’" + 0.008*"leaders" + 0.006*"needs" + 0.005*"plans" + 0.005*"well" + 0.005*"good" + 0.005*"supported" + 0.005*"progress" + 0.005*"Isle" + 0.005*"November"
+2024-11-18 09:37:48,716 - topic diff=0.766294, rho=1.000000
+2024-11-18 09:37:48,716 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=976, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:37:48.716918', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:37:49,603 - Inspection date 2023-10-30 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:37:49,603 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:49,603 - Inspection date 2023-10-30 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:37:49,603 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:49,603 - Inspection date 2023-10-30 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:37:49,604 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:49,604 - Inspection date 2023-10-30 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:37:49,604 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:49,604 - Inspection date 2023-10-30 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:37:49,604 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:37:49,604 - Inspection date 2023-10-30 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:37:49,604 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:01,260 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:38:01,263 - built Dictionary<1298 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2888 corpus positions)
+2024-11-18 09:38:01,263 - Dictionary lifecycle event {'msg': "built Dictionary<1298 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2888 corpus positions)", 'datetime': '2024-11-18T09:38:01.263289', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:38:01,264 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:38:01,264 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:38:01,264 - using serial LDA version on this node
+2024-11-18 09:38:01,265 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:38:01,265 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:38:01,269 - -8.168 per-word bound, 287.6 perplexity estimate based on a held-out corpus of 1 documents with 2888 words
+2024-11-18 09:38:01,269 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:38:01,270 - topic #0 (0.333): 0.022*"’" + 0.010*"Kent" + 0.008*"needs" + 0.007*"well" + 0.006*"Council" + 0.006*"supported" + 0.005*"progress" + 0.005*"leaders" + 0.004*"County" + 0.004*"2022"
+2024-11-18 09:38:01,271 - topic #1 (0.333): 0.016*"’" + 0.008*"Kent" + 0.006*"needs" + 0.006*"Council" + 0.005*"supported" + 0.005*"County" + 0.004*"leaders" + 0.004*"progress" + 0.004*"well" + 0.004*"practice"
+2024-11-18 09:38:01,271 - topic #2 (0.333): 0.015*"’" + 0.011*"Kent" + 0.007*"needs" + 0.007*"well" + 0.006*"Council" + 0.006*"County" + 0.005*"supported" + 0.005*"practice" + 0.005*"progress" + 0.004*"ensure"
+2024-11-18 09:38:01,271 - topic diff=0.799365, rho=1.000000
+2024-11-18 09:38:01,271 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1298, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:38:01.271436', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:38:02,113 - Inspection date 2022-05-09 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:38:02,113 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:02,113 - Inspection date 2022-05-09 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:38:02,114 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:02,114 - Inspection date 2022-05-09 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:38:02,114 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:02,114 - Inspection date 2022-05-09 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:38:02,114 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:02,114 - Inspection date 2022-05-09 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:38:02,114 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:02,115 - Inspection date 2022-05-09 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:38:02,115 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:11,056 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:38:11,058 - built Dictionary<976 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1970 corpus positions)
+2024-11-18 09:38:11,058 - Dictionary lifecycle event {'msg': "built Dictionary<976 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1970 corpus positions)", 'datetime': '2024-11-18T09:38:11.058385', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:38:11,059 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:38:11,059 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:38:11,059 - using serial LDA version on this node
+2024-11-18 09:38:11,059 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:38:11,060 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:38:11,063 - -7.949 per-word bound, 247.2 perplexity estimate based on a held-out corpus of 1 documents with 1970 words
+2024-11-18 09:38:11,063 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:38:11,064 - topic #0 (0.333): 0.017*"’" + 0.006*"planning" + 0.006*"well" + 0.006*"protection" + 0.006*"number" + 0.006*"management" + 0.006*"risks" + 0.005*"practice" + 0.005*"need" + 0.005*"impact"
+2024-11-18 09:38:11,064 - topic #1 (0.333): 0.018*"’" + 0.008*"number" + 0.006*"Hull" + 0.006*"teams" + 0.006*"planning" + 0.006*"small" + 0.005*"14" + 0.005*"well" + 0.005*"practice" + 0.005*"25"
+2024-11-18 09:38:11,064 - topic #2 (0.333): 0.012*"’" + 0.007*"planning" + 0.007*"practice" + 0.006*"need" + 0.006*"protection" + 0.006*"well" + 0.006*"risks" + 0.006*"number" + 0.005*"Hull" + 0.005*"oversight"
+2024-11-18 09:38:11,065 - topic diff=0.752865, rho=1.000000
+2024-11-18 09:38:11,065 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=976, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:38:11.065144', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:38:11,885 - Inspection date 2022-11-14 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:38:11,885 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:11,885 - Inspection date 2022-11-14 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:38:11,885 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:11,885 - Inspection date 2022-11-14 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:38:11,886 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:11,886 - Inspection date 2022-11-14 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:38:11,886 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:11,886 - Inspection date 2022-11-14 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:38:11,886 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:11,886 - Inspection date 2022-11-14 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:38:11,886 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:22,205 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:38:22,207 - built Dictionary<963 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2139 corpus positions)
+2024-11-18 09:38:22,207 - Dictionary lifecycle event {'msg': "built Dictionary<963 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2139 corpus positions)", 'datetime': '2024-11-18T09:38:22.207752', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:38:22,208 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:38:22,208 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:38:22,209 - using serial LDA version on this node
+2024-11-18 09:38:22,209 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:38:22,209 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:38:22,212 - -7.874 per-word bound, 234.6 perplexity estimate based on a held-out corpus of 1 documents with 2139 words
+2024-11-18 09:38:22,212 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:38:22,214 - topic #0 (0.333): 0.019*"’" + 0.008*"plans" + 0.007*"needs" + 0.007*"Kirklees" + 0.006*"well" + 0.005*"protection" + 0.005*"need" + 0.005*"experiences" + 0.005*"family" + 0.005*"progress"
+2024-11-18 09:38:22,214 - topic #1 (0.333): 0.023*"’" + 0.007*"Kirklees" + 0.007*"plans" + 0.007*"effective" + 0.007*"needs" + 0.007*"impact" + 0.006*"well" + 0.005*"leaders" + 0.005*"progress" + 0.005*"Leaders"
+2024-11-18 09:38:22,214 - topic #2 (0.333): 0.019*"’" + 0.009*"effective" + 0.008*"Kirklees" + 0.008*"needs" + 0.006*"plans" + 0.006*"need" + 0.006*"quality" + 0.006*"ensure" + 0.005*"well" + 0.005*"impact"
+2024-11-18 09:38:22,214 - topic diff=0.792306, rho=1.000000
+2024-11-18 09:38:22,214 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=963, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:38:22.214679', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:38:23,150 - Inspection date 2024-07-08 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:38:23,150 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:23,151 - Inspection date 2024-07-08 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:38:23,151 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:23,151 - Inspection date 2024-07-08 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:38:23,151 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:23,151 - Inspection date 2024-07-08 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:38:23,151 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:23,151 - Inspection date 2024-07-08 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:38:23,151 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:23,151 - Inspection date 2024-07-08 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:38:23,152 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:31,492 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:38:31,494 - built Dictionary<886 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1837 corpus positions)
+2024-11-18 09:38:31,494 - Dictionary lifecycle event {'msg': "built Dictionary<886 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1837 corpus positions)", 'datetime': '2024-11-18T09:38:31.494697', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:38:31,495 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:38:31,495 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:38:31,495 - using serial LDA version on this node
+2024-11-18 09:38:31,496 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:38:31,496 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:38:31,499 - -7.827 per-word bound, 227.1 perplexity estimate based on a held-out corpus of 1 documents with 1837 words
+2024-11-18 09:38:31,499 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:38:31,500 - topic #0 (0.333): 0.013*"’" + 0.009*"progress" + 0.009*"quality" + 0.008*"needs" + 0.007*"plans" + 0.006*"22" + 0.005*"impact" + 0.005*"2021" + 0.005*"need" + 0.005*"Knowsley"
+2024-11-18 09:38:31,501 - topic #1 (0.333): 0.015*"’" + 0.008*"needs" + 0.007*"Knowsley" + 0.007*"plans" + 0.007*"2021" + 0.006*"quality" + 0.006*"progress" + 0.006*"experiences" + 0.005*"domestic" + 0.005*"risk"
+2024-11-18 09:38:31,501 - topic #2 (0.333): 0.014*"’" + 0.010*"progress" + 0.007*"plans" + 0.006*"need" + 0.006*"Knowsley" + 0.006*"good" + 0.005*"quality" + 0.005*"2021" + 0.005*"needs" + 0.004*"11"
+2024-11-18 09:38:31,501 - topic diff=0.743270, rho=1.000000
+2024-11-18 09:38:31,501 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=886, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:38:31.501523', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:38:32,325 - Inspection date 2021-10-11 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:38:32,325 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:32,326 - Inspection date 2021-10-11 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:38:32,326 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:32,326 - Inspection date 2021-10-11 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:38:32,326 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:32,326 - Inspection date 2021-10-11 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:38:32,326 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:32,326 - Inspection date 2021-10-11 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:38:32,326 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:32,326 - Inspection date 2021-10-11 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:38:32,327 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:41,965 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:38:41,968 - built Dictionary<1048 unique tokens: ['0', '0161', '0300', '1', '10']...> from 1 documents (total 2263 corpus positions)
+2024-11-18 09:38:41,968 - Dictionary lifecycle event {'msg': "built Dictionary<1048 unique tokens: ['0', '0161', '0300', '1', '10']...> from 1 documents (total 2263 corpus positions)", 'datetime': '2024-11-18T09:38:41.968636', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:38:41,969 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:38:41,969 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:38:41,969 - using serial LDA version on this node
+2024-11-18 09:38:41,970 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:38:41,970 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:38:41,973 - -7.975 per-word bound, 251.5 perplexity estimate based on a held-out corpus of 1 documents with 2263 words
+2024-11-18 09:38:41,973 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:38:41,975 - topic #0 (0.333): 0.013*"’" + 0.009*"well" + 0.006*"need" + 0.006*"Lancashire" + 0.005*"parents" + 0.005*"28" + 0.005*"plans" + 0.005*"needs" + 0.004*"homes" + 0.004*"practice"
+2024-11-18 09:38:41,975 - topic #1 (0.333): 0.018*"’" + 0.008*"well" + 0.008*"needs" + 0.007*"need" + 0.006*"supported" + 0.005*"practice" + 0.005*"positive" + 0.005*"Lancashire" + 0.005*"information" + 0.005*"9"
+2024-11-18 09:38:41,975 - topic #2 (0.333): 0.016*"’" + 0.009*"well" + 0.009*"needs" + 0.008*"need" + 0.007*"Lancashire" + 0.006*"plans" + 0.006*"progress" + 0.005*"live" + 0.005*"supported" + 0.005*"health"
+2024-11-18 09:38:41,975 - topic diff=0.781242, rho=1.000000
+2024-11-18 09:38:41,975 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1048, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:38:41.975619', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:38:42,873 - Inspection date 2022-11-28 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:38:42,874 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:42,874 - Inspection date 2022-11-28 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:38:42,874 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:42,874 - Inspection date 2022-11-28 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:38:42,874 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:42,875 - Inspection date 2022-11-28 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:38:42,875 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:42,875 - Inspection date 2022-11-28 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:38:42,875 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:42,875 - Inspection date 2022-11-28 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:38:42,875 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:53,283 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:38:53,285 - built Dictionary<1071 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2261 corpus positions)
+2024-11-18 09:38:53,286 - Dictionary lifecycle event {'msg': "built Dictionary<1071 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2261 corpus positions)", 'datetime': '2024-11-18T09:38:53.286094', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:38:53,287 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:38:53,287 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:38:53,287 - using serial LDA version on this node
+2024-11-18 09:38:53,287 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:38:53,287 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:38:53,291 - -8.010 per-word bound, 257.7 perplexity estimate based on a held-out corpus of 1 documents with 2261 words
+2024-11-18 09:38:53,291 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:38:53,292 - topic #0 (0.333): 0.016*"’" + 0.007*"needs" + 0.007*"Leeds" + 0.006*"well" + 0.005*"risk" + 0.005*"4" + 0.004*"protection" + 0.004*"2022" + 0.004*"ensure" + 0.004*"21"
+2024-11-18 09:38:53,292 - topic #1 (0.333): 0.014*"’" + 0.008*"Leeds" + 0.006*"needs" + 0.005*"practice" + 0.005*"plans" + 0.004*"well" + 0.004*"risk" + 0.004*"4" + 0.004*"ensure" + 0.004*"making"
+2024-11-18 09:38:53,293 - topic #2 (0.333): 0.017*"’" + 0.007*"Leeds" + 0.007*"needs" + 0.006*"well" + 0.006*"risk" + 0.005*"supported" + 0.005*"protection" + 0.005*"practice" + 0.004*"ensure" + 0.004*"plans"
+2024-11-18 09:38:53,293 - topic diff=0.775204, rho=1.000000
+2024-11-18 09:38:53,293 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1071, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:38:53.293227', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:38:54,118 - Inspection date 2022-02-21 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:38:54,118 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:54,118 - Inspection date 2022-02-21 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:38:54,118 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:54,118 - Inspection date 2022-02-21 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:38:54,119 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:54,119 - Inspection date 2022-02-21 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:38:54,119 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:54,119 - Inspection date 2022-02-21 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:38:54,119 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:38:54,119 - Inspection date 2022-02-21 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:38:54,119 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:02,738 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:39:02,739 - built Dictionary<932 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1950 corpus positions)
+2024-11-18 09:39:02,740 - Dictionary lifecycle event {'msg': "built Dictionary<932 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1950 corpus positions)", 'datetime': '2024-11-18T09:39:02.740093', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:39:02,741 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:39:02,741 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:39:02,741 - using serial LDA version on this node
+2024-11-18 09:39:02,741 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:39:02,741 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:39:02,744 - -7.879 per-word bound, 235.4 perplexity estimate based on a held-out corpus of 1 documents with 1950 words
+2024-11-18 09:39:02,744 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:39:02,746 - topic #0 (0.333): 0.019*"’" + 0.008*"well" + 0.007*"Leicester" + 0.006*"needs" + 0.006*"good" + 0.006*"2021" + 0.006*"1" + 0.006*"ensure" + 0.005*"progress" + 0.005*"including"
+2024-11-18 09:39:02,746 - topic #1 (0.333): 0.022*"’" + 0.010*"2021" + 0.009*"well" + 0.007*"Leicester" + 0.007*"good" + 0.006*"number" + 0.006*"ensure" + 0.006*"needs" + 0.005*"20" + 0.005*"October"
+2024-11-18 09:39:02,746 - topic #2 (0.333): 0.017*"’" + 0.008*"2021" + 0.008*"Leicester" + 0.008*"well" + 0.008*"needs" + 0.005*"ensure" + 0.005*"number" + 0.005*"20" + 0.005*"including" + 0.004*"Council"
+2024-11-18 09:39:02,746 - topic diff=0.780746, rho=1.000000
+2024-11-18 09:39:02,746 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=932, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:39:02.746670', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:39:03,763 - Inspection date 2021-09-20 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:39:03,763 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:03,764 - Inspection date 2021-09-20 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:39:03,764 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:03,764 - Inspection date 2021-09-20 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:39:03,764 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:03,764 - Inspection date 2021-09-20 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:39:03,764 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:03,764 - Inspection date 2021-09-20 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:39:03,764 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:03,765 - Inspection date 2021-09-20 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:39:03,765 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:16,701 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:39:16,704 - built Dictionary<1223 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2745 corpus positions)
+2024-11-18 09:39:16,704 - Dictionary lifecycle event {'msg': "built Dictionary<1223 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2745 corpus positions)", 'datetime': '2024-11-18T09:39:16.704456', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:39:16,705 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:39:16,705 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:39:16,705 - using serial LDA version on this node
+2024-11-18 09:39:16,706 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:39:16,706 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:39:16,710 - -8.108 per-word bound, 275.8 perplexity estimate based on a held-out corpus of 1 documents with 2745 words
+2024-11-18 09:39:16,710 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:39:16,711 - topic #0 (0.333): 0.011*"’" + 0.011*"well" + 0.006*"family" + 0.006*"Leicestershire" + 0.005*"need" + 0.005*"needs" + 0.005*"risk" + 0.005*"good" + 0.005*"ensure" + 0.005*"experiences"
+2024-11-18 09:39:16,711 - topic #1 (0.333): 0.015*"’" + 0.007*"well" + 0.006*"experiences" + 0.006*"family" + 0.005*"Leicestershire" + 0.005*"need" + 0.005*"understand" + 0.005*"risk" + 0.005*"progress" + 0.004*"PAs"
+2024-11-18 09:39:16,712 - topic #2 (0.333): 0.025*"’" + 0.009*"well" + 0.007*"Leicestershire" + 0.007*"needs" + 0.006*"plans" + 0.005*"understand" + 0.005*"progress" + 0.005*"PAs" + 0.005*"experiences" + 0.005*"family"
+2024-11-18 09:39:16,712 - topic diff=0.811958, rho=1.000000
+2024-11-18 09:39:16,712 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1223, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:39:16.712276', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:39:17,670 - Inspection date 2024-04-22 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:39:17,670 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:17,670 - Inspection date 2024-04-22 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:39:17,670 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:17,671 - Inspection date 2024-04-22 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:39:17,671 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:17,671 - Inspection date 2024-04-22 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:39:17,671 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:17,671 - Inspection date 2024-04-22 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:39:17,671 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:17,671 - Inspection date 2024-04-22 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:39:17,671 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:30,717 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:39:30,720 - built Dictionary<1323 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2927 corpus positions)
+2024-11-18 09:39:30,720 - Dictionary lifecycle event {'msg': "built Dictionary<1323 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2927 corpus positions)", 'datetime': '2024-11-18T09:39:30.720595', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:39:30,721 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:39:30,721 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:39:30,722 - using serial LDA version on this node
+2024-11-18 09:39:30,722 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:39:30,722 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:39:30,726 - -8.190 per-word bound, 292.1 perplexity estimate based on a held-out corpus of 1 documents with 2927 words
+2024-11-18 09:39:30,726 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:39:30,728 - topic #0 (0.333): 0.024*"’" + 0.007*"Lincolnshire" + 0.006*"needs" + 0.006*"progress" + 0.005*"well" + 0.005*"family" + 0.004*"28" + 0.004*"need" + 0.004*"plans" + 0.004*"24"
+2024-11-18 09:39:30,728 - topic #1 (0.333): 0.023*"’" + 0.008*"needs" + 0.007*"Lincolnshire" + 0.006*"well" + 0.005*"plans" + 0.004*"24" + 0.004*"April" + 0.004*"number" + 0.004*"28" + 0.004*"effective"
+2024-11-18 09:39:30,728 - topic #2 (0.333): 0.016*"’" + 0.008*"Lincolnshire" + 0.006*"well" + 0.005*"plans" + 0.005*"needs" + 0.005*"education" + 0.005*"family" + 0.005*"progress" + 0.003*"need" + 0.003*"24"
+2024-11-18 09:39:30,728 - topic diff=0.789247, rho=1.000000
+2024-11-18 09:39:30,728 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1323, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:39:30.728938', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:39:31,555 - Inspection date 2023-04-24 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:39:31,555 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:31,556 - Inspection date 2023-04-24 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:39:31,556 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:31,556 - Inspection date 2023-04-24 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:39:31,556 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:31,556 - Inspection date 2023-04-24 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:39:31,556 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:31,556 - Inspection date 2023-04-24 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:39:31,557 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:31,557 - Inspection date 2023-04-24 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:39:31,557 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:43,415 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:39:43,417 - built Dictionary<1134 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2720 corpus positions)
+2024-11-18 09:39:43,418 - Dictionary lifecycle event {'msg': "built Dictionary<1134 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2720 corpus positions)", 'datetime': '2024-11-18T09:39:43.418045', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:39:43,419 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:39:43,419 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:39:43,419 - using serial LDA version on this node
+2024-11-18 09:39:43,419 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:39:43,419 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:39:43,423 - -8.000 per-word bound, 255.9 perplexity estimate based on a held-out corpus of 1 documents with 2720 words
+2024-11-18 09:39:43,423 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:39:43,424 - topic #0 (0.333): 0.021*"’" + 0.007*"needs" + 0.007*"always" + 0.006*"practice" + 0.006*"Liverpool" + 0.005*"need" + 0.005*"quality" + 0.005*"24" + 0.005*"protection" + 0.004*"13"
+2024-11-18 09:39:43,425 - topic #1 (0.333): 0.018*"’" + 0.007*"practice" + 0.007*"need" + 0.007*"needs" + 0.006*"quality" + 0.006*"Liverpool" + 0.005*"always" + 0.005*"protection" + 0.004*"health" + 0.004*"2023"
+2024-11-18 09:39:43,425 - topic #2 (0.333): 0.018*"’" + 0.007*"needs" + 0.007*"need" + 0.006*"always" + 0.006*"practice" + 0.006*"quality" + 0.005*"Liverpool" + 0.005*"protection" + 0.005*"PAs" + 0.005*"13"
+2024-11-18 09:39:43,425 - topic diff=0.839497, rho=1.000000
+2024-11-18 09:39:43,425 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1134, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:39:43.425551', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:39:44,344 - Inspection date 2023-03-13 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:39:44,345 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:44,345 - Inspection date 2023-03-13 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:39:44,345 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:44,345 - Inspection date 2023-03-13 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:39:44,345 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:44,345 - Inspection date 2023-03-13 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:39:44,345 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:44,345 - Inspection date 2023-03-13 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:39:44,346 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:44,346 - Inspection date 2023-03-13 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:39:44,346 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:55,668 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:39:55,671 - built Dictionary<1193 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2610 corpus positions)
+2024-11-18 09:39:55,671 - Dictionary lifecycle event {'msg': "built Dictionary<1193 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2610 corpus positions)", 'datetime': '2024-11-18T09:39:55.671450', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:39:55,672 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:39:55,672 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:39:55,672 - using serial LDA version on this node
+2024-11-18 09:39:55,673 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:39:55,673 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:39:55,677 - -8.094 per-word bound, 273.3 perplexity estimate based on a held-out corpus of 1 documents with 2610 words
+2024-11-18 09:39:55,677 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:39:55,678 - topic #0 (0.333): 0.025*"’" + 0.007*"needs" + 0.006*"good" + 0.005*"carers" + 0.005*"plans" + 0.004*"e" + 0.004*"practice" + 0.004*"information" + 0.004*"London" + 0.004*"well"
+2024-11-18 09:39:55,678 - topic #1 (0.333): 0.021*"’" + 0.008*"needs" + 0.006*"well" + 0.005*"plans" + 0.005*"progress" + 0.005*"carers" + 0.005*"information" + 0.005*"Dagenham" + 0.004*"good" + 0.004*"London"
+2024-11-18 09:39:55,679 - topic #2 (0.333): 0.021*"’" + 0.009*"needs" + 0.007*"plans" + 0.006*"good" + 0.006*"progress" + 0.006*"practice" + 0.005*"well" + 0.005*"carers" + 0.005*"planning" + 0.004*"timely"
+2024-11-18 09:39:55,679 - topic diff=0.796705, rho=1.000000
+2024-11-18 09:39:55,679 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1193, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:39:55.679268', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:39:56,528 - Inspection date 2023-07-10 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:39:56,528 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:56,528 - Inspection date 2023-07-10 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:39:56,528 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:56,528 - Inspection date 2023-07-10 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:39:56,529 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:56,529 - Inspection date 2023-07-10 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:39:56,529 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:56,529 - Inspection date 2023-07-10 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:39:56,529 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:39:56,529 - Inspection date 2023-07-10 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:39:56,529 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:07,346 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:40:07,349 - built Dictionary<1132 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2445 corpus positions)
+2024-11-18 09:40:07,349 - Dictionary lifecycle event {'msg': "built Dictionary<1132 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2445 corpus positions)", 'datetime': '2024-11-18T09:40:07.349345', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:40:07,350 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:40:07,350 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:40:07,350 - using serial LDA version on this node
+2024-11-18 09:40:07,351 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:40:07,351 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:40:07,354 - -8.053 per-word bound, 265.6 perplexity estimate based on a held-out corpus of 1 documents with 2445 words
+2024-11-18 09:40:07,354 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:40:07,356 - topic #0 (0.333): 0.019*"’" + 0.009*"needs" + 0.007*"plans" + 0.006*"Barnet" + 0.006*"well" + 0.005*"effective" + 0.004*"understand" + 0.004*"10" + 0.004*"risk" + 0.004*"experiences"
+2024-11-18 09:40:07,356 - topic #1 (0.333): 0.023*"’" + 0.010*"well" + 0.008*"needs" + 0.008*"Barnet" + 0.007*"plans" + 0.005*"experiences" + 0.005*"information" + 0.005*"progress" + 0.005*"14" + 0.004*"parents"
+2024-11-18 09:40:07,356 - topic #2 (0.333): 0.020*"’" + 0.008*"needs" + 0.008*"plans" + 0.006*"Barnet" + 0.005*"well" + 0.005*"risk" + 0.004*"2024" + 0.004*"10" + 0.004*"information" + 0.004*"experiences"
+2024-11-18 09:40:07,356 - topic diff=0.785945, rho=1.000000
+2024-11-18 09:40:07,356 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1132, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:40:07.356861', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:40:08,293 - Inspection date 2024-06-10 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:40:08,293 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:08,294 - Inspection date 2024-06-10 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:40:08,294 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:08,294 - Inspection date 2024-06-10 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:40:08,294 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:08,294 - Inspection date 2024-06-10 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:40:08,294 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:08,294 - Inspection date 2024-06-10 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:40:08,295 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:08,295 - Inspection date 2024-06-10 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:40:08,295 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:19,645 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:40:19,647 - built Dictionary<1190 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2563 corpus positions)
+2024-11-18 09:40:19,647 - Dictionary lifecycle event {'msg': "built Dictionary<1190 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2563 corpus positions)", 'datetime': '2024-11-18T09:40:19.647826', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:40:19,648 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:40:19,649 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:40:19,649 - using serial LDA version on this node
+2024-11-18 09:40:19,649 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:40:19,649 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:40:19,654 - -8.101 per-word bound, 274.6 perplexity estimate based on a held-out corpus of 1 documents with 2563 words
+2024-11-18 09:40:19,654 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:40:19,655 - topic #0 (0.333): 0.018*"’" + 0.007*"needs" + 0.006*"Bexley" + 0.006*"well" + 0.005*"effective" + 0.005*"need" + 0.005*"10" + 0.005*"plans" + 0.004*"6" + 0.004*"practice"
+2024-11-18 09:40:19,655 - topic #1 (0.333): 0.022*"’" + 0.007*"well" + 0.006*"needs" + 0.006*"need" + 0.006*"plans" + 0.005*"effective" + 0.005*"Bexley" + 0.005*"including" + 0.005*"clear" + 0.004*"6"
+2024-11-18 09:40:19,655 - topic #2 (0.333): 0.017*"’" + 0.006*"well" + 0.006*"effective" + 0.005*"make" + 0.005*"plans" + 0.005*"Bexley" + 0.005*"needs" + 0.004*"practice" + 0.004*"need" + 0.004*"including"
+2024-11-18 09:40:19,655 - topic diff=0.785278, rho=1.000000
+2024-11-18 09:40:19,656 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1190, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:40:19.656016', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:40:20,674 - Inspection date 2023-02-06 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:40:20,674 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:20,674 - Inspection date 2023-02-06 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:40:20,674 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:20,674 - Inspection date 2023-02-06 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:40:20,674 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:20,675 - Inspection date 2023-02-06 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:40:20,675 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:20,675 - Inspection date 2023-02-06 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:40:20,675 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:20,675 - Inspection date 2023-02-06 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:40:20,675 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:31,575 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:40:31,577 - built Dictionary<1038 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2371 corpus positions)
+2024-11-18 09:40:31,577 - Dictionary lifecycle event {'msg': "built Dictionary<1038 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2371 corpus positions)", 'datetime': '2024-11-18T09:40:31.577370', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:40:31,578 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:40:31,578 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:40:31,578 - using serial LDA version on this node
+2024-11-18 09:40:31,579 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:40:31,579 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:40:31,582 - -7.933 per-word bound, 244.4 perplexity estimate based on a held-out corpus of 1 documents with 2371 words
+2024-11-18 09:40:31,582 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:40:31,583 - topic #0 (0.333): 0.021*"’" + 0.009*"well" + 0.006*"plans" + 0.006*"leaders" + 0.006*"good" + 0.006*"Brent" + 0.006*"quality" + 0.006*"timely" + 0.005*"needs" + 0.005*"number"
+2024-11-18 09:40:31,584 - topic #1 (0.333): 0.017*"’" + 0.008*"leaders" + 0.007*"well" + 0.005*"plans" + 0.005*"number" + 0.005*"progress" + 0.005*"quality" + 0.005*"information" + 0.005*"senior" + 0.005*"good"
+2024-11-18 09:40:31,584 - topic #2 (0.333): 0.013*"’" + 0.009*"well" + 0.009*"progress" + 0.007*"plans" + 0.007*"leaders" + 0.006*"senior" + 0.006*"good" + 0.005*"Brent" + 0.005*"number" + 0.005*"practice"
+2024-11-18 09:40:31,584 - topic diff=0.826418, rho=1.000000
+2024-11-18 09:40:31,584 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1038, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:40:31.584519', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:40:32,461 - Inspection date 2023-02-20 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:40:32,461 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:32,462 - Inspection date 2023-02-20 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:40:32,462 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:32,462 - Inspection date 2023-02-20 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:40:32,462 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:32,462 - Inspection date 2023-02-20 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:40:32,462 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:32,462 - Inspection date 2023-02-20 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:40:32,462 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:32,463 - Inspection date 2023-02-20 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:40:32,463 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:44,791 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:40:44,794 - built Dictionary<1266 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2640 corpus positions)
+2024-11-18 09:40:44,794 - Dictionary lifecycle event {'msg': "built Dictionary<1266 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2640 corpus positions)", 'datetime': '2024-11-18T09:40:44.794347', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:40:44,795 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:40:44,795 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:40:44,795 - using serial LDA version on this node
+2024-11-18 09:40:44,796 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:40:44,796 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:40:44,800 - -8.185 per-word bound, 291.1 perplexity estimate based on a held-out corpus of 1 documents with 2640 words
+2024-11-18 09:40:44,800 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:40:44,801 - topic #0 (0.333): 0.024*"’" + 0.010*"Bromley" + 0.007*"needs" + 0.006*"well" + 0.005*"plans" + 0.005*"health" + 0.005*"practice" + 0.005*"leaders" + 0.005*"17" + 0.004*"relationships"
+2024-11-18 09:40:44,802 - topic #1 (0.333): 0.020*"’" + 0.008*"Bromley" + 0.007*"well" + 0.007*"leaders" + 0.006*"plans" + 0.006*"needs" + 0.006*"progress" + 0.006*"practice" + 0.005*"education" + 0.004*"experiences"
+2024-11-18 09:40:44,802 - topic #2 (0.333): 0.012*"’" + 0.009*"Bromley" + 0.007*"well" + 0.006*"needs" + 0.005*"13" + 0.004*"plans" + 0.004*"YPAs" + 0.004*"health" + 0.004*"practice" + 0.004*"strong"
+2024-11-18 09:40:44,802 - topic diff=0.773836, rho=1.000000
+2024-11-18 09:40:44,802 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1266, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:40:44.802586', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:40:45,636 - Inspection date 2023-11-13 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:40:45,636 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:45,637 - Inspection date 2023-11-13 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:40:45,637 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:45,637 - Inspection date 2023-11-13 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:40:45,637 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:45,637 - Inspection date 2023-11-13 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:40:45,637 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:45,637 - Inspection date 2023-11-13 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:40:45,637 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:45,638 - Inspection date 2023-11-13 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:40:45,638 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:53,630 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:40:53,633 - built Dictionary<993 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1735 corpus positions)
+2024-11-18 09:40:53,634 - Dictionary lifecycle event {'msg': "built Dictionary<993 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1735 corpus positions)", 'datetime': '2024-11-18T09:40:53.633996', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:40:53,635 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:40:53,635 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:40:53,636 - using serial LDA version on this node
+2024-11-18 09:40:53,636 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:40:53,636 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:40:53,642 - -8.063 per-word bound, 267.3 perplexity estimate based on a held-out corpus of 1 documents with 1735 words
+2024-11-18 09:40:53,642 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:40:53,644 - topic #0 (0.333): 0.010*"’" + 0.007*"practice" + 0.007*"leaders" + 0.006*"Camden" + 0.006*"well" + 0.005*"protection" + 0.005*"response" + 0.005*"appropriate" + 0.004*"meetings" + 0.004*"progress"
+2024-11-18 09:40:53,644 - topic #1 (0.333): 0.011*"’" + 0.009*"Camden" + 0.007*"leaders" + 0.006*"needs" + 0.006*"practice" + 0.005*"well" + 0.004*"29" + 0.004*"25" + 0.004*"protection" + 0.004*"April"
+2024-11-18 09:40:53,644 - topic #2 (0.333): 0.011*"’" + 0.006*"Camden" + 0.005*"leaders" + 0.005*"practice" + 0.005*"protection" + 0.005*"needs" + 0.004*"response" + 0.004*"2022" + 0.004*"well" + 0.004*"appropriate"
+2024-11-18 09:40:53,645 - topic diff=0.701784, rho=1.000000
+2024-11-18 09:40:53,645 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=993, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:40:53.645159', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:40:54,443 - Inspection date 2022-04-25 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:40:54,443 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:54,443 - Inspection date 2022-04-25 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:40:54,443 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:54,444 - Inspection date 2022-04-25 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:40:54,444 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:54,444 - Inspection date 2022-04-25 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:40:54,444 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:54,444 - Inspection date 2022-04-25 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:40:54,444 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:40:54,445 - Inspection date 2022-04-25 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:40:54,445 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:04,620 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:41:04,622 - built Dictionary<1046 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2209 corpus positions)
+2024-11-18 09:41:04,622 - Dictionary lifecycle event {'msg': "built Dictionary<1046 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2209 corpus positions)", 'datetime': '2024-11-18T09:41:04.622821', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:41:04,623 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:41:04,623 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:41:04,624 - using serial LDA version on this node
+2024-11-18 09:41:04,624 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:41:04,624 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:41:04,627 - -7.988 per-word bound, 253.9 perplexity estimate based on a held-out corpus of 1 documents with 2209 words
+2024-11-18 09:41:04,627 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:41:04,629 - topic #0 (0.333): 0.009*"’" + 0.008*"needs" + 0.006*"Croydon" + 0.006*"well" + 0.005*"need" + 0.005*"quality" + 0.005*"effective" + 0.005*"ensure" + 0.005*"Senior" + 0.005*"plans"
+2024-11-18 09:41:04,629 - topic #1 (0.333): 0.014*"’" + 0.007*"well" + 0.007*"needs" + 0.006*"good" + 0.006*"Croydon" + 0.005*"quality" + 0.005*"ensure" + 0.005*"need" + 0.005*"effective" + 0.005*"Senior"
+2024-11-18 09:41:04,629 - topic #2 (0.333): 0.012*"’" + 0.008*"well" + 0.006*"needs" + 0.006*"Senior" + 0.006*"risk" + 0.006*"health" + 0.005*"plans" + 0.005*"need" + 0.005*"quality" + 0.005*"education"
+2024-11-18 09:41:04,629 - topic diff=0.770743, rho=1.000000
+2024-11-18 09:41:04,629 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1046, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:41:04.629655', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:41:05,613 - Inspection date 2020-02-03 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:41:05,613 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:05,614 - Inspection date 2020-02-03 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:41:05,614 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:05,614 - Inspection date 2020-02-03 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:41:05,614 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:05,614 - Inspection date 2020-02-03 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:41:05,614 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:05,614 - Inspection date 2020-02-03 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:41:05,614 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:05,614 - Inspection date 2020-02-03 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:41:05,614 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:16,508 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:41:16,510 - built Dictionary<1119 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2365 corpus positions)
+2024-11-18 09:41:16,510 - Dictionary lifecycle event {'msg': "built Dictionary<1119 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2365 corpus positions)", 'datetime': '2024-11-18T09:41:16.510839', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:41:16,511 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:41:16,512 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:41:16,512 - using serial LDA version on this node
+2024-11-18 09:41:16,512 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:41:16,512 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:41:16,516 - -8.054 per-word bound, 265.8 perplexity estimate based on a held-out corpus of 1 documents with 2365 words
+2024-11-18 09:41:16,516 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:41:16,517 - topic #0 (0.333): 0.017*"’" + 0.009*"Ealing" + 0.007*"well" + 0.006*"plans" + 0.005*"progress" + 0.005*"effective" + 0.005*"2024" + 0.005*"needs" + 0.004*"3" + 0.004*"good"
+2024-11-18 09:41:16,518 - topic #1 (0.333): 0.017*"’" + 0.008*"Ealing" + 0.007*"needs" + 0.006*"progress" + 0.006*"well" + 0.006*"need" + 0.006*"plans" + 0.004*"April" + 0.004*"quality" + 0.004*"health"
+2024-11-18 09:41:16,518 - topic #2 (0.333): 0.018*"’" + 0.009*"well" + 0.007*"Ealing" + 0.006*"needs" + 0.006*"effective" + 0.006*"progress" + 0.005*"need" + 0.005*"3" + 0.005*"22" + 0.005*"London"
+2024-11-18 09:41:16,518 - topic diff=0.786573, rho=1.000000
+2024-11-18 09:41:16,518 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1119, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:41:16.518500', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:41:17,463 - Inspection date 2024-04-22 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:41:17,463 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:17,464 - Inspection date 2024-04-22 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:41:17,464 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:17,464 - Inspection date 2024-04-22 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:41:17,464 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:17,464 - Inspection date 2024-04-22 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:41:17,464 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:17,465 - Inspection date 2024-04-22 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:41:17,465 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:17,465 - Inspection date 2024-04-22 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:41:17,465 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:27,782 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:41:27,784 - built Dictionary<1108 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2531 corpus positions)
+2024-11-18 09:41:27,784 - Dictionary lifecycle event {'msg': "built Dictionary<1108 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2531 corpus positions)", 'datetime': '2024-11-18T09:41:27.784615', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:41:27,785 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:41:27,785 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:41:27,786 - using serial LDA version on this node
+2024-11-18 09:41:27,786 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:41:27,786 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:41:27,790 - -7.996 per-word bound, 255.3 perplexity estimate based on a held-out corpus of 1 documents with 2531 words
+2024-11-18 09:41:27,790 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:41:27,791 - topic #0 (0.333): 0.009*"’" + 0.008*"plans" + 0.007*"needs" + 0.007*"well" + 0.007*"Enfield" + 0.006*"need" + 0.005*"receive" + 0.005*"timely" + 0.004*"22" + 0.004*"ensure"
+2024-11-18 09:41:27,791 - topic #1 (0.333): 0.019*"’" + 0.011*"needs" + 0.008*"well" + 0.007*"Enfield" + 0.006*"plans" + 0.005*"timely" + 0.005*"education" + 0.005*"good" + 0.005*"need" + 0.005*"progress"
+2024-11-18 09:41:27,791 - topic #2 (0.333): 0.019*"’" + 0.012*"needs" + 0.011*"well" + 0.007*"Enfield" + 0.007*"plans" + 0.006*"receive" + 0.006*"need" + 0.005*"practice" + 0.005*"ensure" + 0.005*"protection"
+2024-11-18 09:41:27,791 - topic diff=0.803308, rho=1.000000
+2024-11-18 09:41:27,791 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1108, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:41:27.791916', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:41:28,664 - Inspection date 2024-07-22 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:41:28,664 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:28,665 - Inspection date 2024-07-22 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:41:28,665 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:28,665 - Inspection date 2024-07-22 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:41:28,665 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:28,665 - Inspection date 2024-07-22 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:41:28,665 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:28,666 - Inspection date 2024-07-22 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:41:28,666 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:28,666 - Inspection date 2024-07-22 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:41:28,666 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:38,858 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:41:38,860 - built Dictionary<1023 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2078 corpus positions)
+2024-11-18 09:41:38,860 - Dictionary lifecycle event {'msg': "built Dictionary<1023 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2078 corpus positions)", 'datetime': '2024-11-18T09:41:38.860170', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:41:38,861 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:41:38,861 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:41:38,861 - using serial LDA version on this node
+2024-11-18 09:41:38,861 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:41:38,861 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:41:38,865 - -7.989 per-word bound, 254.1 perplexity estimate based on a held-out corpus of 1 documents with 2078 words
+2024-11-18 09:41:38,865 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:41:38,866 - topic #0 (0.333): 0.017*"’" + 0.011*"Greenwich" + 0.007*"needs" + 0.006*"7" + 0.006*"well" + 0.006*"plans" + 0.005*"quality" + 0.005*"Royal" + 0.005*"effective" + 0.005*"3"
+2024-11-18 09:41:38,866 - topic #1 (0.333): 0.015*"’" + 0.011*"Greenwich" + 0.007*"well" + 0.006*"plans" + 0.005*"needs" + 0.005*"progress" + 0.004*"provide" + 0.004*"7" + 0.004*"3" + 0.004*"2024"
+2024-11-18 09:41:38,866 - topic #2 (0.333): 0.020*"’" + 0.011*"Greenwich" + 0.009*"needs" + 0.008*"well" + 0.006*"plans" + 0.005*"2024" + 0.005*"progress" + 0.005*"provide" + 0.004*"Borough" + 0.004*"3"
+2024-11-18 09:41:38,866 - topic diff=0.757790, rho=1.000000
+2024-11-18 09:41:38,866 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1023, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:41:38.866908', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:41:39,776 - Inspection date 2024-06-03 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:41:39,776 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:39,777 - Inspection date 2024-06-03 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:41:39,777 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:39,777 - Inspection date 2024-06-03 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:41:39,777 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:39,777 - Inspection date 2024-06-03 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:41:39,777 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:39,777 - Inspection date 2024-06-03 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:41:39,777 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:39,778 - Inspection date 2024-06-03 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:41:39,778 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:52,284 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:41:52,287 - built Dictionary<1222 unique tokens: ["'s", '0161', '0300', '1', '10']...> from 1 documents (total 2748 corpus positions)
+2024-11-18 09:41:52,287 - Dictionary lifecycle event {'msg': 'built Dictionary<1222 unique tokens: ["\'s", \'0161\', \'0300\', \'1\', \'10\']...> from 1 documents (total 2748 corpus positions)', 'datetime': '2024-11-18T09:41:52.287435', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:41:52,288 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:41:52,288 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:41:52,289 - using serial LDA version on this node
+2024-11-18 09:41:52,289 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:41:52,289 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:41:52,293 - -8.101 per-word bound, 274.7 perplexity estimate based on a held-out corpus of 1 documents with 2748 words
+2024-11-18 09:41:52,293 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:41:52,294 - topic #0 (0.333): 0.020*"’" + 0.009*"Hackney" + 0.008*"needs" + 0.007*"well" + 0.006*"carers" + 0.005*"practice" + 0.004*"timely" + 0.004*"July" + 0.004*"need" + 0.004*"education"
+2024-11-18 09:41:52,294 - topic #1 (0.333): 0.014*"’" + 0.010*"Hackney" + 0.009*"needs" + 0.006*"carers" + 0.005*"12" + 0.005*"need" + 0.005*"council" + 0.005*"timely" + 0.004*"2024" + 0.004*"effective"
+2024-11-18 09:41:52,295 - topic #2 (0.333): 0.019*"’" + 0.008*"Hackney" + 0.006*"needs" + 0.005*"12" + 0.005*"well" + 0.004*"carers" + 0.004*"need" + 0.004*"1" + 0.004*"leaders" + 0.004*"practice"
+2024-11-18 09:41:52,295 - topic diff=0.801717, rho=1.000000
+2024-11-18 09:41:52,295 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1222, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:41:52.295305', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:41:53,320 - Inspection date 2024-07-01 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:41:53,320 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:53,320 - Inspection date 2024-07-01 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:41:53,320 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:53,321 - Inspection date 2024-07-01 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:41:53,321 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:53,321 - Inspection date 2024-07-01 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:41:53,321 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:53,321 - Inspection date 2024-07-01 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:41:53,321 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:41:53,321 - Inspection date 2024-07-01 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:41:53,321 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:06,209 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:42:06,212 - built Dictionary<1330 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2905 corpus positions)
+2024-11-18 09:42:06,212 - Dictionary lifecycle event {'msg': "built Dictionary<1330 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2905 corpus positions)", 'datetime': '2024-11-18T09:42:06.212210', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:42:06,213 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:42:06,213 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:42:06,213 - using serial LDA version on this node
+2024-11-18 09:42:06,214 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:42:06,214 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:42:06,218 - -8.199 per-word bound, 293.9 perplexity estimate based on a held-out corpus of 1 documents with 2905 words
+2024-11-18 09:42:06,218 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:42:06,219 - topic #0 (0.333): 0.012*"’" + 0.006*"well" + 0.005*"needs" + 0.005*"receive" + 0.004*"leaders" + 0.004*"timely" + 0.004*"understand" + 0.004*"protection" + 0.004*"Fulham" + 0.003*"early"
+2024-11-18 09:42:06,220 - topic #1 (0.333): 0.019*"’" + 0.009*"well" + 0.006*"needs" + 0.006*"receive" + 0.005*"Fulham" + 0.005*"plans" + 0.005*"Hammersmith" + 0.005*"supported" + 0.005*"need" + 0.004*"2024"
+2024-11-18 09:42:06,220 - topic #2 (0.333): 0.012*"’" + 0.007*"well" + 0.006*"receive" + 0.005*"leaders" + 0.004*"Hammersmith" + 0.004*"effective" + 0.004*"15" + 0.004*"protection" + 0.004*"needs" + 0.004*"11"
+2024-11-18 09:42:06,220 - topic diff=0.804742, rho=1.000000
+2024-11-18 09:42:06,220 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1330, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:42:06.220487', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:42:07,105 - Inspection date 2024-03-11 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:42:07,105 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:07,105 - Inspection date 2024-03-11 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:42:07,106 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:07,106 - Inspection date 2024-03-11 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:42:07,106 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:07,106 - Inspection date 2024-03-11 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:42:07,106 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:07,106 - Inspection date 2024-03-11 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:42:07,106 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:07,106 - Inspection date 2024-03-11 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:42:07,106 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:19,306 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:42:19,308 - built Dictionary<1252 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2620 corpus positions)
+2024-11-18 09:42:19,308 - Dictionary lifecycle event {'msg': "built Dictionary<1252 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2620 corpus positions)", 'datetime': '2024-11-18T09:42:19.308791', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:42:19,309 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:42:19,310 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:42:19,310 - using serial LDA version on this node
+2024-11-18 09:42:19,310 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:42:19,310 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:42:19,314 - -8.169 per-word bound, 287.9 perplexity estimate based on a held-out corpus of 1 documents with 2620 words
+2024-11-18 09:42:19,314 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:42:19,316 - topic #0 (0.333): 0.014*"’" + 0.009*"Haringey" + 0.008*"needs" + 0.006*"well" + 0.006*"good" + 0.006*"plans" + 0.005*"need" + 0.005*"progress" + 0.005*"leaders" + 0.004*"risk"
+2024-11-18 09:42:19,316 - topic #1 (0.333): 0.020*"’" + 0.009*"plans" + 0.008*"needs" + 0.008*"Haringey" + 0.006*"well" + 0.005*"education" + 0.005*"good" + 0.005*"progress" + 0.005*"need" + 0.004*"timely"
+2024-11-18 09:42:19,316 - topic #2 (0.333): 0.011*"’" + 0.007*"Haringey" + 0.006*"needs" + 0.005*"well" + 0.005*"plans" + 0.005*"need" + 0.005*"impact" + 0.004*"good" + 0.004*"progress" + 0.004*"supported"
+2024-11-18 09:42:19,316 - topic diff=0.779751, rho=1.000000
+2024-11-18 09:42:19,316 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1252, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:42:19.316724', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:42:20,158 - Inspection date 2023-02-13 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:42:20,158 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:20,159 - Inspection date 2023-02-13 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:42:20,159 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:20,159 - Inspection date 2023-02-13 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:42:20,159 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:20,159 - Inspection date 2023-02-13 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:42:20,159 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:20,159 - Inspection date 2023-02-13 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:42:20,159 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:20,159 - Inspection date 2023-02-13 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:42:20,159 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:28,113 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:42:28,114 - built Dictionary<942 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1732 corpus positions)
+2024-11-18 09:42:28,115 - Dictionary lifecycle event {'msg': "built Dictionary<942 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1732 corpus positions)", 'datetime': '2024-11-18T09:42:28.115099', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:42:28,115 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:42:28,116 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:42:28,116 - using serial LDA version on this node
+2024-11-18 09:42:28,116 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:42:28,116 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:42:28,119 - -7.972 per-word bound, 251.1 perplexity estimate based on a held-out corpus of 1 documents with 1732 words
+2024-11-18 09:42:28,119 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:42:28,121 - topic #0 (0.333): 0.012*"’" + 0.012*"good" + 0.008*"needs" + 0.008*"well" + 0.007*"impact" + 0.005*"practice" + 0.005*"need" + 0.005*"school" + 0.005*"experiences" + 0.005*"early"
+2024-11-18 09:42:28,121 - topic #1 (0.333): 0.010*"’" + 0.006*"needs" + 0.006*"well" + 0.005*"good" + 0.004*"plans" + 0.004*"impact" + 0.004*"early" + 0.004*"experiences" + 0.004*"need" + 0.004*"school"
+2024-11-18 09:42:28,121 - topic #2 (0.333): 0.012*"good" + 0.012*"’" + 0.010*"well" + 0.008*"needs" + 0.006*"protection" + 0.006*"plans" + 0.005*"practice" + 0.005*"need" + 0.005*"planning" + 0.005*"experiences"
+2024-11-18 09:42:28,122 - topic diff=0.702891, rho=1.000000
+2024-11-18 09:42:28,122 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=942, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:42:28.122147', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:42:29,803 - Inspection date 2020-02-10 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:42:29,803 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:29,804 - Inspection date 2020-02-10 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:42:29,804 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:29,804 - Inspection date 2020-02-10 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:42:29,804 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:29,804 - Inspection date 2020-02-10 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:42:29,804 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:29,804 - Inspection date 2020-02-10 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:42:29,804 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:29,805 - Inspection date 2020-02-10 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:42:29,805 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:39,848 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:42:39,850 - built Dictionary<1069 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2243 corpus positions)
+2024-11-18 09:42:39,850 - Dictionary lifecycle event {'msg': "built Dictionary<1069 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2243 corpus positions)", 'datetime': '2024-11-18T09:42:39.850575', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:42:39,851 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:42:39,851 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:42:39,851 - using serial LDA version on this node
+2024-11-18 09:42:39,852 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:42:39,852 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:42:39,855 - -8.010 per-word bound, 257.8 perplexity estimate based on a held-out corpus of 1 documents with 2243 words
+2024-11-18 09:42:39,855 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:42:39,857 - topic #0 (0.333): 0.013*"’" + 0.012*"Havering" + 0.009*"quality" + 0.006*"plans" + 0.006*"effective" + 0.005*"oversight" + 0.005*"2023" + 0.004*"11" + 0.004*"many" + 0.004*"well"
+2024-11-18 09:42:39,857 - topic #1 (0.333): 0.022*"’" + 0.011*"Havering" + 0.009*"quality" + 0.008*"plans" + 0.006*"needs" + 0.005*"effective" + 0.005*"oversight" + 0.005*"11" + 0.004*"December" + 0.004*"22"
+2024-11-18 09:42:39,857 - topic #2 (0.333): 0.016*"’" + 0.011*"Havering" + 0.007*"quality" + 0.006*"plans" + 0.006*"oversight" + 0.005*"effective" + 0.004*"practice" + 0.004*"22" + 0.004*"information" + 0.004*"needs"
+2024-11-18 09:42:39,857 - topic diff=0.768420, rho=1.000000
+2024-11-18 09:42:39,857 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1069, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:42:39.857708', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:42:40,803 - Inspection date 2023-12-11 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:42:40,803 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:40,803 - Inspection date 2023-12-11 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:42:40,803 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:40,804 - Inspection date 2023-12-11 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:42:40,804 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:40,804 - Inspection date 2023-12-11 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:42:40,804 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:40,804 - Inspection date 2023-12-11 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:42:40,804 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:40,804 - Inspection date 2023-12-11 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:42:40,805 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:51,257 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:42:51,259 - built Dictionary<1161 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2511 corpus positions)
+2024-11-18 09:42:51,259 - Dictionary lifecycle event {'msg': "built Dictionary<1161 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2511 corpus positions)", 'datetime': '2024-11-18T09:42:51.259728', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:42:51,260 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:42:51,260 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:42:51,261 - using serial LDA version on this node
+2024-11-18 09:42:51,261 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:42:51,261 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:42:51,265 - -8.076 per-word bound, 269.9 perplexity estimate based on a held-out corpus of 1 documents with 2511 words
+2024-11-18 09:42:51,265 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:42:51,266 - topic #0 (0.333): 0.020*"’" + 0.010*"needs" + 0.008*"plans" + 0.007*"Hillingdon" + 0.006*"well" + 0.005*"2" + 0.004*"family" + 0.004*"need" + 0.004*"improve" + 0.004*"October"
+2024-11-18 09:42:51,266 - topic #1 (0.333): 0.011*"’" + 0.009*"Hillingdon" + 0.008*"needs" + 0.008*"well" + 0.007*"plans" + 0.006*"need" + 0.005*"leaders" + 0.005*"6" + 0.004*"PAs" + 0.004*"team"
+2024-11-18 09:42:51,267 - topic #2 (0.333): 0.022*"’" + 0.010*"needs" + 0.008*"well" + 0.007*"plans" + 0.007*"Hillingdon" + 0.005*"team" + 0.004*"2023" + 0.004*"6" + 0.004*"positive" + 0.004*"progress"
+2024-11-18 09:42:51,267 - topic diff=0.793053, rho=1.000000
+2024-11-18 09:42:51,267 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1161, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:42:51.267302', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:42:52,206 - Inspection date 2023-10-02 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:42:52,206 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:52,206 - Inspection date 2023-10-02 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:42:52,206 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:52,206 - Inspection date 2023-10-02 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:42:52,207 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:52,207 - Inspection date 2023-10-02 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:42:52,207 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:52,207 - Inspection date 2023-10-02 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:42:52,207 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:42:52,207 - Inspection date 2023-10-02 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:42:52,207 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:03,010 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:43:03,012 - built Dictionary<1070 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2271 corpus positions)
+2024-11-18 09:43:03,013 - Dictionary lifecycle event {'msg': "built Dictionary<1070 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2271 corpus positions)", 'datetime': '2024-11-18T09:43:03.013210', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:43:03,014 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:43:03,014 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:43:03,014 - using serial LDA version on this node
+2024-11-18 09:43:03,014 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:43:03,015 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:43:03,018 - -8.001 per-word bound, 256.1 perplexity estimate based on a held-out corpus of 1 documents with 2271 words
+2024-11-18 09:43:03,018 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:43:03,019 - topic #0 (0.333): 0.025*"’" + 0.012*"needs" + 0.010*"well" + 0.009*"effective" + 0.007*"Hounslow" + 0.006*"plans" + 0.006*"timely" + 0.005*"16" + 0.005*"2023" + 0.005*"strong"
+2024-11-18 09:43:03,020 - topic #1 (0.333): 0.016*"’" + 0.011*"well" + 0.011*"needs" + 0.009*"Hounslow" + 0.007*"effective" + 0.006*"timely" + 0.005*"plans" + 0.005*"education" + 0.004*"training" + 0.004*"oversight"
+2024-11-18 09:43:03,020 - topic #2 (0.333): 0.016*"’" + 0.009*"needs" + 0.008*"well" + 0.006*"timely" + 0.005*"effective" + 0.005*"Hounslow" + 0.005*"16" + 0.005*"plans" + 0.004*"strong" + 0.004*"oversight"
+2024-11-18 09:43:03,020 - topic diff=0.786040, rho=1.000000
+2024-11-18 09:43:03,020 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1070, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:43:03.020618', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:43:03,884 - Inspection date 2023-10-16 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:43:03,884 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:03,885 - Inspection date 2023-10-16 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:43:03,885 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:03,885 - Inspection date 2023-10-16 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:43:03,885 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:03,885 - Inspection date 2023-10-16 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:43:03,885 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:03,885 - Inspection date 2023-10-16 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:43:03,885 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:03,886 - Inspection date 2023-10-16 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:43:03,886 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:12,277 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:43:12,279 - built Dictionary<968 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1982 corpus positions)
+2024-11-18 09:43:12,279 - Dictionary lifecycle event {'msg': "built Dictionary<968 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1982 corpus positions)", 'datetime': '2024-11-18T09:43:12.279868', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:43:12,280 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:43:12,280 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:43:12,281 - using serial LDA version on this node
+2024-11-18 09:43:12,281 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:43:12,281 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:43:12,284 - -7.927 per-word bound, 243.4 perplexity estimate based on a held-out corpus of 1 documents with 1982 words
+2024-11-18 09:43:12,284 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:43:12,285 - topic #0 (0.333): 0.010*"needs" + 0.010*"well" + 0.009*"’" + 0.006*"plans" + 0.005*"highly" + 0.005*"leaders" + 0.005*"quality" + 0.005*"meet" + 0.004*"Islington" + 0.004*"risk"
+2024-11-18 09:43:12,286 - topic #1 (0.333): 0.014*"’" + 0.012*"needs" + 0.012*"well" + 0.008*"plans" + 0.008*"good" + 0.007*"quality" + 0.007*"highly" + 0.006*"effective" + 0.006*"leaders" + 0.005*"Islington"
+2024-11-18 09:43:12,286 - topic #2 (0.333): 0.014*"’" + 0.009*"needs" + 0.007*"well" + 0.004*"leaders" + 0.004*"plans" + 0.004*"effective" + 0.004*"highly" + 0.004*"Islington" + 0.004*"practice" + 0.004*"good"
+2024-11-18 09:43:12,286 - topic diff=0.760976, rho=1.000000
+2024-11-18 09:43:12,286 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=968, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:43:12.286518', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:43:14,026 - Inspection date 2020-03-09 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:43:14,027 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:14,027 - Inspection date 2020-03-09 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:43:14,027 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:14,027 - Inspection date 2020-03-09 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:43:14,027 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:14,027 - Inspection date 2020-03-09 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:43:14,028 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:14,028 - Inspection date 2020-03-09 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:43:14,028 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:14,028 - Inspection date 2020-03-09 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:43:14,028 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:24,973 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:43:24,975 - built Dictionary<976 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2090 corpus positions)
+2024-11-18 09:43:24,975 - Dictionary lifecycle event {'msg': "built Dictionary<976 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2090 corpus positions)", 'datetime': '2024-11-18T09:43:24.975447', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:43:24,976 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:43:24,976 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:43:24,976 - using serial LDA version on this node
+2024-11-18 09:43:24,977 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:43:24,977 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:43:24,980 - -7.905 per-word bound, 239.7 perplexity estimate based on a held-out corpus of 1 documents with 2090 words
+2024-11-18 09:43:24,980 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:43:24,981 - topic #0 (0.333): 0.017*"’" + 0.009*"well" + 0.009*"needs" + 0.008*"plans" + 0.007*"good" + 0.007*"need" + 0.007*"progress" + 0.006*"impact" + 0.006*"leaders" + 0.005*"Lambeth"
+2024-11-18 09:43:24,981 - topic #1 (0.333): 0.014*"’" + 0.008*"well" + 0.007*"needs" + 0.007*"plans" + 0.007*"good" + 0.006*"Lambeth" + 0.005*"need" + 0.005*"number" + 0.005*"impact" + 0.004*"arrangements"
+2024-11-18 09:43:24,982 - topic #2 (0.333): 0.013*"’" + 0.010*"needs" + 0.008*"Lambeth" + 0.007*"well" + 0.006*"plans" + 0.006*"good" + 0.006*"progress" + 0.005*"proceedings" + 0.005*"impact" + 0.005*"24"
+2024-11-18 09:43:24,982 - topic diff=0.802505, rho=1.000000
+2024-11-18 09:43:24,982 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=976, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:43:24.982403', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:43:25,884 - Inspection date 2022-10-24 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:43:25,885 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:25,885 - Inspection date 2022-10-24 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:43:25,885 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:25,885 - Inspection date 2022-10-24 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:43:25,885 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:25,886 - Inspection date 2022-10-24 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:43:25,886 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:25,886 - Inspection date 2022-10-24 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:43:25,886 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:25,886 - Inspection date 2022-10-24 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:43:25,886 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:36,949 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:43:36,951 - built Dictionary<1115 unique tokens: ['00', '0161', '03', '0300', '1']...> from 1 documents (total 2352 corpus positions)
+2024-11-18 09:43:36,951 - Dictionary lifecycle event {'msg': "built Dictionary<1115 unique tokens: ['00', '0161', '03', '0300', '1']...> from 1 documents (total 2352 corpus positions)", 'datetime': '2024-11-18T09:43:36.951855', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:43:36,952 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:43:36,953 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:43:36,953 - using serial LDA version on this node
+2024-11-18 09:43:36,953 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:43:36,953 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:43:36,957 - -8.050 per-word bound, 265.0 perplexity estimate based on a held-out corpus of 1 documents with 2352 words
+2024-11-18 09:43:36,957 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:43:36,958 - topic #0 (0.333): 0.014*"’" + 0.007*"needs" + 0.007*"effective" + 0.007*"well" + 0.006*"progress" + 0.005*"plans" + 0.005*"Lewisham" + 0.005*"appropriate" + 0.005*"leaders" + 0.004*"good"
+2024-11-18 09:43:36,958 - topic #1 (0.333): 0.020*"’" + 0.009*"well" + 0.007*"needs" + 0.006*"Lewisham" + 0.006*"plans" + 0.005*"effective" + 0.005*"good" + 0.005*"4" + 0.005*"benefit" + 0.005*"receive"
+2024-11-18 09:43:36,958 - topic #2 (0.333): 0.017*"’" + 0.009*"plans" + 0.008*"needs" + 0.008*"well" + 0.006*"Lewisham" + 0.006*"effective" + 0.005*"supported" + 0.005*"arrangements" + 0.005*"4" + 0.005*"2023"
+2024-11-18 09:43:36,958 - topic diff=0.766652, rho=1.000000
+2024-11-18 09:43:36,959 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1115, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:43:36.959056', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:43:37,845 - Inspection date 2023-12-04 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:43:37,845 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:37,845 - Inspection date 2023-12-04 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:43:37,846 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:37,846 - Inspection date 2023-12-04 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:43:37,846 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:37,846 - Inspection date 2023-12-04 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:43:37,846 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:37,846 - Inspection date 2023-12-04 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:43:37,846 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:37,846 - Inspection date 2023-12-04 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:43:37,847 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:47,309 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:43:47,311 - built Dictionary<1015 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2032 corpus positions)
+2024-11-18 09:43:47,311 - Dictionary lifecycle event {'msg': "built Dictionary<1015 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2032 corpus positions)", 'datetime': '2024-11-18T09:43:47.311285', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:43:47,312 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:43:47,312 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:43:47,312 - using serial LDA version on this node
+2024-11-18 09:43:47,312 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:43:47,312 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:43:47,316 - -7.990 per-word bound, 254.3 perplexity estimate based on a held-out corpus of 1 documents with 2032 words
+2024-11-18 09:43:47,316 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:43:47,317 - topic #0 (0.333): 0.016*"’" + 0.007*"well" + 0.005*"plans" + 0.005*"Merton" + 0.004*"family" + 0.004*"needs" + 0.004*"progress" + 0.004*"4" + 0.004*"health" + 0.004*"across"
+2024-11-18 09:43:47,317 - topic #1 (0.333): 0.017*"’" + 0.009*"well" + 0.007*"Merton" + 0.006*"needs" + 0.005*"2022" + 0.005*"plans" + 0.004*"ensure" + 0.004*"information" + 0.004*"risk" + 0.004*"4"
+2024-11-18 09:43:47,317 - topic #2 (0.333): 0.014*"’" + 0.007*"well" + 0.007*"Merton" + 0.006*"needs" + 0.005*"family" + 0.005*"progress" + 0.004*"plans" + 0.004*"good" + 0.004*"access" + 0.004*"ensure"
+2024-11-18 09:43:47,318 - topic diff=0.755945, rho=1.000000
+2024-11-18 09:43:47,318 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1015, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:43:47.318158', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:43:48,113 - Inspection date 2022-02-28 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:43:48,114 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:48,114 - Inspection date 2022-02-28 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:43:48,114 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:48,114 - Inspection date 2022-02-28 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:43:48,114 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:48,114 - Inspection date 2022-02-28 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:43:48,115 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:48,115 - Inspection date 2022-02-28 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:43:48,115 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:48,115 - Inspection date 2022-02-28 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:43:48,115 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:43:59,341 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:43:59,343 - built Dictionary<1153 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2540 corpus positions)
+2024-11-18 09:43:59,343 - Dictionary lifecycle event {'msg': "built Dictionary<1153 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2540 corpus positions)", 'datetime': '2024-11-18T09:43:59.343874', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:43:59,345 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:43:59,345 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:43:59,345 - using serial LDA version on this node
+2024-11-18 09:43:59,345 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:43:59,345 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:43:59,349 - -8.055 per-word bound, 266.0 perplexity estimate based on a held-out corpus of 1 documents with 2540 words
+2024-11-18 09:43:59,349 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:43:59,350 - topic #0 (0.333): 0.014*"’" + 0.007*"needs" + 0.007*"practice" + 0.006*"Newham" + 0.006*"progress" + 0.005*"good" + 0.005*"need" + 0.005*"plans" + 0.005*"effective" + 0.004*"ensure"
+2024-11-18 09:43:59,351 - topic #1 (0.333): 0.020*"’" + 0.009*"needs" + 0.008*"need" + 0.007*"Newham" + 0.006*"practice" + 0.006*"plans" + 0.006*"progress" + 0.005*"effective" + 0.004*"good" + 0.004*"18"
+2024-11-18 09:43:59,351 - topic #2 (0.333): 0.022*"’" + 0.007*"needs" + 0.007*"effective" + 0.007*"Newham" + 0.007*"progress" + 0.007*"plans" + 0.005*"practice" + 0.005*"risks" + 0.005*"good" + 0.004*"early"
+2024-11-18 09:43:59,351 - topic diff=0.773607, rho=1.000000
+2024-11-18 09:43:59,351 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1153, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:43:59.351407', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:44:00,338 - Inspection date 2022-07-18 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:44:00,339 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:00,339 - Inspection date 2022-07-18 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:44:00,339 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:00,339 - Inspection date 2022-07-18 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:44:00,339 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:00,339 - Inspection date 2022-07-18 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:44:00,339 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:00,340 - Inspection date 2022-07-18 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:44:00,340 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:00,340 - Inspection date 2022-07-18 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:44:00,340 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:10,788 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:44:10,790 - built Dictionary<1204 unique tokens: ['0', '0161', '0300', '1', '10']...> from 1 documents (total 2389 corpus positions)
+2024-11-18 09:44:10,790 - Dictionary lifecycle event {'msg': "built Dictionary<1204 unique tokens: ['0', '0161', '0300', '1', '10']...> from 1 documents (total 2389 corpus positions)", 'datetime': '2024-11-18T09:44:10.790860', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:44:10,791 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:44:10,792 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:44:10,792 - using serial LDA version on this node
+2024-11-18 09:44:10,792 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:44:10,792 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:44:10,796 - -8.167 per-word bound, 287.5 perplexity estimate based on a held-out corpus of 1 documents with 2389 words
+2024-11-18 09:44:10,796 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:44:10,797 - topic #0 (0.333): 0.016*"’" + 0.007*"Redbridge" + 0.005*"practice" + 0.005*"leaders" + 0.005*"supported" + 0.005*"early" + 0.005*"family" + 0.004*"2024" + 0.004*"10" + 0.004*"needs"
+2024-11-18 09:44:10,798 - topic #1 (0.333): 0.009*"’" + 0.005*"Redbridge" + 0.005*"effective" + 0.004*"practice" + 0.004*"needs" + 0.004*"supported" + 0.004*"risk" + 0.004*"well" + 0.004*"family" + 0.004*"2024"
+2024-11-18 09:44:10,798 - topic #2 (0.333): 0.015*"’" + 0.008*"Redbridge" + 0.006*"carers" + 0.006*"needs" + 0.005*"supported" + 0.005*"family" + 0.005*"leaders" + 0.005*"parents" + 0.004*"practice" + 0.004*"14"
+2024-11-18 09:44:10,798 - topic diff=0.760422, rho=1.000000
+2024-11-18 09:44:10,798 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1204, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:44:10.798330', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:44:11,621 - Inspection date 2024-06-10 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:44:11,621 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:11,621 - Inspection date 2024-06-10 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:44:11,621 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:11,621 - Inspection date 2024-06-10 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:44:11,622 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:11,622 - Inspection date 2024-06-10 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:44:11,622 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:11,622 - Inspection date 2024-06-10 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:44:11,622 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:11,622 - Inspection date 2024-06-10 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:44:11,622 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:20,064 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:44:20,066 - built Dictionary<968 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1818 corpus positions)
+2024-11-18 09:44:20,066 - Dictionary lifecycle event {'msg': "built Dictionary<968 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1818 corpus positions)", 'datetime': '2024-11-18T09:44:20.066637', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:44:20,067 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:44:20,067 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:44:20,067 - using serial LDA version on this node
+2024-11-18 09:44:20,068 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:44:20,068 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:44:20,071 - -7.987 per-word bound, 253.7 perplexity estimate based on a held-out corpus of 1 documents with 1818 words
+2024-11-18 09:44:20,071 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:44:20,072 - topic #0 (0.333): 0.019*"’" + 0.013*"well" + 0.008*"needs" + 0.007*"Richmond" + 0.007*"supported" + 0.006*"good" + 0.005*"team" + 0.005*"need" + 0.005*"upon" + 0.005*"ensure"
+2024-11-18 09:44:20,072 - topic #1 (0.333): 0.011*"’" + 0.010*"well" + 0.008*"Richmond" + 0.007*"needs" + 0.005*"team" + 0.005*"need" + 0.004*"supported" + 0.004*"protection" + 0.004*"good" + 0.004*"2022"
+2024-11-18 09:44:20,073 - topic #2 (0.333): 0.015*"’" + 0.009*"Richmond" + 0.008*"well" + 0.007*"needs" + 0.006*"need" + 0.006*"good" + 0.006*"supported" + 0.005*"team" + 0.005*"4" + 0.005*"strong"
+2024-11-18 09:44:20,073 - topic diff=0.732443, rho=1.000000
+2024-11-18 09:44:20,073 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=968, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:44:20.073263', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:44:20,950 - Inspection date 2022-01-31 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:44:20,950 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:20,950 - Inspection date 2022-01-31 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:44:20,951 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:20,951 - Inspection date 2022-01-31 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:44:20,951 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:20,951 - Inspection date 2022-01-31 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:44:20,951 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:20,951 - Inspection date 2022-01-31 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:44:20,951 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:20,952 - Inspection date 2022-01-31 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:44:20,952 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:30,659 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:44:30,661 - built Dictionary<945 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1878 corpus positions)
+2024-11-18 09:44:30,661 - Dictionary lifecycle event {'msg': "built Dictionary<945 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1878 corpus positions)", 'datetime': '2024-11-18T09:44:30.661304', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:44:30,662 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:44:30,662 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:44:30,662 - using serial LDA version on this node
+2024-11-18 09:44:30,662 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:44:30,662 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:44:30,666 - -7.923 per-word bound, 242.6 perplexity estimate based on a held-out corpus of 1 documents with 1878 words
+2024-11-18 09:44:30,666 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:44:30,667 - topic #0 (0.333): 0.018*"’" + 0.010*"Southwark" + 0.007*"well" + 0.007*"progress" + 0.006*"need" + 0.006*"leaders" + 0.006*"needs" + 0.006*"good" + 0.006*"Leaders" + 0.005*"receive"
+2024-11-18 09:44:30,667 - topic #1 (0.333): 0.017*"’" + 0.009*"Southwark" + 0.007*"good" + 0.007*"needs" + 0.006*"well" + 0.006*"strong" + 0.006*"progress" + 0.005*"Leaders" + 0.005*"effective" + 0.005*"plans"
+2024-11-18 09:44:30,667 - topic #2 (0.333): 0.019*"’" + 0.011*"good" + 0.009*"Southwark" + 0.009*"needs" + 0.008*"well" + 0.006*"plans" + 0.005*"need" + 0.005*"effective" + 0.005*"practice" + 0.005*"risks"
+2024-11-18 09:44:30,667 - topic diff=0.733495, rho=1.000000
+2024-11-18 09:44:30,668 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=945, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:44:30.668005', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:44:31,511 - Inspection date 2022-09-26 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:44:31,511 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:31,511 - Inspection date 2022-09-26 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:44:31,512 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:31,512 - Inspection date 2022-09-26 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:44:31,512 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:31,512 - Inspection date 2022-09-26 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:44:31,512 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:31,512 - Inspection date 2022-09-26 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:44:31,512 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:31,512 - Inspection date 2022-09-26 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:44:31,512 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:39,726 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:44:39,728 - built Dictionary<976 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1847 corpus positions)
+2024-11-18 09:44:39,728 - Dictionary lifecycle event {'msg': "built Dictionary<976 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1847 corpus positions)", 'datetime': '2024-11-18T09:44:39.728517', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:44:39,729 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:44:39,729 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:44:39,729 - using serial LDA version on this node
+2024-11-18 09:44:39,730 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:44:39,730 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:44:39,733 - -7.985 per-word bound, 253.3 perplexity estimate based on a held-out corpus of 1 documents with 1847 words
+2024-11-18 09:44:39,733 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:44:39,734 - topic #0 (0.333): 0.015*"’" + 0.007*"well" + 0.007*"Sutton" + 0.005*"receive" + 0.005*"progress" + 0.005*"good" + 0.005*"effective" + 0.004*"needs" + 0.004*"need" + 0.004*"6"
+2024-11-18 09:44:39,734 - topic #1 (0.333): 0.009*"’" + 0.006*"needs" + 0.005*"well" + 0.004*"Sutton" + 0.004*"progress" + 0.004*"leaders" + 0.004*"effective" + 0.004*"10" + 0.004*"6" + 0.004*"2021"
+2024-11-18 09:44:39,735 - topic #2 (0.333): 0.022*"’" + 0.007*"well" + 0.007*"needs" + 0.006*"Sutton" + 0.006*"progress" + 0.005*"good" + 0.005*"effective" + 0.005*"receive" + 0.005*"supported" + 0.005*"6"
+2024-11-18 09:44:39,735 - topic diff=0.741499, rho=1.000000
+2024-11-18 09:44:39,735 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=976, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:44:39.735245', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:44:41,564 - Inspection date 2021-12-06 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:44:41,564 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:41,565 - Inspection date 2021-12-06 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:44:41,565 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:41,565 - Inspection date 2021-12-06 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:44:41,565 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:41,565 - Inspection date 2021-12-06 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:44:41,565 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:41,565 - Inspection date 2021-12-06 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:44:41,565 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:41,565 - Inspection date 2021-12-06 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:44:41,565 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:51,806 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:44:51,808 - built Dictionary<1194 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2465 corpus positions)
+2024-11-18 09:44:51,808 - Dictionary lifecycle event {'msg': "built Dictionary<1194 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2465 corpus positions)", 'datetime': '2024-11-18T09:44:51.808814', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:44:51,809 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:44:51,810 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:44:51,810 - using serial LDA version on this node
+2024-11-18 09:44:51,810 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:44:51,810 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:44:51,814 - -8.131 per-word bound, 280.4 perplexity estimate based on a held-out corpus of 1 documents with 2465 words
+2024-11-18 09:44:51,814 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:44:51,815 - topic #0 (0.333): 0.012*"’" + 0.005*"need" + 0.005*"progress" + 0.005*"carers" + 0.005*"effective" + 0.005*"plans" + 0.005*"good" + 0.004*"practice" + 0.004*"early" + 0.004*"‘"
+2024-11-18 09:44:51,816 - topic #1 (0.333): 0.016*"’" + 0.008*"good" + 0.007*"effective" + 0.007*"‘" + 0.006*"plans" + 0.005*"need" + 0.005*"well" + 0.005*"practice" + 0.005*"risk" + 0.005*"early"
+2024-11-18 09:44:51,816 - topic #2 (0.333): 0.016*"’" + 0.007*"well" + 0.007*"plans" + 0.006*"good" + 0.006*"practice" + 0.006*"effective" + 0.006*"including" + 0.005*"‘" + 0.005*"needs" + 0.005*"progress"
+2024-11-18 09:44:51,816 - topic diff=0.774547, rho=1.000000
+2024-11-18 09:44:51,816 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1194, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:44:51.816595', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:44:52,670 - Inspection date 2019-06-10 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:44:52,671 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:52,671 - Inspection date 2019-06-10 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:44:52,671 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:52,671 - Inspection date 2019-06-10 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:44:52,671 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:52,672 - Inspection date 2019-06-10 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:44:52,672 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:52,672 - Inspection date 2019-06-10 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:44:52,672 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:44:52,672 - Inspection date 2019-06-10 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:44:52,672 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:03,750 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:45:03,752 - built Dictionary<1061 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2398 corpus positions)
+2024-11-18 09:45:03,752 - Dictionary lifecycle event {'msg': "built Dictionary<1061 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2398 corpus positions)", 'datetime': '2024-11-18T09:45:03.752835', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:45:03,753 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:45:03,753 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:45:03,754 - using serial LDA version on this node
+2024-11-18 09:45:03,754 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:45:03,754 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:45:03,758 - -7.958 per-word bound, 248.7 perplexity estimate based on a held-out corpus of 1 documents with 2398 words
+2024-11-18 09:45:03,758 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:45:03,759 - topic #0 (0.333): 0.020*"’" + 0.008*"well" + 0.008*"needs" + 0.007*"Forest" + 0.006*"plans" + 0.005*"12" + 0.005*"progress" + 0.005*"leaders" + 0.005*"effective" + 0.004*"2024"
+2024-11-18 09:45:03,759 - topic #1 (0.333): 0.016*"’" + 0.010*"needs" + 0.007*"well" + 0.006*"plans" + 0.006*"Waltham" + 0.005*"leaders" + 0.004*"education" + 0.004*"Forest" + 0.004*"timely" + 0.004*"8"
+2024-11-18 09:45:03,759 - topic #2 (0.333): 0.017*"’" + 0.010*"needs" + 0.009*"well" + 0.008*"plans" + 0.007*"Waltham" + 0.006*"progress" + 0.005*"Leaders" + 0.005*"Forest" + 0.005*"8" + 0.004*"2024"
+2024-11-18 09:45:03,759 - topic diff=0.784648, rho=1.000000
+2024-11-18 09:45:03,759 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1061, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:45:03.759929', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:45:04,703 - Inspection date 2024-07-08 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:45:04,704 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:04,704 - Inspection date 2024-07-08 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:45:04,704 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:04,704 - Inspection date 2024-07-08 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:45:04,704 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:04,704 - Inspection date 2024-07-08 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:45:04,705 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:04,705 - Inspection date 2024-07-08 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:45:04,705 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:04,705 - Inspection date 2024-07-08 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:45:04,705 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:13,136 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:45:13,138 - built Dictionary<884 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1772 corpus positions)
+2024-11-18 09:45:13,138 - Dictionary lifecycle event {'msg': "built Dictionary<884 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1772 corpus positions)", 'datetime': '2024-11-18T09:45:13.138424', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:45:13,139 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:45:13,139 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:45:13,139 - using serial LDA version on this node
+2024-11-18 09:45:13,139 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:45:13,139 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:45:13,142 - -7.850 per-word bound, 230.7 perplexity estimate based on a held-out corpus of 1 documents with 1772 words
+2024-11-18 09:45:13,143 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:45:13,144 - topic #0 (0.333): 0.013*"’" + 0.006*"well" + 0.006*"progress" + 0.006*"needs" + 0.006*"quality" + 0.006*"Senior" + 0.006*"protection" + 0.005*"ensure" + 0.005*"Wandsworth" + 0.005*"practice"
+2024-11-18 09:45:13,144 - topic #1 (0.333): 0.011*"’" + 0.007*"well" + 0.005*"needs" + 0.005*"protection" + 0.005*"practice" + 0.005*"receive" + 0.005*"effective" + 0.004*"Wandsworth" + 0.004*"progress" + 0.004*"good"
+2024-11-18 09:45:13,144 - topic #2 (0.333): 0.010*"’" + 0.006*"well" + 0.005*"7" + 0.005*"Wandsworth" + 0.005*"practice" + 0.005*"progress" + 0.005*"Senior" + 0.005*"needs" + 0.005*"However" + 0.004*"receive"
+2024-11-18 09:45:13,144 - topic diff=0.751155, rho=1.000000
+2024-11-18 09:45:13,144 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=884, num_topics=3, decay=0.5, chunksize=2000> in 0.00s', 'datetime': '2024-11-18T09:45:13.144692', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:45:14,017 - Inspection date 2022-11-07 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:45:14,017 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:14,017 - Inspection date 2022-11-07 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:45:14,017 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:14,018 - Inspection date 2022-11-07 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:45:14,018 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:14,018 - Inspection date 2022-11-07 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:45:14,018 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:14,018 - Inspection date 2022-11-07 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:45:14,018 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:14,019 - Inspection date 2022-11-07 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:45:14,019 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:22,797 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:45:22,800 - built Dictionary<1136 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2101 corpus positions)
+2024-11-18 09:45:22,800 - Dictionary lifecycle event {'msg': "built Dictionary<1136 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2101 corpus positions)", 'datetime': '2024-11-18T09:45:22.800348', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:45:22,801 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:45:22,801 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:45:22,801 - using serial LDA version on this node
+2024-11-18 09:45:22,802 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:45:22,802 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:45:22,805 - -8.153 per-word bound, 284.7 perplexity estimate based on a held-out corpus of 1 documents with 2101 words
+2024-11-18 09:45:22,805 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:45:22,807 - topic #0 (0.333): 0.009*"’" + 0.006*"practice" + 0.005*"needs" + 0.005*"well" + 0.005*"highly" + 0.004*"many" + 0.004*"shared" + 0.003*"across" + 0.003*"direct" + 0.003*"plans"
+2024-11-18 09:45:22,807 - topic #1 (0.333): 0.015*"’" + 0.007*"highly" + 0.007*"needs" + 0.006*"practice" + 0.005*"well" + 0.004*"skilled" + 0.004*"many" + 0.004*"across" + 0.004*"family" + 0.003*"high"
+2024-11-18 09:45:22,807 - topic #2 (0.333): 0.013*"’" + 0.008*"practice" + 0.005*"needs" + 0.005*"highly" + 0.004*"well" + 0.004*"across" + 0.004*"direct" + 0.004*"family" + 0.004*"many" + 0.003*"high"
+2024-11-18 09:45:22,807 - topic diff=0.696926, rho=1.000000
+2024-11-18 09:45:22,807 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1136, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:45:22.807744', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:45:23,934 - Inspection date 2019-09-09 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:45:23,934 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:23,935 - Inspection date 2019-09-09 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:45:23,935 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:23,935 - Inspection date 2019-09-09 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:45:23,935 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:23,935 - Inspection date 2019-09-09 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:45:23,935 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:23,935 - Inspection date 2019-09-09 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:45:23,935 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:23,935 - Inspection date 2019-09-09 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:45:23,936 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:35,448 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:45:35,450 - built Dictionary<1199 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2593 corpus positions)
+2024-11-18 09:45:35,450 - Dictionary lifecycle event {'msg': "built Dictionary<1199 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2593 corpus positions)", 'datetime': '2024-11-18T09:45:35.450553', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:45:35,451 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:45:35,451 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:45:35,451 - using serial LDA version on this node
+2024-11-18 09:45:35,452 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:45:35,452 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:45:35,456 - -8.104 per-word bound, 275.1 perplexity estimate based on a held-out corpus of 1 documents with 2593 words
+2024-11-18 09:45:35,456 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:45:35,457 - topic #0 (0.333): 0.016*"’" + 0.008*"needs" + 0.006*"effective" + 0.006*"plans" + 0.005*"need" + 0.005*"good" + 0.005*"Luton" + 0.005*"ensure" + 0.005*"quality" + 0.004*"impact"
+2024-11-18 09:45:35,457 - topic #1 (0.333): 0.019*"’" + 0.006*"needs" + 0.006*"need" + 0.005*"progress" + 0.005*"good" + 0.005*"plans" + 0.005*"Luton" + 0.005*"effective" + 0.004*"impact" + 0.004*"well"
+2024-11-18 09:45:35,457 - topic #2 (0.333): 0.016*"’" + 0.008*"need" + 0.007*"Luton" + 0.006*"plans" + 0.005*"impact" + 0.005*"effective" + 0.005*"receive" + 0.005*"progress" + 0.005*"needs" + 0.005*"quality"
+2024-11-18 09:45:35,457 - topic diff=0.787330, rho=1.000000
+2024-11-18 09:45:35,458 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1199, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:45:35.457991', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:45:36,360 - Inspection date 2022-07-11 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:45:36,361 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:36,361 - Inspection date 2022-07-11 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:45:36,361 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:36,361 - Inspection date 2022-07-11 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:45:36,361 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:36,361 - Inspection date 2022-07-11 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:45:36,361 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:36,361 - Inspection date 2022-07-11 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:45:36,361 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:36,362 - Inspection date 2022-07-11 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:45:36,362 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:44,769 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:45:44,771 - built Dictionary<871 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1938 corpus positions)
+2024-11-18 09:45:44,771 - Dictionary lifecycle event {'msg': "built Dictionary<871 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1938 corpus positions)", 'datetime': '2024-11-18T09:45:44.771742', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:45:44,772 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:45:44,772 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:45:44,772 - using serial LDA version on this node
+2024-11-18 09:45:44,773 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:45:44,773 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:45:44,776 - -7.769 per-word bound, 218.1 perplexity estimate based on a held-out corpus of 1 documents with 1938 words
+2024-11-18 09:45:44,776 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:45:44,777 - topic #0 (0.333): 0.027*"’" + 0.012*"Manchester" + 0.009*"needs" + 0.008*"supported" + 0.007*"always" + 0.006*"plans" + 0.006*"well" + 0.005*"family" + 0.005*"education" + 0.005*"progress"
+2024-11-18 09:45:44,777 - topic #1 (0.333): 0.017*"’" + 0.012*"needs" + 0.010*"Manchester" + 0.008*"well" + 0.006*"supported" + 0.006*"effective" + 0.005*"plans" + 0.005*"always" + 0.005*"quality" + 0.005*"protection"
+2024-11-18 09:45:44,777 - topic #2 (0.333): 0.016*"’" + 0.009*"Manchester" + 0.007*"needs" + 0.006*"always" + 0.006*"well" + 0.006*"protection" + 0.005*"effective" + 0.005*"supported" + 0.005*"education" + 0.005*"1"
+2024-11-18 09:45:44,777 - topic diff=0.808643, rho=1.000000
+2024-11-18 09:45:44,777 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=871, num_topics=3, decay=0.5, chunksize=2000> in 0.00s', 'datetime': '2024-11-18T09:45:44.777937', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:45:45,589 - Inspection date 2022-03-21 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:45:45,589 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:45,589 - Inspection date 2022-03-21 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:45:45,589 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:45,589 - Inspection date 2022-03-21 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:45:45,589 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:45,590 - Inspection date 2022-03-21 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:45:45,590 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:45,590 - Inspection date 2022-03-21 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:45:45,590 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:45,590 - Inspection date 2022-03-21 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:45:45,590 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:54,757 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:45:54,759 - built Dictionary<922 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1857 corpus positions)
+2024-11-18 09:45:54,759 - Dictionary lifecycle event {'msg': "built Dictionary<922 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1857 corpus positions)", 'datetime': '2024-11-18T09:45:54.759429', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:45:54,760 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:45:54,760 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:45:54,760 - using serial LDA version on this node
+2024-11-18 09:45:54,760 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:45:54,760 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:45:54,764 - -7.891 per-word bound, 237.3 perplexity estimate based on a held-out corpus of 1 documents with 1857 words
+2024-11-18 09:45:54,764 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:45:54,765 - topic #0 (0.333): 0.017*"’" + 0.010*"Medway" + 0.009*"practice" + 0.008*"well" + 0.008*"needs" + 0.007*"quality" + 0.007*"leaders" + 0.007*"oversight" + 0.007*"experiences" + 0.006*"Senior"
+2024-11-18 09:45:54,765 - topic #1 (0.333): 0.015*"’" + 0.008*"well" + 0.007*"Medway" + 0.007*"quality" + 0.007*"practice" + 0.007*"impact" + 0.006*"oversight" + 0.005*"risk" + 0.005*"needs" + 0.005*"good"
+2024-11-18 09:45:54,765 - topic #2 (0.333): 0.015*"’" + 0.009*"Medway" + 0.008*"quality" + 0.007*"practice" + 0.007*"well" + 0.006*"leaders" + 0.005*"needs" + 0.005*"clear" + 0.005*"17" + 0.005*"risk"
+2024-11-18 09:45:54,765 - topic diff=0.762938, rho=1.000000
+2024-11-18 09:45:54,765 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=922, num_topics=3, decay=0.5, chunksize=2000> in 0.00s', 'datetime': '2024-11-18T09:45:54.765815', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:45:55,669 - Inspection date 2023-07-17 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:45:55,669 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:55,670 - Inspection date 2023-07-17 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:45:55,670 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:55,670 - Inspection date 2023-07-17 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:45:55,670 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:55,670 - Inspection date 2023-07-17 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:45:55,670 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:55,670 - Inspection date 2023-07-17 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:45:55,671 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:45:55,671 - Inspection date 2023-07-17 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:45:55,671 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:07,357 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:46:07,359 - built Dictionary<1068 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2278 corpus positions)
+2024-11-18 09:46:07,359 - Dictionary lifecycle event {'msg': "built Dictionary<1068 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2278 corpus positions)", 'datetime': '2024-11-18T09:46:07.359265', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:46:07,360 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:46:07,360 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:46:07,360 - using serial LDA version on this node
+2024-11-18 09:46:07,361 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:46:07,361 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:46:07,364 - -8.003 per-word bound, 256.5 perplexity estimate based on a held-out corpus of 1 documents with 2278 words
+2024-11-18 09:46:07,364 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:46:07,365 - topic #0 (0.333): 0.010*"’" + 0.006*"effective" + 0.005*"well" + 0.005*"plans" + 0.005*"progress" + 0.005*"good" + 0.005*"needs" + 0.004*"Middlesbrough" + 0.004*"means" + 0.004*"24"
+2024-11-18 09:46:07,366 - topic #1 (0.333): 0.018*"’" + 0.008*"plans" + 0.008*"well" + 0.008*"effective" + 0.008*"Middlesbrough" + 0.007*"needs" + 0.006*"progress" + 0.006*"practice" + 0.005*"24" + 0.005*"place"
+2024-11-18 09:46:07,366 - topic #2 (0.333): 0.010*"’" + 0.007*"plans" + 0.007*"Middlesbrough" + 0.007*"practice" + 0.006*"effective" + 0.005*"good" + 0.005*"needs" + 0.005*"place" + 0.005*"well" + 0.004*"means"
+2024-11-18 09:46:07,366 - topic diff=0.798469, rho=1.000000
+2024-11-18 09:46:07,366 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1068, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:46:07.366385', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:46:08,219 - Inspection date 2023-03-13 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:46:08,219 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:08,219 - Inspection date 2023-03-13 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:46:08,219 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:08,219 - Inspection date 2023-03-13 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:46:08,219 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:08,219 - Inspection date 2023-03-13 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:46:08,219 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:08,219 - Inspection date 2023-03-13 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:46:08,220 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:08,220 - Inspection date 2023-03-13 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:46:08,220 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:18,341 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:46:18,343 - built Dictionary<1101 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2328 corpus positions)
+2024-11-18 09:46:18,344 - Dictionary lifecycle event {'msg': "built Dictionary<1101 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2328 corpus positions)", 'datetime': '2024-11-18T09:46:18.344016', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:46:18,345 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:46:18,345 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:46:18,345 - using serial LDA version on this node
+2024-11-18 09:46:18,345 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:46:18,345 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:46:18,349 - -8.037 per-word bound, 262.6 perplexity estimate based on a held-out corpus of 1 documents with 2328 words
+2024-11-18 09:46:18,349 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:46:18,350 - topic #0 (0.333): 0.017*"’" + 0.006*"well" + 0.006*"need" + 0.006*"Milton" + 0.005*"good" + 0.005*"25" + 0.005*"leaders" + 0.005*"Keynes" + 0.005*"5" + 0.004*"practice"
+2024-11-18 09:46:18,350 - topic #1 (0.333): 0.011*"’" + 0.006*"Milton" + 0.006*"need" + 0.005*"Keynes" + 0.005*"education" + 0.005*"plans" + 0.004*"practice" + 0.004*"impact" + 0.004*"needs" + 0.004*"well"
+2024-11-18 09:46:18,351 - topic #2 (0.333): 0.016*"’" + 0.007*"Keynes" + 0.006*"well" + 0.005*"Milton" + 0.005*"plans" + 0.005*"practice" + 0.004*"need" + 0.004*"25" + 0.004*"October" + 0.004*"November"
+2024-11-18 09:46:18,351 - topic diff=0.778495, rho=1.000000
+2024-11-18 09:46:18,351 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1101, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:46:18.351279', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:46:19,280 - Inspection date 2021-10-25 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:46:19,280 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:19,280 - Inspection date 2021-10-25 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:46:19,280 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:19,280 - Inspection date 2021-10-25 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:46:19,281 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:19,281 - Inspection date 2021-10-25 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:46:19,281 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:19,281 - Inspection date 2021-10-25 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:46:19,281 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:19,281 - Inspection date 2021-10-25 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:46:19,281 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:28,561 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:46:28,563 - built Dictionary<956 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2076 corpus positions)
+2024-11-18 09:46:28,563 - Dictionary lifecycle event {'msg': "built Dictionary<956 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2076 corpus positions)", 'datetime': '2024-11-18T09:46:28.563474', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:46:28,564 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:46:28,564 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:46:28,564 - using serial LDA version on this node
+2024-11-18 09:46:28,565 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:46:28,565 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:46:28,568 - -7.876 per-word bound, 234.9 perplexity estimate based on a held-out corpus of 1 documents with 2076 words
+2024-11-18 09:46:28,568 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:46:28,569 - topic #0 (0.333): 0.015*"’" + 0.009*"plans" + 0.009*"needs" + 0.007*"well" + 0.007*"protection" + 0.006*"need" + 0.006*"Newcastle" + 0.006*"making" + 0.005*"management" + 0.005*"29"
+2024-11-18 09:46:28,569 - topic #1 (0.333): 0.012*"’" + 0.012*"plans" + 0.007*"Newcastle" + 0.007*"needs" + 0.006*"well" + 0.006*"progress" + 0.006*"good" + 0.005*"protection" + 0.005*"ensure" + 0.005*"planning"
+2024-11-18 09:46:28,570 - topic #2 (0.333): 0.020*"’" + 0.010*"plans" + 0.009*"good" + 0.008*"Newcastle" + 0.007*"needs" + 0.007*"protection" + 0.006*"progress" + 0.006*"making" + 0.006*"response" + 0.006*"ensure"
+2024-11-18 09:46:28,570 - topic diff=0.783571, rho=1.000000
+2024-11-18 09:46:28,570 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=956, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:46:28.570259', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:46:29,579 - Inspection date 2021-11-29 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:46:29,580 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:29,580 - Inspection date 2021-11-29 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:46:29,580 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:29,580 - Inspection date 2021-11-29 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:46:29,580 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:29,580 - Inspection date 2021-11-29 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:46:29,581 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:29,581 - Inspection date 2021-11-29 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:46:29,581 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:29,581 - Inspection date 2021-11-29 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:46:29,581 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:40,706 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:46:40,708 - built Dictionary<1221 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2655 corpus positions)
+2024-11-18 09:46:40,708 - Dictionary lifecycle event {'msg': "built Dictionary<1221 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2655 corpus positions)", 'datetime': '2024-11-18T09:46:40.708738', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:46:40,709 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:46:40,710 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:46:40,710 - using serial LDA version on this node
+2024-11-18 09:46:40,710 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:46:40,710 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:46:40,714 - -8.119 per-word bound, 278.0 perplexity estimate based on a held-out corpus of 1 documents with 2655 words
+2024-11-18 09:46:40,714 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:46:40,715 - topic #0 (0.333): 0.014*"’" + 0.007*"well" + 0.007*"Norfolk" + 0.005*"carers" + 0.005*"needs" + 0.004*"plans" + 0.004*"practice" + 0.004*"supported" + 0.004*"progress" + 0.004*"information"
+2024-11-18 09:46:40,716 - topic #1 (0.333): 0.021*"’" + 0.009*"Norfolk" + 0.009*"well" + 0.007*"carers" + 0.007*"practice" + 0.006*"needs" + 0.006*"supported" + 0.005*"effective" + 0.005*"18" + 0.005*"including"
+2024-11-18 09:46:40,716 - topic #2 (0.333): 0.013*"’" + 0.007*"well" + 0.007*"needs" + 0.006*"Norfolk" + 0.006*"carers" + 0.005*"supported" + 0.005*"plans" + 0.005*"practice" + 0.004*"range" + 0.004*"information"
+2024-11-18 09:46:40,716 - topic diff=0.789549, rho=1.000000
+2024-11-18 09:46:40,716 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1221, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:46:40.716410', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:46:41,597 - Inspection date 2022-11-07 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:46:41,598 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:41,598 - Inspection date 2022-11-07 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:46:41,598 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:41,598 - Inspection date 2022-11-07 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:46:41,598 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:41,598 - Inspection date 2022-11-07 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:46:41,599 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:41,599 - Inspection date 2022-11-07 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:46:41,599 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:41,599 - Inspection date 2022-11-07 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:46:41,599 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:50,952 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:46:50,954 - built Dictionary<958 unique tokens: ['0161', '021', '0300', '1', '10']...> from 1 documents (total 2045 corpus positions)
+2024-11-18 09:46:50,954 - Dictionary lifecycle event {'msg': "built Dictionary<958 unique tokens: ['0161', '021', '0300', '1', '10']...> from 1 documents (total 2045 corpus positions)", 'datetime': '2024-11-18T09:46:50.954603', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:46:50,955 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:46:50,955 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:46:50,955 - using serial LDA version on this node
+2024-11-18 09:46:50,956 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:46:50,956 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:46:50,959 - -7.892 per-word bound, 237.6 perplexity estimate based on a held-out corpus of 1 documents with 2045 words
+2024-11-18 09:46:50,959 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:46:50,960 - topic #0 (0.333): 0.019*"’" + 0.008*"practice" + 0.007*"leaders" + 0.007*"planning" + 0.007*"risk" + 0.007*"needs" + 0.006*"need" + 0.005*"many" + 0.005*"October" + 0.005*"East"
+2024-11-18 09:46:50,960 - topic #1 (0.333): 0.012*"’" + 0.007*"practice" + 0.007*"risk" + 0.005*"planning" + 0.005*"leaders" + 0.005*"many" + 0.005*"needs" + 0.005*"need" + 0.004*"plans" + 0.004*"October"
+2024-11-18 09:46:50,960 - topic #2 (0.333): 0.009*"’" + 0.008*"practice" + 0.007*"needs" + 0.006*"risk" + 0.006*"leaders" + 0.005*"planning" + 0.005*"2021" + 0.005*"need" + 0.005*"quality" + 0.004*"plans"
+2024-11-18 09:46:50,961 - topic diff=0.773593, rho=1.000000
+2024-11-18 09:46:50,961 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=958, num_topics=3, decay=0.5, chunksize=2000> in 0.00s', 'datetime': '2024-11-18T09:46:50.961154', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:46:51,892 - Inspection date 2021-10-04 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:46:51,893 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:51,893 - Inspection date 2021-10-04 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:46:51,893 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:51,893 - Inspection date 2021-10-04 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:46:51,893 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:51,893 - Inspection date 2021-10-04 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:46:51,894 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:51,894 - Inspection date 2021-10-04 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:46:51,894 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:46:51,894 - Inspection date 2021-10-04 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:46:51,894 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:00,958 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:47:00,961 - built Dictionary<1092 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2174 corpus positions)
+2024-11-18 09:47:00,961 - Dictionary lifecycle event {'msg': "built Dictionary<1092 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2174 corpus positions)", 'datetime': '2024-11-18T09:47:00.961334', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:47:00,962 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:47:00,962 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:47:00,962 - using serial LDA version on this node
+2024-11-18 09:47:00,962 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:47:00,962 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:47:00,966 - -8.073 per-word bound, 269.3 perplexity estimate based on a held-out corpus of 1 documents with 2174 words
+2024-11-18 09:47:00,966 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:47:00,967 - topic #0 (0.333): 0.019*"’" + 0.008*"‘" + 0.006*"North" + 0.005*"approach" + 0.005*"need" + 0.005*"leaders" + 0.005*"well" + 0.005*"October" + 0.005*"2022" + 0.004*"family"
+2024-11-18 09:47:00,967 - topic #1 (0.333): 0.022*"’" + 0.007*"‘" + 0.007*"family" + 0.005*"Lincolnshire" + 0.005*"well" + 0.005*"10" + 0.005*"approach" + 0.005*"leaders" + 0.005*"need" + 0.005*"14"
+2024-11-18 09:47:00,968 - topic #2 (0.333): 0.019*"’" + 0.006*"family" + 0.006*"Lincolnshire" + 0.006*"‘" + 0.005*"North" + 0.005*"leaders" + 0.005*"well" + 0.005*"10" + 0.005*"approach" + 0.005*"team"
+2024-11-18 09:47:00,968 - topic diff=0.749492, rho=1.000000
+2024-11-18 09:47:00,968 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1092, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:47:00.968201', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:47:01,858 - Inspection date 2022-10-10 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:47:01,858 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:01,859 - Inspection date 2022-10-10 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:47:01,859 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:01,859 - Inspection date 2022-10-10 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:47:01,859 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:01,859 - Inspection date 2022-10-10 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:47:01,859 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:01,859 - Inspection date 2022-10-10 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:47:01,859 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:01,860 - Inspection date 2022-10-10 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:47:01,860 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:10,978 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:47:10,980 - built Dictionary<1076 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2204 corpus positions)
+2024-11-18 09:47:10,981 - Dictionary lifecycle event {'msg': "built Dictionary<1076 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2204 corpus positions)", 'datetime': '2024-11-18T09:47:10.981007', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:47:10,982 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:47:10,982 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:47:10,982 - using serial LDA version on this node
+2024-11-18 09:47:10,982 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:47:10,982 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:47:10,986 - -8.032 per-word bound, 261.8 perplexity estimate based on a held-out corpus of 1 documents with 2204 words
+2024-11-18 09:47:10,986 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:47:10,987 - topic #0 (0.333): 0.016*"’" + 0.009*"Northamptonshire" + 0.007*"quality" + 0.005*"well" + 0.005*"North" + 0.005*"Leaders" + 0.005*"practice" + 0.005*"NCT" + 0.004*"impact" + 0.004*"2022"
+2024-11-18 09:47:10,987 - topic #1 (0.333): 0.019*"’" + 0.008*"Northamptonshire" + 0.006*"well" + 0.005*"North" + 0.005*"practice" + 0.005*"14" + 0.004*"needs" + 0.004*"impact" + 0.004*"e" + 0.004*"experiences"
+2024-11-18 09:47:10,987 - topic #2 (0.333): 0.016*"’" + 0.009*"North" + 0.007*"Northamptonshire" + 0.007*"well" + 0.006*"quality" + 0.005*"needs" + 0.005*"practice" + 0.005*"NCT" + 0.005*"impact" + 0.005*"3"
+2024-11-18 09:47:10,987 - topic diff=0.750546, rho=1.000000
+2024-11-18 09:47:10,988 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1076, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:47:10.988027', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:47:11,882 - Inspection date 2022-10-03 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:47:11,882 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:11,883 - Inspection date 2022-10-03 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:47:11,883 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:11,883 - Inspection date 2022-10-03 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:47:11,883 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:11,883 - Inspection date 2022-10-03 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:47:11,883 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:11,883 - Inspection date 2022-10-03 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:47:11,883 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:11,884 - Inspection date 2022-10-03 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:47:11,884 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:23,083 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:47:23,086 - built Dictionary<1219 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2902 corpus positions)
+2024-11-18 09:47:23,086 - Dictionary lifecycle event {'msg': "built Dictionary<1219 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2902 corpus positions)", 'datetime': '2024-11-18T09:47:23.086318', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:47:23,087 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:47:23,087 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:47:23,087 - using serial LDA version on this node
+2024-11-18 09:47:23,088 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:47:23,088 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:47:23,092 - -8.070 per-word bound, 268.8 perplexity estimate based on a held-out corpus of 1 documents with 2902 words
+2024-11-18 09:47:23,092 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:47:23,093 - topic #0 (0.333): 0.018*"’" + 0.008*"quality" + 0.007*"needs" + 0.006*"always" + 0.006*"risk" + 0.006*"North" + 0.006*"progress" + 0.006*"number" + 0.005*"Somerset" + 0.005*"practice"
+2024-11-18 09:47:23,093 - topic #1 (0.333): 0.021*"’" + 0.007*"quality" + 0.007*"needs" + 0.006*"number" + 0.005*"North" + 0.005*"need" + 0.005*"always" + 0.005*"Somerset" + 0.005*"well" + 0.005*"practice"
+2024-11-18 09:47:23,093 - topic #2 (0.333): 0.011*"’" + 0.007*"Somerset" + 0.006*"quality" + 0.006*"always" + 0.006*"practice" + 0.006*"needs" + 0.006*"experienced" + 0.005*"North" + 0.005*"need" + 0.005*"well"
+2024-11-18 09:47:23,093 - topic diff=0.832763, rho=1.000000
+2024-11-18 09:47:23,094 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1219, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:47:23.094010', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:47:24,878 - Inspection date 2023-03-13 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:47:24,878 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:24,878 - Inspection date 2023-03-13 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:47:24,878 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:24,878 - Inspection date 2023-03-13 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:47:24,879 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:24,879 - Inspection date 2023-03-13 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:47:24,879 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:24,879 - Inspection date 2023-03-13 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:47:24,879 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:24,879 - Inspection date 2023-03-13 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:47:24,879 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:35,492 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:47:35,494 - built Dictionary<1273 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2518 corpus positions)
+2024-11-18 09:47:35,494 - Dictionary lifecycle event {'msg': "built Dictionary<1273 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2518 corpus positions)", 'datetime': '2024-11-18T09:47:35.494799', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:47:35,495 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:47:35,496 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:47:35,496 - using serial LDA version on this node
+2024-11-18 09:47:35,496 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:47:35,496 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:47:35,500 - -8.224 per-word bound, 299.0 perplexity estimate based on a held-out corpus of 1 documents with 2518 words
+2024-11-18 09:47:35,500 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:47:35,502 - topic #0 (0.333): 0.014*"’" + 0.006*"leaders" + 0.005*"quality" + 0.005*"make" + 0.005*"well" + 0.004*"impact" + 0.004*"need" + 0.004*"needs" + 0.004*"clear" + 0.003*"family"
+2024-11-18 09:47:35,502 - topic #1 (0.333): 0.014*"’" + 0.007*"well" + 0.005*"need" + 0.005*"make" + 0.004*"needs" + 0.004*"quality" + 0.004*"leaders" + 0.004*"progress" + 0.004*"working" + 0.004*"impact"
+2024-11-18 09:47:35,502 - topic #2 (0.333): 0.018*"’" + 0.007*"well" + 0.006*"need" + 0.006*"leaders" + 0.004*"early" + 0.004*"needs" + 0.004*"protection" + 0.004*"quality" + 0.004*"make" + 0.004*"impact"
+2024-11-18 09:47:35,502 - topic diff=0.732513, rho=1.000000
+2024-11-18 09:47:35,502 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1273, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:47:35.502731', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:47:36,442 - Inspection date 2020-03-09 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:47:36,443 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:36,443 - Inspection date 2020-03-09 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:47:36,443 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:36,443 - Inspection date 2020-03-09 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:47:36,443 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:36,444 - Inspection date 2020-03-09 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:47:36,444 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:36,444 - Inspection date 2020-03-09 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:47:36,444 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:36,444 - Inspection date 2020-03-09 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:47:36,444 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:47,501 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:47:47,503 - built Dictionary<1259 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2759 corpus positions)
+2024-11-18 09:47:47,503 - Dictionary lifecycle event {'msg': "built Dictionary<1259 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2759 corpus positions)", 'datetime': '2024-11-18T09:47:47.503646', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:47:47,504 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:47:47,504 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:47:47,505 - using serial LDA version on this node
+2024-11-18 09:47:47,505 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:47:47,505 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:47:47,509 - -8.147 per-word bound, 283.5 perplexity estimate based on a held-out corpus of 1 documents with 2759 words
+2024-11-18 09:47:47,509 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:47:47,511 - topic #0 (0.333): 0.019*"’" + 0.007*"well" + 0.006*"North" + 0.006*"Yorkshire" + 0.005*"practice" + 0.005*"needs" + 0.005*"family" + 0.004*"‘" + 0.004*"3" + 0.004*"need"
+2024-11-18 09:47:47,511 - topic #1 (0.333): 0.026*"’" + 0.008*"well" + 0.007*"practice" + 0.007*"North" + 0.006*"needs" + 0.006*"Yorkshire" + 0.006*"‘" + 0.005*"family" + 0.004*"2023" + 0.004*"supported"
+2024-11-18 09:47:47,511 - topic #2 (0.333): 0.016*"’" + 0.009*"well" + 0.006*"family" + 0.006*"Yorkshire" + 0.005*"practice" + 0.005*"North" + 0.005*"7" + 0.005*"needs" + 0.005*"3" + 0.004*"‘"
+2024-11-18 09:47:47,511 - topic diff=0.800110, rho=1.000000
+2024-11-18 09:47:47,511 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1259, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:47:47.511691', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:47:48,394 - Inspection date 2023-07-03 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:47:48,395 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:48,395 - Inspection date 2023-07-03 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:47:48,395 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:48,395 - Inspection date 2023-07-03 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:47:48,395 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:48,395 - Inspection date 2023-07-03 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:47:48,395 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:48,396 - Inspection date 2023-07-03 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:47:48,396 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:47:48,396 - Inspection date 2023-07-03 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:47:48,396 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:01,005 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:48:01,008 - built Dictionary<1218 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2884 corpus positions)
+2024-11-18 09:48:01,008 - Dictionary lifecycle event {'msg': "built Dictionary<1218 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2884 corpus positions)", 'datetime': '2024-11-18T09:48:01.008349', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:48:01,009 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:48:01,009 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:48:01,009 - using serial LDA version on this node
+2024-11-18 09:48:01,010 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:48:01,010 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:48:01,014 - -8.070 per-word bound, 268.7 perplexity estimate based on a held-out corpus of 1 documents with 2884 words
+2024-11-18 09:48:01,014 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:48:01,015 - topic #0 (0.333): 0.021*"’" + 0.009*"family" + 0.008*"needs" + 0.007*"leaders" + 0.006*"experiences" + 0.006*"strong" + 0.005*"practice" + 0.005*"progress" + 0.005*"well" + 0.005*"Northumberland"
+2024-11-18 09:48:01,015 - topic #1 (0.333): 0.014*"’" + 0.008*"family" + 0.007*"well" + 0.006*"strong" + 0.006*"leaders" + 0.006*"experiences" + 0.005*"effective" + 0.004*"within" + 0.004*"provide" + 0.004*"Northumberland"
+2024-11-18 09:48:01,015 - topic #2 (0.333): 0.020*"’" + 0.007*"Northumberland" + 0.006*"leaders" + 0.006*"needs" + 0.006*"strong" + 0.006*"experiences" + 0.005*"well" + 0.005*"family" + 0.005*"effective" + 0.005*"2024"
+2024-11-18 09:48:01,015 - topic diff=0.836767, rho=1.000000
+2024-11-18 09:48:01,015 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1218, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:48:01.015973', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:48:01,881 - Inspection date 2024-05-20 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:48:01,881 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:01,882 - Inspection date 2024-05-20 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:48:01,882 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:01,882 - Inspection date 2024-05-20 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:48:01,882 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:01,882 - Inspection date 2024-05-20 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:48:01,882 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:01,883 - Inspection date 2024-05-20 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:48:01,883 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:01,883 - Inspection date 2024-05-20 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:48:01,883 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:12,717 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:48:12,720 - built Dictionary<1092 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2316 corpus positions)
+2024-11-18 09:48:12,720 - Dictionary lifecycle event {'msg': "built Dictionary<1092 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2316 corpus positions)", 'datetime': '2024-11-18T09:48:12.720304', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:48:12,721 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:48:12,721 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:48:12,721 - using serial LDA version on this node
+2024-11-18 09:48:12,722 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:48:12,722 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:48:12,725 - -8.029 per-word bound, 261.2 perplexity estimate based on a held-out corpus of 1 documents with 2316 words
+2024-11-18 09:48:12,725 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:48:12,726 - topic #0 (0.333): 0.013*"’" + 0.008*"needs" + 0.007*"Nottingham" + 0.006*"effective" + 0.005*"plans" + 0.005*"City" + 0.005*"impact" + 0.005*"oversight" + 0.004*"11" + 0.004*"2022"
+2024-11-18 09:48:12,727 - topic #1 (0.333): 0.018*"’" + 0.007*"needs" + 0.005*"Nottingham" + 0.005*"plans" + 0.005*"11" + 0.005*"practice" + 0.005*"oversight" + 0.005*"City" + 0.005*"However" + 0.005*"risk"
+2024-11-18 09:48:12,727 - topic #2 (0.333): 0.009*"’" + 0.008*"needs" + 0.006*"plans" + 0.005*"impact" + 0.005*"effective" + 0.004*"Nottingham" + 0.004*"protection" + 0.004*"risk" + 0.004*"consistently" + 0.004*"practice"
+2024-11-18 09:48:12,727 - topic diff=0.767879, rho=1.000000
+2024-11-18 09:48:12,727 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1092, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:48:12.727551', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:48:13,679 - Inspection date None / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:48:13,679 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:13,679 - Inspection date None / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:48:13,679 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:13,679 - Inspection date None / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:48:13,679 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:13,680 - Inspection date None / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:48:13,680 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:13,680 - Inspection date None / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:48:13,680 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:13,680 - Inspection date None / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:48:13,680 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:23,850 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:48:23,854 - built Dictionary<1048 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2129 corpus positions)
+2024-11-18 09:48:23,854 - Dictionary lifecycle event {'msg': "built Dictionary<1048 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2129 corpus positions)", 'datetime': '2024-11-18T09:48:23.854489', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:48:23,856 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:48:23,856 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:48:23,856 - using serial LDA version on this node
+2024-11-18 09:48:23,857 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:48:23,857 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:48:23,863 - -8.012 per-word bound, 258.1 perplexity estimate based on a held-out corpus of 1 documents with 2129 words
+2024-11-18 09:48:23,863 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:48:23,865 - topic #0 (0.333): 0.021*"’" + 0.010*"well" + 0.009*"needs" + 0.008*"Nottinghamshire" + 0.005*"plans" + 0.005*"leaders" + 0.005*"Leaders" + 0.005*"practice" + 0.004*"effective" + 0.004*"20"
+2024-11-18 09:48:23,865 - topic #1 (0.333): 0.014*"’" + 0.008*"well" + 0.008*"needs" + 0.006*"effective" + 0.005*"24" + 0.005*"plans" + 0.004*"Nottinghamshire" + 0.004*"practice" + 0.004*"20" + 0.004*"benefit"
+2024-11-18 09:48:23,866 - topic #2 (0.333): 0.017*"’" + 0.008*"needs" + 0.007*"well" + 0.007*"plans" + 0.006*"Nottinghamshire" + 0.005*"Leaders" + 0.005*"ensure" + 0.004*"range" + 0.004*"practice" + 0.004*"effective"
+2024-11-18 09:48:23,866 - topic diff=0.763669, rho=1.000000
+2024-11-18 09:48:23,866 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1048, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:48:23.866374', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:48:24,760 - Inspection date 2024-05-20 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:48:24,761 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:24,761 - Inspection date 2024-05-20 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:48:24,761 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:24,761 - Inspection date 2024-05-20 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:48:24,761 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:24,761 - Inspection date 2024-05-20 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:48:24,761 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:24,762 - Inspection date 2024-05-20 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:48:24,762 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:24,762 - Inspection date 2024-05-20 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:48:24,762 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:36,166 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:48:36,168 - built Dictionary<1152 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2441 corpus positions)
+2024-11-18 09:48:36,168 - Dictionary lifecycle event {'msg': "built Dictionary<1152 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2441 corpus positions)", 'datetime': '2024-11-18T09:48:36.168420', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:48:36,169 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:48:36,169 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:48:36,169 - using serial LDA version on this node
+2024-11-18 09:48:36,170 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:48:36,170 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:48:36,174 - -8.080 per-word bound, 270.6 perplexity estimate based on a held-out corpus of 1 documents with 2441 words
+2024-11-18 09:48:36,174 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:48:36,175 - topic #0 (0.333): 0.011*"’" + 0.007*"plans" + 0.006*"leaders" + 0.006*"Oldham" + 0.006*"needs" + 0.006*"well" + 0.006*"effective" + 0.006*"practice" + 0.005*"24" + 0.005*"progress"
+2024-11-18 09:48:36,175 - topic #1 (0.333): 0.012*"’" + 0.010*"well" + 0.008*"plans" + 0.007*"needs" + 0.006*"PAs" + 0.005*"leaders" + 0.005*"Oldham" + 0.005*"effective" + 0.004*"family" + 0.004*"progress"
+2024-11-18 09:48:36,175 - topic #2 (0.333): 0.015*"’" + 0.010*"plans" + 0.008*"well" + 0.007*"practice" + 0.006*"Oldham" + 0.006*"PAs" + 0.005*"May" + 0.005*"needs" + 0.005*"progress" + 0.005*"risk"
+2024-11-18 09:48:36,175 - topic diff=0.777819, rho=1.000000
+2024-11-18 09:48:36,176 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1152, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:48:36.175984', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:48:37,049 - Inspection date 2024-05-13 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:48:37,049 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:37,049 - Inspection date 2024-05-13 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:48:37,049 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:37,049 - Inspection date 2024-05-13 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:48:37,049 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:37,050 - Inspection date 2024-05-13 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:48:37,050 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:37,050 - Inspection date 2024-05-13 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:48:37,050 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:37,050 - Inspection date 2024-05-13 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:48:37,050 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:47,600 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:48:47,602 - built Dictionary<1066 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2294 corpus positions)
+2024-11-18 09:48:47,603 - Dictionary lifecycle event {'msg': "built Dictionary<1066 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2294 corpus positions)", 'datetime': '2024-11-18T09:48:47.603124', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:48:47,604 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:48:47,604 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:48:47,604 - using serial LDA version on this node
+2024-11-18 09:48:47,604 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:48:47,604 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:48:47,608 - -7.995 per-word bound, 255.1 perplexity estimate based on a held-out corpus of 1 documents with 2294 words
+2024-11-18 09:48:47,608 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:48:47,609 - topic #0 (0.333): 0.019*"’" + 0.012*"needs" + 0.008*"Oxfordshire" + 0.007*"supported" + 0.007*"well" + 0.006*"good" + 0.006*"risk" + 0.005*"12" + 0.005*"receive" + 0.005*"progress"
+2024-11-18 09:48:47,609 - topic #1 (0.333): 0.014*"’" + 0.007*"needs" + 0.007*"well" + 0.005*"Oxfordshire" + 0.005*"quality" + 0.005*"supported" + 0.004*"good" + 0.004*"risk" + 0.004*"progress" + 0.004*"12"
+2024-11-18 09:48:47,609 - topic #2 (0.333): 0.023*"’" + 0.009*"needs" + 0.007*"risk" + 0.007*"Oxfordshire" + 0.006*"well" + 0.006*"good" + 0.005*"education" + 0.005*"practice" + 0.005*"quality" + 0.005*"arrangements"
+2024-11-18 09:48:47,610 - topic diff=0.786393, rho=1.000000
+2024-11-18 09:48:47,610 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1066, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:48:47.610143', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:48:48,536 - Inspection date 2024-02-12 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:48:48,536 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:48,536 - Inspection date 2024-02-12 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:48:48,537 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:48,537 - Inspection date 2024-02-12 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:48:48,537 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:48,537 - Inspection date 2024-02-12 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:48:48,537 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:48,537 - Inspection date 2024-02-12 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:48:48,537 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:48,537 - Inspection date 2024-02-12 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:48:48,538 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:57,192 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:48:57,194 - built Dictionary<893 unique tokens: ['0-25', '0161', '0300', '1', '10']...> from 1 documents (total 1737 corpus positions)
+2024-11-18 09:48:57,194 - Dictionary lifecycle event {'msg': "built Dictionary<893 unique tokens: ['0-25', '0161', '0300', '1', '10']...> from 1 documents (total 1737 corpus positions)", 'datetime': '2024-11-18T09:48:57.194502', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:48:57,195 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:48:57,195 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:48:57,195 - using serial LDA version on this node
+2024-11-18 09:48:57,195 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:48:57,196 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:48:57,199 - -7.881 per-word bound, 235.8 perplexity estimate based on a held-out corpus of 1 documents with 1737 words
+2024-11-18 09:48:57,199 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:48:57,200 - topic #0 (0.333): 0.013*"’" + 0.011*"needs" + 0.007*"progress" + 0.006*"Peterborough" + 0.005*"supported" + 0.005*"need" + 0.005*"well" + 0.005*"2023" + 0.005*"November" + 0.005*"27"
+2024-11-18 09:48:57,200 - topic #1 (0.333): 0.018*"’" + 0.016*"needs" + 0.009*"need" + 0.009*"Peterborough" + 0.007*"well" + 0.007*"2023" + 0.006*"progress" + 0.006*"plans" + 0.006*"8" + 0.006*"receive"
+2024-11-18 09:48:57,200 - topic #2 (0.333): 0.011*"needs" + 0.010*"’" + 0.006*"2023" + 0.005*"need" + 0.005*"supported" + 0.005*"well" + 0.005*"plans" + 0.004*"Peterborough" + 0.004*"November" + 0.004*"27"
+2024-11-18 09:48:57,200 - topic diff=0.753938, rho=1.000000
+2024-11-18 09:48:57,200 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=893, num_topics=3, decay=0.5, chunksize=2000> in 0.00s', 'datetime': '2024-11-18T09:48:57.200901', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:48:58,083 - Inspection date 2023-11-27 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:48:58,083 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:58,083 - Inspection date 2023-11-27 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:48:58,083 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:58,084 - Inspection date 2023-11-27 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:48:58,084 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:58,084 - Inspection date 2023-11-27 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:48:58,084 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:58,084 - Inspection date 2023-11-27 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:48:58,084 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:48:58,084 - Inspection date 2023-11-27 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:48:58,084 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:49:11,016 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:49:11,019 - built Dictionary<1232 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2905 corpus positions)
+2024-11-18 09:49:11,019 - Dictionary lifecycle event {'msg': "built Dictionary<1232 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2905 corpus positions)", 'datetime': '2024-11-18T09:49:11.019301', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:49:11,020 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:49:11,020 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:49:11,020 - using serial LDA version on this node
+2024-11-18 09:49:11,021 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:49:11,021 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:49:11,025 - -8.085 per-word bound, 271.5 perplexity estimate based on a held-out corpus of 1 documents with 2905 words
+2024-11-18 09:49:11,025 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:49:11,026 - topic #0 (0.333): 0.010*"needs" + 0.008*"’" + 0.007*"well" + 0.006*"Plymouth" + 0.005*"practice" + 0.005*"timely" + 0.005*"plans" + 0.005*"22" + 0.005*"2024" + 0.005*"2"
+2024-11-18 09:49:11,026 - topic #1 (0.333): 0.015*"’" + 0.008*"needs" + 0.006*"Plymouth" + 0.006*"well" + 0.005*"plans" + 0.004*"February" + 0.004*"2" + 0.004*"practice" + 0.004*"effective" + 0.004*"Council"
+2024-11-18 09:49:11,026 - topic #2 (0.333): 0.016*"’" + 0.008*"well" + 0.008*"needs" + 0.007*"Plymouth" + 0.006*"practice" + 0.005*"education" + 0.005*"good" + 0.005*"appropriate" + 0.005*"City" + 0.004*"risks"
+2024-11-18 09:49:11,026 - topic diff=0.834936, rho=1.000000
+2024-11-18 09:49:11,027 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1232, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:49:11.027037', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:49:11,886 - Inspection date 2024-01-22 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:49:11,886 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:49:11,886 - Inspection date 2024-01-22 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:49:11,886 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:49:11,886 - Inspection date 2024-01-22 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:49:11,886 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:49:11,887 - Inspection date 2024-01-22 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:49:11,887 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:49:11,887 - Inspection date 2024-01-22 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:49:11,887 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:49:11,887 - Inspection date 2024-01-22 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:49:11,887 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:49:23,680 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:49:23,683 - built Dictionary<1223 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2738 corpus positions)
+2024-11-18 09:49:23,683 - Dictionary lifecycle event {'msg': "built Dictionary<1223 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2738 corpus positions)", 'datetime': '2024-11-18T09:49:23.683258', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:49:23,684 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:49:23,684 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:49:23,684 - using serial LDA version on this node
+2024-11-18 09:49:23,685 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:49:23,685 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:49:23,691 - -8.107 per-word bound, 275.7 perplexity estimate based on a held-out corpus of 1 documents with 2738 words
+2024-11-18 09:49:23,691 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:49:23,692 - topic #0 (0.333): 0.019*"’" + 0.008*"care-experienced" + 0.007*"well" + 0.007*"needs" + 0.006*"Portsmouth" + 0.005*"health" + 0.005*"practice" + 0.005*"plans" + 0.005*"need" + 0.005*"family"
+2024-11-18 09:49:23,693 - topic #1 (0.333): 0.017*"’" + 0.009*"care-experienced" + 0.007*"well" + 0.007*"Portsmouth" + 0.007*"needs" + 0.006*"family" + 0.006*"plans" + 0.004*"carers" + 0.004*"need" + 0.004*"health"
+2024-11-18 09:49:23,693 - topic #2 (0.333): 0.014*"’" + 0.007*"care-experienced" + 0.007*"Portsmouth" + 0.007*"needs" + 0.006*"well" + 0.006*"family" + 0.006*"health" + 0.005*"plans" + 0.005*"leaders" + 0.004*"19"
+2024-11-18 09:49:23,693 - topic diff=0.793069, rho=1.000000
+2024-11-18 09:49:23,693 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1223, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:49:23.693505', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:49:24,928 - Inspection date 2023-05-15 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:49:24,928 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:49:24,928 - Inspection date 2023-05-15 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:49:24,929 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:49:24,929 - Inspection date 2023-05-15 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:49:24,929 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:49:24,929 - Inspection date 2023-05-15 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:49:24,929 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:49:24,929 - Inspection date 2023-05-15 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:49:24,929 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:49:24,929 - Inspection date 2023-05-15 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:49:24,929 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:49:35,565 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:49:35,567 - built Dictionary<1231 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2562 corpus positions)
+2024-11-18 09:49:35,567 - Dictionary lifecycle event {'msg': "built Dictionary<1231 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2562 corpus positions)", 'datetime': '2024-11-18T09:49:35.567857', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:49:35,569 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:49:35,569 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:49:35,569 - using serial LDA version on this node
+2024-11-18 09:49:35,569 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:49:35,569 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:49:35,573 - -8.157 per-word bound, 285.4 perplexity estimate based on a held-out corpus of 1 documents with 2562 words
+2024-11-18 09:49:35,573 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:49:35,575 - topic #0 (0.333): 0.013*"’" + 0.009*"needs" + 0.006*"PAs" + 0.005*"progress" + 0.005*"well" + 0.005*"clear" + 0.004*"22" + 0.004*"plans" + 0.004*"Reading" + 0.004*"timely"
+2024-11-18 09:49:35,575 - topic #1 (0.333): 0.017*"’" + 0.005*"well" + 0.005*"plans" + 0.005*"Reading" + 0.005*"PAs" + 0.005*"arrangements" + 0.004*"practice" + 0.004*"needs" + 0.004*"progress" + 0.004*"3"
+2024-11-18 09:49:35,575 - topic #2 (0.333): 0.011*"’" + 0.006*"needs" + 0.005*"PAs" + 0.005*"plans" + 0.005*"progress" + 0.004*"Reading" + 0.004*"3" + 0.004*"well" + 0.004*"May" + 0.004*"clear"
+2024-11-18 09:49:35,575 - topic diff=0.761758, rho=1.000000
+2024-11-18 09:49:35,575 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1231, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:49:35.575533', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:49:36,411 - Inspection date 2024-04-22 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:49:36,411 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:49:36,411 - Inspection date 2024-04-22 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:49:36,412 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:49:36,412 - Inspection date 2024-04-22 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:49:36,412 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:49:36,412 - Inspection date 2024-04-22 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:49:36,412 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:49:36,412 - Inspection date 2024-04-22 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:49:36,412 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:49:36,413 - Inspection date 2024-04-22 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:49:36,413 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:49:46,563 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:49:46,565 - built Dictionary<1112 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2515 corpus positions)
+2024-11-18 09:49:46,566 - Dictionary lifecycle event {'msg': "built Dictionary<1112 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2515 corpus positions)", 'datetime': '2024-11-18T09:49:46.566143', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:49:46,567 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:49:46,567 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:49:46,567 - using serial LDA version on this node
+2024-11-18 09:49:46,567 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:49:46,567 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:49:46,571 - -8.005 per-word bound, 256.9 perplexity estimate based on a held-out corpus of 1 documents with 2515 words
+2024-11-18 09:49:46,571 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:49:46,572 - topic #0 (0.333): 0.017*"’" + 0.006*"leaders" + 0.006*"needs" + 0.006*"consistently" + 0.005*"Redcar" + 0.005*"20" + 0.005*"However" + 0.005*"Cleveland" + 0.005*"practice" + 0.005*"plans"
+2024-11-18 09:49:46,573 - topic #1 (0.333): 0.014*"’" + 0.006*"plans" + 0.005*"consistently" + 0.005*"needs" + 0.005*"July" + 0.005*"However" + 0.005*"2022" + 0.004*"practice" + 0.004*"leaders" + 0.004*"ensure"
+2024-11-18 09:49:46,573 - topic #2 (0.333): 0.020*"’" + 0.007*"leaders" + 0.006*"However" + 0.005*"plans" + 0.005*"carers" + 0.005*"needs" + 0.005*"2022" + 0.005*"20" + 0.005*"practice" + 0.004*"consistently"
+2024-11-18 09:49:46,573 - topic diff=0.799674, rho=1.000000
+2024-11-18 09:49:46,573 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1112, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:49:46.573533', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:49:47,456 - Inspection date None / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:49:47,456 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:49:47,457 - Inspection date None / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:49:47,457 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:49:47,457 - Inspection date None / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:49:47,457 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:49:47,457 - Inspection date None / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:49:47,457 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:49:47,457 - Inspection date None / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:49:47,457 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:49:47,457 - Inspection date None / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:49:47,457 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:49:59,292 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:49:59,294 - built Dictionary<1150 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2656 corpus positions)
+2024-11-18 09:49:59,294 - Dictionary lifecycle event {'msg': "built Dictionary<1150 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2656 corpus positions)", 'datetime': '2024-11-18T09:49:59.294924', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:49:59,296 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:49:59,296 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:49:59,296 - using serial LDA version on this node
+2024-11-18 09:49:59,296 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:49:59,296 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:49:59,300 - -8.032 per-word bound, 261.8 perplexity estimate based on a held-out corpus of 1 documents with 2656 words
+2024-11-18 09:49:59,300 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:49:59,301 - topic #0 (0.333): 0.020*"’" + 0.010*"experienced" + 0.007*"needs" + 0.007*"practice" + 0.006*"response" + 0.006*"consistently" + 0.005*"good" + 0.005*"quality" + 0.005*"plans" + 0.005*"PAs"
+2024-11-18 09:49:59,302 - topic #1 (0.333): 0.019*"’" + 0.009*"needs" + 0.008*"practice" + 0.007*"experienced" + 0.007*"plans" + 0.006*"response" + 0.005*"well" + 0.005*"good" + 0.005*"3" + 0.004*"quality"
+2024-11-18 09:49:59,302 - topic #2 (0.333): 0.021*"’" + 0.011*"experienced" + 0.008*"practice" + 0.007*"needs" + 0.007*"Rochdale" + 0.006*"plans" + 0.006*"consistently" + 0.005*"quality" + 0.005*"response" + 0.005*"progress"
+2024-11-18 09:49:59,302 - topic diff=0.820053, rho=1.000000
+2024-11-18 09:49:59,302 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1150, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:49:59.302409', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:50:00,193 - Inspection date 2023-01-23 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:50:00,193 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:00,193 - Inspection date 2023-01-23 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:50:00,193 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:00,194 - Inspection date 2023-01-23 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:50:00,194 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:00,194 - Inspection date 2023-01-23 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:50:00,194 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:00,194 - Inspection date 2023-01-23 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:50:00,194 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:00,194 - Inspection date 2023-01-23 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:50:00,194 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:11,031 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:50:11,033 - built Dictionary<1127 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2366 corpus positions)
+2024-11-18 09:50:11,033 - Dictionary lifecycle event {'msg': "built Dictionary<1127 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2366 corpus positions)", 'datetime': '2024-11-18T09:50:11.033427', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:50:11,034 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:50:11,034 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:50:11,034 - using serial LDA version on this node
+2024-11-18 09:50:11,035 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:50:11,035 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:50:11,038 - -8.070 per-word bound, 268.7 perplexity estimate based on a held-out corpus of 1 documents with 2366 words
+2024-11-18 09:50:11,038 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:50:11,040 - topic #0 (0.333): 0.013*"’" + 0.009*"Rotherham" + 0.007*"needs" + 0.005*"good" + 0.005*"well" + 0.005*"ensure" + 0.004*"Council" + 0.004*"27" + 0.004*"clear" + 0.004*"However"
+2024-11-18 09:50:11,040 - topic #1 (0.333): 0.021*"’" + 0.009*"Rotherham" + 0.006*"needs" + 0.006*"well" + 0.005*"plans" + 0.005*"However" + 0.005*"Council" + 0.004*"clear" + 0.004*"ensure" + 0.004*"1"
+2024-11-18 09:50:11,040 - topic #2 (0.333): 0.009*"’" + 0.007*"Rotherham" + 0.006*"good" + 0.006*"needs" + 0.005*"ensure" + 0.005*"Council" + 0.004*"well" + 0.004*"However" + 0.004*"plans" + 0.004*"2022"
+2024-11-18 09:50:11,040 - topic diff=0.773612, rho=1.000000
+2024-11-18 09:50:11,040 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1127, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:50:11.040735', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:50:11,857 - Inspection date 2022-06-27 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:50:11,857 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:11,858 - Inspection date 2022-06-27 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:50:11,858 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:11,858 - Inspection date 2022-06-27 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:50:11,858 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:11,858 - Inspection date 2022-06-27 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:50:11,858 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:11,858 - Inspection date 2022-06-27 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:50:11,858 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:11,858 - Inspection date 2022-06-27 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:50:11,858 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:21,788 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:50:21,790 - built Dictionary<1119 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2380 corpus positions)
+2024-11-18 09:50:21,790 - Dictionary lifecycle event {'msg': "built Dictionary<1119 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2380 corpus positions)", 'datetime': '2024-11-18T09:50:21.790645', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:50:21,791 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:50:21,791 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:50:21,791 - using serial LDA version on this node
+2024-11-18 09:50:21,792 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:50:21,792 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:50:21,795 - -8.044 per-word bound, 263.9 perplexity estimate based on a held-out corpus of 1 documents with 2380 words
+2024-11-18 09:50:21,796 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:50:21,797 - topic #0 (0.333): 0.010*"well" + 0.008*"practice" + 0.008*"’" + 0.005*"highly" + 0.005*"strong" + 0.004*"needs" + 0.004*"effective" + 0.004*"high" + 0.004*"improve" + 0.004*"ensure"
+2024-11-18 09:50:21,797 - topic #1 (0.333): 0.015*"well" + 0.012*"’" + 0.011*"practice" + 0.008*"highly" + 0.006*"strong" + 0.006*"needs" + 0.006*"effective" + 0.005*"range" + 0.005*"leaders" + 0.004*"need"
+2024-11-18 09:50:21,797 - topic #2 (0.333): 0.013*"well" + 0.013*"’" + 0.011*"practice" + 0.008*"highly" + 0.007*"strong" + 0.006*"leaders" + 0.005*"needs" + 0.005*"high" + 0.005*"professionals" + 0.004*"effective"
+2024-11-18 09:50:21,797 - topic diff=0.784319, rho=1.000000
+2024-11-18 09:50:21,797 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1119, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:50:21.797811', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:50:22,654 - Inspection date 2019-09-09 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:50:22,654 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:22,654 - Inspection date 2019-09-09 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:50:22,655 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:22,655 - Inspection date 2019-09-09 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:50:22,655 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:22,655 - Inspection date 2019-09-09 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:50:22,655 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:22,655 - Inspection date 2019-09-09 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:50:22,655 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:22,655 - Inspection date 2019-09-09 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:50:22,656 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:32,530 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:50:32,532 - built Dictionary<1107 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2257 corpus positions)
+2024-11-18 09:50:32,532 - Dictionary lifecycle event {'msg': "built Dictionary<1107 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2257 corpus positions)", 'datetime': '2024-11-18T09:50:32.532923', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:50:32,533 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:50:32,534 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:50:32,534 - using serial LDA version on this node
+2024-11-18 09:50:32,534 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:50:32,534 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:50:32,538 - -8.063 per-word bound, 267.4 perplexity estimate based on a held-out corpus of 1 documents with 2257 words
+2024-11-18 09:50:32,538 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:50:32,539 - topic #0 (0.333): 0.012*"’" + 0.009*"plans" + 0.008*"well" + 0.008*"needs" + 0.005*"effective" + 0.005*"supported" + 0.004*"practice" + 0.004*"clear" + 0.004*"risk" + 0.004*"need"
+2024-11-18 09:50:32,539 - topic #1 (0.333): 0.015*"’" + 0.010*"well" + 0.009*"plans" + 0.008*"needs" + 0.006*"good" + 0.005*"practice" + 0.005*"need" + 0.005*"effective" + 0.004*"risk" + 0.004*"Kingston"
+2024-11-18 09:50:32,539 - topic #2 (0.333): 0.013*"’" + 0.009*"well" + 0.006*"needs" + 0.006*"plans" + 0.005*"good" + 0.005*"clear" + 0.004*"appropriate" + 0.004*"supported" + 0.004*"parents" + 0.004*"effective"
+2024-11-18 09:50:32,540 - topic diff=0.749204, rho=1.000000
+2024-11-18 09:50:32,540 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1107, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:50:32.540162', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:50:33,522 - Inspection date 2019-10-21 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:50:33,523 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:33,523 - Inspection date 2019-10-21 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:50:33,523 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:33,523 - Inspection date 2019-10-21 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:50:33,523 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:33,523 - Inspection date 2019-10-21 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:50:33,523 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:33,524 - Inspection date 2019-10-21 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:50:33,524 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:33,524 - Inspection date 2019-10-21 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:50:33,524 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:43,119 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:50:43,121 - built Dictionary<1109 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2088 corpus positions)
+2024-11-18 09:50:43,121 - Dictionary lifecycle event {'msg': "built Dictionary<1109 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2088 corpus positions)", 'datetime': '2024-11-18T09:50:43.121349', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:50:43,122 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:50:43,122 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:50:43,122 - using serial LDA version on this node
+2024-11-18 09:50:43,123 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:50:43,123 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:50:43,126 - -8.120 per-word bound, 278.3 perplexity estimate based on a held-out corpus of 1 documents with 2088 words
+2024-11-18 09:50:43,126 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:50:43,127 - topic #0 (0.333): 0.010*"’" + 0.006*"quality" + 0.004*"well" + 0.004*"always" + 0.004*"information" + 0.004*"needs" + 0.004*"benefit" + 0.004*"plans" + 0.004*"health" + 0.004*"education"
+2024-11-18 09:50:43,128 - topic #1 (0.333): 0.011*"’" + 0.007*"well" + 0.005*"needs" + 0.005*"plans" + 0.004*"information" + 0.004*"However" + 0.004*"actions" + 0.004*"effective" + 0.004*"quality" + 0.004*"use"
+2024-11-18 09:50:43,128 - topic #2 (0.333): 0.014*"’" + 0.005*"needs" + 0.005*"quality" + 0.005*"plans" + 0.005*"well" + 0.004*"effective" + 0.004*"use" + 0.004*"benefit" + 0.004*"early" + 0.004*"good"
+2024-11-18 09:50:43,128 - topic diff=0.717769, rho=1.000000
+2024-11-18 09:50:43,128 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1109, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:50:43.128530', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:50:44,278 - Inspection date 2020-01-13 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:50:44,278 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:44,278 - Inspection date 2020-01-13 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:50:44,279 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:44,279 - Inspection date 2020-01-13 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:50:44,279 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:44,279 - Inspection date 2020-01-13 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:50:44,279 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:44,279 - Inspection date 2020-01-13 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:50:44,279 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:44,279 - Inspection date 2020-01-13 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:50:44,279 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:54,679 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:50:54,681 - built Dictionary<1089 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2211 corpus positions)
+2024-11-18 09:50:54,681 - Dictionary lifecycle event {'msg': "built Dictionary<1089 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2211 corpus positions)", 'datetime': '2024-11-18T09:50:54.681461', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:50:54,682 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:50:54,682 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:50:54,682 - using serial LDA version on this node
+2024-11-18 09:50:54,683 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:50:54,683 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:50:54,686 - -8.048 per-word bound, 264.7 perplexity estimate based on a held-out corpus of 1 documents with 2211 words
+2024-11-18 09:50:54,686 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:50:54,688 - topic #0 (0.333): 0.013*"’" + 0.006*"Rutland" + 0.006*"needs" + 0.006*"effective" + 0.005*"practice" + 0.005*"impact" + 0.004*"need" + 0.004*"positive" + 0.004*"2024" + 0.004*"ensure"
+2024-11-18 09:50:54,688 - topic #1 (0.333): 0.020*"’" + 0.009*"Rutland" + 0.008*"needs" + 0.006*"effective" + 0.006*"positive" + 0.005*"impact" + 0.005*"plans" + 0.005*"practitioners" + 0.005*"need" + 0.005*"good"
+2024-11-18 09:50:54,688 - topic #2 (0.333): 0.021*"’" + 0.010*"Rutland" + 0.008*"needs" + 0.008*"impact" + 0.007*"effective" + 0.006*"need" + 0.006*"plans" + 0.005*"positive" + 0.005*"good" + 0.005*"well"
+2024-11-18 09:50:54,688 - topic diff=0.775918, rho=1.000000
+2024-11-18 09:50:54,688 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1089, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:50:54.688555', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:50:55,579 - Inspection date 2024-04-15 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:50:55,580 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:55,580 - Inspection date 2024-04-15 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:50:55,580 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:55,580 - Inspection date 2024-04-15 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:50:55,580 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:55,580 - Inspection date 2024-04-15 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:50:55,580 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:55,581 - Inspection date 2024-04-15 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:50:55,581 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:50:55,581 - Inspection date 2024-04-15 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:50:55,581 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:06,122 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:51:06,124 - built Dictionary<1069 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2253 corpus positions)
+2024-11-18 09:51:06,124 - Dictionary lifecycle event {'msg': "built Dictionary<1069 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2253 corpus positions)", 'datetime': '2024-11-18T09:51:06.124375', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:51:06,125 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:51:06,125 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:51:06,125 - using serial LDA version on this node
+2024-11-18 09:51:06,126 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:51:06,126 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:51:06,129 - -8.008 per-word bound, 257.4 perplexity estimate based on a held-out corpus of 1 documents with 2253 words
+2024-11-18 09:51:06,129 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:51:06,130 - topic #0 (0.333): 0.019*"’" + 0.009*"needs" + 0.008*"well" + 0.007*"plans" + 0.006*"effective" + 0.006*"Salford" + 0.005*"leaders" + 0.005*"10" + 0.005*"experiences" + 0.005*"quality"
+2024-11-18 09:51:06,131 - topic #1 (0.333): 0.006*"’" + 0.006*"plans" + 0.006*"needs" + 0.005*"Salford" + 0.005*"planning" + 0.005*"effective" + 0.005*"well" + 0.005*"ensure" + 0.004*"experiences" + 0.004*"leaders"
+2024-11-18 09:51:06,131 - topic #2 (0.333): 0.013*"’" + 0.009*"plans" + 0.007*"effective" + 0.007*"well" + 0.006*"needs" + 0.006*"practice" + 0.006*"Salford" + 0.005*"planning" + 0.005*"progress" + 0.005*"6"
+2024-11-18 09:51:06,131 - topic diff=0.793537, rho=1.000000
+2024-11-18 09:51:06,131 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1069, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:51:06.131382', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:51:06,928 - Inspection date 2023-11-06 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:51:06,928 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:06,928 - Inspection date 2023-11-06 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:51:06,929 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:06,929 - Inspection date 2023-11-06 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:51:06,929 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:06,929 - Inspection date 2023-11-06 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:51:06,929 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:06,929 - Inspection date 2023-11-06 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:51:06,929 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:06,929 - Inspection date 2023-11-06 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:51:06,929 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:16,246 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:51:16,248 - built Dictionary<995 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2066 corpus positions)
+2024-11-18 09:51:16,248 - Dictionary lifecycle event {'msg': "built Dictionary<995 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2066 corpus positions)", 'datetime': '2024-11-18T09:51:16.248731', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:51:16,249 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:51:16,249 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:51:16,250 - using serial LDA version on this node
+2024-11-18 09:51:16,250 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:51:16,250 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:51:16,253 - -7.942 per-word bound, 246.0 perplexity estimate based on a held-out corpus of 1 documents with 2066 words
+2024-11-18 09:51:16,253 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:51:16,255 - topic #0 (0.333): 0.012*"’" + 0.007*"plans" + 0.007*"Sandwell" + 0.006*"well" + 0.006*"needs" + 0.005*"9" + 0.005*"20" + 0.005*"quality" + 0.004*"receive" + 0.004*"Trust"
+2024-11-18 09:51:16,255 - topic #1 (0.333): 0.013*"’" + 0.009*"needs" + 0.007*"well" + 0.007*"Sandwell" + 0.007*"plans" + 0.006*"quality" + 0.005*"number" + 0.004*"Trust" + 0.004*"changes" + 0.004*"good"
+2024-11-18 09:51:16,255 - topic #2 (0.333): 0.016*"’" + 0.008*"needs" + 0.008*"Sandwell" + 0.007*"plans" + 0.006*"well" + 0.005*"quality" + 0.005*"Trust" + 0.005*"number" + 0.005*"education" + 0.005*"training"
+2024-11-18 09:51:16,255 - topic diff=0.760369, rho=1.000000
+2024-11-18 09:51:16,255 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=995, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:51:16.255692', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:51:17,038 - Inspection date 2022-05-09 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:51:17,038 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:17,038 - Inspection date 2022-05-09 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:51:17,038 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:17,039 - Inspection date 2022-05-09 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:51:17,039 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:17,039 - Inspection date 2022-05-09 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:51:17,039 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:17,039 - Inspection date 2022-05-09 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:51:17,039 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:17,039 - Inspection date 2022-05-09 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:51:17,039 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:27,094 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:51:27,096 - built Dictionary<1023 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2300 corpus positions)
+2024-11-18 09:51:27,097 - Dictionary lifecycle event {'msg': "built Dictionary<1023 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2300 corpus positions)", 'datetime': '2024-11-18T09:51:27.097000', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:51:27,097 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:51:27,098 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:51:27,098 - using serial LDA version on this node
+2024-11-18 09:51:27,098 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:51:27,098 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:51:27,102 - -7.927 per-word bound, 243.4 perplexity estimate based on a held-out corpus of 1 documents with 2300 words
+2024-11-18 09:51:27,102 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:51:27,103 - topic #0 (0.333): 0.010*"’" + 0.009*"needs" + 0.007*"practice" + 0.005*"many" + 0.005*"lack" + 0.004*"management" + 0.004*"oversight" + 0.004*"protection" + 0.004*"including" + 0.004*"◼"
+2024-11-18 09:51:27,103 - topic #1 (0.333): 0.019*"’" + 0.009*"needs" + 0.007*"oversight" + 0.006*"including" + 0.006*"practice" + 0.005*"timely" + 0.005*"protection" + 0.005*"need" + 0.005*"lack" + 0.005*"management"
+2024-11-18 09:51:27,103 - topic #2 (0.333): 0.017*"’" + 0.010*"needs" + 0.006*"practice" + 0.005*"plans" + 0.005*"21" + 0.005*"many" + 0.005*"March" + 0.005*"Sefton" + 0.005*"protection" + 0.005*"◼"
+2024-11-18 09:51:27,103 - topic diff=0.792075, rho=1.000000
+2024-11-18 09:51:27,104 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1023, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:51:27.103993', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:51:27,958 - Inspection date 2022-02-21 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:51:27,959 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:27,959 - Inspection date 2022-02-21 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:51:27,959 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:27,959 - Inspection date 2022-02-21 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:51:27,959 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:27,959 - Inspection date 2022-02-21 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:51:27,959 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:27,959 - Inspection date 2022-02-21 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:51:27,959 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:27,960 - Inspection date 2022-02-21 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:51:27,960 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:38,707 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:51:38,709 - built Dictionary<1124 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2327 corpus positions)
+2024-11-18 09:51:38,709 - Dictionary lifecycle event {'msg': "built Dictionary<1124 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2327 corpus positions)", 'datetime': '2024-11-18T09:51:38.709583', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:51:38,710 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:51:38,710 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:51:38,710 - using serial LDA version on this node
+2024-11-18 09:51:38,711 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:51:38,711 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:51:38,714 - -8.070 per-word bound, 268.7 perplexity estimate based on a held-out corpus of 1 documents with 2327 words
+2024-11-18 09:51:38,715 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:51:38,716 - topic #0 (0.333): 0.018*"’" + 0.011*"Sheffield" + 0.007*"needs" + 0.006*"well" + 0.006*"leaders" + 0.005*"practice" + 0.005*"health" + 0.004*"adviser" + 0.004*"good" + 0.004*"experiences"
+2024-11-18 09:51:38,716 - topic #1 (0.333): 0.021*"’" + 0.009*"needs" + 0.009*"Sheffield" + 0.008*"well" + 0.006*"leaders" + 0.005*"practice" + 0.005*"health" + 0.005*"mental" + 0.004*"plans" + 0.004*"11"
+2024-11-18 09:51:38,716 - topic #2 (0.333): 0.021*"’" + 0.013*"Sheffield" + 0.009*"needs" + 0.007*"practice" + 0.006*"well" + 0.006*"health" + 0.005*"leaders" + 0.005*"quality" + 0.005*"effective" + 0.005*"11"
+2024-11-18 09:51:38,716 - topic diff=0.769436, rho=1.000000
+2024-11-18 09:51:38,716 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1124, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:51:38.716892', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:51:39,528 - Inspection date 2023-09-11 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:51:39,528 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:39,528 - Inspection date 2023-09-11 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:51:39,528 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:39,528 - Inspection date 2023-09-11 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:51:39,528 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:39,529 - Inspection date 2023-09-11 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:51:39,529 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:39,529 - Inspection date 2023-09-11 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:51:39,529 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:39,529 - Inspection date 2023-09-11 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:51:39,529 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:47,262 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:51:47,264 - built Dictionary<939 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1749 corpus positions)
+2024-11-18 09:51:47,264 - Dictionary lifecycle event {'msg': "built Dictionary<939 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 1749 corpus positions)", 'datetime': '2024-11-18T09:51:47.264627', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:51:47,265 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:51:47,265 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:51:47,265 - using serial LDA version on this node
+2024-11-18 09:51:47,266 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:51:47,266 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:51:47,269 - -7.964 per-word bound, 249.7 perplexity estimate based on a held-out corpus of 1 documents with 1749 words
+2024-11-18 09:51:47,269 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:51:47,270 - topic #0 (0.333): 0.019*"’" + 0.009*"needs" + 0.007*"well" + 0.007*"Shropshire" + 0.005*"2022" + 0.005*"making" + 0.005*"progress" + 0.005*"plans" + 0.004*"training" + 0.004*"effectively"
+2024-11-18 09:51:47,270 - topic #1 (0.333): 0.015*"’" + 0.007*"Shropshire" + 0.007*"well" + 0.007*"needs" + 0.005*"progress" + 0.005*"plans" + 0.005*"making" + 0.005*"7" + 0.005*"2022" + 0.004*"leaders"
+2024-11-18 09:51:47,270 - topic #2 (0.333): 0.018*"’" + 0.009*"needs" + 0.006*"Shropshire" + 0.006*"progress" + 0.006*"well" + 0.006*"plans" + 0.005*"7" + 0.004*"2022" + 0.004*"making" + 0.004*"effective"
+2024-11-18 09:51:47,270 - topic diff=0.714648, rho=1.000000
+2024-11-18 09:51:47,271 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=939, num_topics=3, decay=0.5, chunksize=2000> in 0.00s', 'datetime': '2024-11-18T09:51:47.271079', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:51:48,069 - Inspection date 2022-02-07 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:51:48,070 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:48,070 - Inspection date 2022-02-07 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:51:48,070 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:48,070 - Inspection date 2022-02-07 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:51:48,070 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:48,070 - Inspection date 2022-02-07 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:51:48,070 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:48,070 - Inspection date 2022-02-07 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:51:48,070 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:48,071 - Inspection date 2022-02-07 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:51:48,071 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:58,932 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:51:58,934 - built Dictionary<1113 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2352 corpus positions)
+2024-11-18 09:51:58,934 - Dictionary lifecycle event {'msg': "built Dictionary<1113 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2352 corpus positions)", 'datetime': '2024-11-18T09:51:58.934967', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:51:58,936 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:51:58,936 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:51:58,936 - using serial LDA version on this node
+2024-11-18 09:51:58,936 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:51:58,936 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:51:58,940 - -8.044 per-word bound, 264.0 perplexity estimate based on a held-out corpus of 1 documents with 2352 words
+2024-11-18 09:51:58,940 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:51:58,941 - topic #0 (0.333): 0.011*"’" + 0.008*"Slough" + 0.006*"plans" + 0.006*"needs" + 0.005*"practice" + 0.005*"However" + 0.005*"3" + 0.004*"senior" + 0.004*"leaders" + 0.004*"quality"
+2024-11-18 09:51:58,941 - topic #1 (0.333): 0.021*"’" + 0.008*"quality" + 0.008*"Slough" + 0.007*"plans" + 0.006*"practice" + 0.006*"needs" + 0.005*"impact" + 0.005*"need" + 0.005*"supported" + 0.005*"leaders"
+2024-11-18 09:51:58,941 - topic #2 (0.333): 0.012*"’" + 0.008*"Slough" + 0.006*"needs" + 0.005*"plans" + 0.005*"However" + 0.005*"3" + 0.005*"quality" + 0.005*"impact" + 0.005*"practice" + 0.005*"2023"
+2024-11-18 09:51:58,941 - topic diff=0.791884, rho=1.000000
+2024-11-18 09:51:58,942 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1113, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:51:58.942076', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:51:59,785 - Inspection date 2023-01-23 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:51:59,785 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:59,786 - Inspection date 2023-01-23 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:51:59,786 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:59,786 - Inspection date 2023-01-23 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:51:59,786 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:59,786 - Inspection date 2023-01-23 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:51:59,786 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:59,786 - Inspection date 2023-01-23 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:51:59,786 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:51:59,786 - Inspection date 2023-01-23 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:51:59,786 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:09,987 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:52:09,989 - built Dictionary<996 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2163 corpus positions)
+2024-11-18 09:52:09,989 - Dictionary lifecycle event {'msg': "built Dictionary<996 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2163 corpus positions)", 'datetime': '2024-11-18T09:52:09.989751', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:52:09,990 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:52:09,990 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:52:09,991 - using serial LDA version on this node
+2024-11-18 09:52:09,991 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:52:09,991 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:52:09,994 - -7.921 per-word bound, 242.3 perplexity estimate based on a held-out corpus of 1 documents with 2163 words
+2024-11-18 09:52:09,994 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:52:09,995 - topic #0 (0.333): 0.011*"lack" + 0.011*"’" + 0.007*"2022" + 0.006*"Solihull" + 0.006*"quality" + 0.006*"risk" + 0.005*"need" + 0.005*"practice" + 0.004*"significant" + 0.004*"experiences"
+2024-11-18 09:52:09,996 - topic #1 (0.333): 0.015*"’" + 0.010*"2022" + 0.009*"lack" + 0.007*"need" + 0.006*"Solihull" + 0.006*"risk" + 0.006*"significant" + 0.005*"delay" + 0.005*"quality" + 0.005*"practice"
+2024-11-18 09:52:09,996 - topic #2 (0.333): 0.018*"’" + 0.012*"lack" + 0.008*"2022" + 0.006*"Solihull" + 0.006*"need" + 0.005*"effective" + 0.005*"risk" + 0.005*"quality" + 0.005*"experiences" + 0.005*"practice"
+2024-11-18 09:52:09,996 - topic diff=0.793787, rho=1.000000
+2024-11-18 09:52:09,996 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=996, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:52:09.996407', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:52:10,875 - Inspection date 2022-10-31 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:52:10,875 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:10,875 - Inspection date 2022-10-31 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:52:10,875 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:10,875 - Inspection date 2022-10-31 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:52:10,875 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:10,875 - Inspection date 2022-10-31 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:52:10,876 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:10,876 - Inspection date 2022-10-31 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:52:10,876 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:10,876 - Inspection date 2022-10-31 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:52:10,876 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:20,492 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:52:20,494 - built Dictionary<1000 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2181 corpus positions)
+2024-11-18 09:52:20,494 - Dictionary lifecycle event {'msg': "built Dictionary<1000 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2181 corpus positions)", 'datetime': '2024-11-18T09:52:20.494550', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:52:20,495 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:52:20,495 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:52:20,495 - using serial LDA version on this node
+2024-11-18 09:52:20,496 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:52:20,496 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:52:20,499 - -7.917 per-word bound, 241.7 perplexity estimate based on a held-out corpus of 1 documents with 2181 words
+2024-11-18 09:52:20,499 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:52:20,500 - topic #0 (0.333): 0.017*"’" + 0.008*"well" + 0.007*"needs" + 0.007*"plans" + 0.006*"Somerset" + 0.006*"number" + 0.005*"need" + 0.005*"including" + 0.005*"good" + 0.005*"leaders"
+2024-11-18 09:52:20,500 - topic #1 (0.333): 0.018*"’" + 0.009*"needs" + 0.009*"well" + 0.006*"Somerset" + 0.006*"good" + 0.006*"plans" + 0.006*"leaders" + 0.005*"progress" + 0.005*"supported" + 0.005*"positive"
+2024-11-18 09:52:20,501 - topic #2 (0.333): 0.016*"’" + 0.010*"well" + 0.008*"needs" + 0.007*"Somerset" + 0.006*"good" + 0.006*"supported" + 0.006*"plans" + 0.005*"2022" + 0.005*"practice" + 0.005*"leaders"
+2024-11-18 09:52:20,501 - topic diff=0.802025, rho=1.000000
+2024-11-18 09:52:20,501 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1000, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:52:20.501313', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:52:21,341 - Inspection date 2022-07-18 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:52:21,341 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:21,341 - Inspection date 2022-07-18 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:52:21,341 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:21,342 - Inspection date 2022-07-18 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:52:21,342 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:21,342 - Inspection date 2022-07-18 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:52:21,342 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:21,342 - Inspection date 2022-07-18 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:52:21,342 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:21,342 - Inspection date 2022-07-18 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:52:21,342 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:32,790 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:52:32,792 - built Dictionary<1188 unique tokens: ['0', '0161', '0300', '1', '10']...> from 1 documents (total 2751 corpus positions)
+2024-11-18 09:52:32,792 - Dictionary lifecycle event {'msg': "built Dictionary<1188 unique tokens: ['0', '0161', '0300', '1', '10']...> from 1 documents (total 2751 corpus positions)", 'datetime': '2024-11-18T09:52:32.792697', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:52:32,793 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:52:32,794 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:52:32,794 - using serial LDA version on this node
+2024-11-18 09:52:32,794 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:52:32,794 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:52:32,798 - -8.056 per-word bound, 266.1 perplexity estimate based on a held-out corpus of 1 documents with 2751 words
+2024-11-18 09:52:32,798 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:52:32,799 - topic #0 (0.333): 0.016*"’" + 0.012*"needs" + 0.007*"2024" + 0.007*"June" + 0.006*"leaders" + 0.006*"well" + 0.006*"ensure" + 0.005*"effective" + 0.005*"understand" + 0.005*"3"
+2024-11-18 09:52:32,800 - topic #1 (0.333): 0.020*"’" + 0.009*"needs" + 0.007*"2024" + 0.006*"June" + 0.006*"understand" + 0.006*"leaders" + 0.006*"plans" + 0.005*"effective" + 0.005*"well" + 0.005*"ensure"
+2024-11-18 09:52:32,800 - topic #2 (0.333): 0.017*"’" + 0.009*"needs" + 0.008*"leaders" + 0.006*"June" + 0.006*"Gloucestershire" + 0.005*"2024" + 0.005*"plans" + 0.005*"South" + 0.005*"quality" + 0.005*"effective"
+2024-11-18 09:52:32,800 - topic diff=0.831701, rho=1.000000
+2024-11-18 09:52:32,800 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1188, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:52:32.800526', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:52:33,603 - Inspection date 2024-06-03 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:52:33,604 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:33,604 - Inspection date 2024-06-03 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:52:33,604 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:33,604 - Inspection date 2024-06-03 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:52:33,604 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:33,604 - Inspection date 2024-06-03 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:52:33,604 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:33,604 - Inspection date 2024-06-03 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:52:33,605 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:33,605 - Inspection date 2024-06-03 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:52:33,605 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:43,154 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:52:43,156 - built Dictionary<981 unique tokens: ["'s", '0161', '0300', '1', '10']...> from 1 documents (total 2189 corpus positions)
+2024-11-18 09:52:43,156 - Dictionary lifecycle event {'msg': 'built Dictionary<981 unique tokens: ["\'s", \'0161\', \'0300\', \'1\', \'10\']...> from 1 documents (total 2189 corpus positions)', 'datetime': '2024-11-18T09:52:43.156301', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:52:43,157 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:52:43,157 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:52:43,157 - using serial LDA version on this node
+2024-11-18 09:52:43,157 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:52:43,157 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:52:43,161 - -7.893 per-word bound, 237.6 perplexity estimate based on a held-out corpus of 1 documents with 2189 words
+2024-11-18 09:52:43,161 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:52:43,162 - topic #0 (0.333): 0.019*"’" + 0.009*"needs" + 0.007*"Tyneside" + 0.006*"carers" + 0.005*"effective" + 0.005*"9" + 0.005*"South" + 0.005*"risk" + 0.004*"December" + 0.004*"2023"
+2024-11-18 09:52:43,162 - topic #1 (0.333): 0.016*"’" + 0.008*"needs" + 0.008*"South" + 0.007*"Tyneside" + 0.005*"practice" + 0.005*"leaders" + 0.005*"risk" + 0.005*"carers" + 0.004*"effective" + 0.004*"5"
+2024-11-18 09:52:43,162 - topic #2 (0.333): 0.032*"’" + 0.009*"needs" + 0.009*"South" + 0.008*"Tyneside" + 0.006*"oversight" + 0.006*"management" + 0.006*"However" + 0.005*"February" + 0.005*"practice" + 0.005*"2022"
+2024-11-18 09:52:43,162 - topic diff=0.809813, rho=1.000000
+2024-11-18 09:52:43,163 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=981, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:52:43.163019', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:52:43,958 - Inspection date 2022-12-05 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:52:43,958 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:43,959 - Inspection date 2022-12-05 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:52:43,959 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:43,959 - Inspection date 2022-12-05 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:52:43,959 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:43,959 - Inspection date 2022-12-05 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:52:43,959 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:43,959 - Inspection date 2022-12-05 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:52:43,959 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:43,960 - Inspection date 2022-12-05 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:52:43,960 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:54,138 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:52:54,140 - built Dictionary<1178 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2318 corpus positions)
+2024-11-18 09:52:54,140 - Dictionary lifecycle event {'msg': "built Dictionary<1178 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2318 corpus positions)", 'datetime': '2024-11-18T09:52:54.140718', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:52:54,141 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:52:54,141 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:52:54,142 - using serial LDA version on this node
+2024-11-18 09:52:54,142 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:52:54,142 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:52:54,146 - -8.151 per-word bound, 284.2 perplexity estimate based on a held-out corpus of 1 documents with 2318 words
+2024-11-18 09:52:54,146 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:52:54,147 - topic #0 (0.333): 0.014*"’" + 0.006*"plans" + 0.005*"progress" + 0.005*"16" + 0.005*"5" + 0.004*"Southampton" + 0.004*"including" + 0.004*"improve" + 0.004*"needs" + 0.004*"timely"
+2024-11-18 09:52:54,147 - topic #1 (0.333): 0.021*"’" + 0.007*"Southampton" + 0.006*"plans" + 0.005*"needs" + 0.005*"provide" + 0.005*"improve" + 0.005*"experiences" + 0.004*"5" + 0.004*"well" + 0.004*"good"
+2024-11-18 09:52:54,147 - topic #2 (0.333): 0.011*"’" + 0.005*"improve" + 0.005*"progress" + 0.005*"Southampton" + 0.005*"2023" + 0.004*"plans" + 0.004*"including" + 0.004*"5" + 0.004*"experiences" + 0.004*"16"
+2024-11-18 09:52:54,147 - topic diff=0.750709, rho=1.000000
+2024-11-18 09:52:54,148 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1178, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:52:54.148036', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:52:54,959 - Inspection date 2023-06-05 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:52:54,959 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:54,959 - Inspection date 2023-06-05 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:52:54,959 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:54,959 - Inspection date 2023-06-05 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:52:54,959 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:54,959 - Inspection date 2023-06-05 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:52:54,959 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:54,960 - Inspection date 2023-06-05 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:52:54,960 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:52:54,960 - Inspection date 2023-06-05 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:52:54,960 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:04,449 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:53:04,451 - built Dictionary<1000 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2086 corpus positions)
+2024-11-18 09:53:04,451 - Dictionary lifecycle event {'msg': "built Dictionary<1000 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2086 corpus positions)", 'datetime': '2024-11-18T09:53:04.451663', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:53:04,452 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:53:04,452 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:53:04,452 - using serial LDA version on this node
+2024-11-18 09:53:04,453 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:53:04,453 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:53:04,456 - -7.946 per-word bound, 246.6 perplexity estimate based on a held-out corpus of 1 documents with 2086 words
+2024-11-18 09:53:04,456 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:53:04,457 - topic #0 (0.333): 0.015*"’" + 0.010*"planning" + 0.007*"practice" + 0.006*"leaders" + 0.006*"quality" + 0.006*"protection" + 0.005*"within" + 0.005*"risk" + 0.005*"number" + 0.005*"need"
+2024-11-18 09:53:04,457 - topic #1 (0.333): 0.014*"’" + 0.008*"practice" + 0.008*"planning" + 0.008*"quality" + 0.007*"leaders" + 0.006*"number" + 0.006*"needs" + 0.006*"protection" + 0.005*"carers" + 0.005*"always"
+2024-11-18 09:53:04,458 - topic #2 (0.333): 0.009*"’" + 0.006*"quality" + 0.005*"effective" + 0.005*"planning" + 0.005*"always" + 0.005*"well" + 0.005*"need" + 0.004*"number" + 0.004*"within" + 0.004*"risk"
+2024-11-18 09:53:04,458 - topic diff=0.778577, rho=1.000000
+2024-11-18 09:53:04,458 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1000, num_topics=3, decay=0.5, chunksize=2000> in 0.00s', 'datetime': '2024-11-18T09:53:04.458201', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:53:05,999 - Inspection date 2019-07-15 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:53:05,999 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:06,000 - Inspection date 2019-07-15 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:53:06,000 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:06,000 - Inspection date 2019-07-15 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:53:06,000 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:06,000 - Inspection date 2019-07-15 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:53:06,000 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:06,000 - Inspection date 2019-07-15 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:53:06,000 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:06,000 - Inspection date 2019-07-15 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:53:06,001 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:17,756 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:53:17,758 - built Dictionary<1092 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2218 corpus positions)
+2024-11-18 09:53:17,759 - Dictionary lifecycle event {'msg': "built Dictionary<1092 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2218 corpus positions)", 'datetime': '2024-11-18T09:53:17.758987', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:53:17,759 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:53:17,760 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:53:17,760 - using serial LDA version on this node
+2024-11-18 09:53:17,760 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:53:17,760 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:53:17,764 - -8.049 per-word bound, 264.9 perplexity estimate based on a held-out corpus of 1 documents with 2218 words
+2024-11-18 09:53:17,764 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:53:17,765 - topic #0 (0.333): 0.012*"’" + 0.008*"Helens" + 0.007*"St" + 0.006*"needs" + 0.006*"well" + 0.005*"risk" + 0.005*"progress" + 0.005*"10" + 0.005*"need" + 0.005*"receive"
+2024-11-18 09:53:17,765 - topic #1 (0.333): 0.013*"’" + 0.010*"St" + 0.007*"Helens" + 0.007*"well" + 0.006*"needs" + 0.006*"progress" + 0.006*"risk" + 0.005*"10" + 0.005*"need" + 0.005*"21"
+2024-11-18 09:53:17,765 - topic #2 (0.333): 0.021*"’" + 0.008*"needs" + 0.007*"Helens" + 0.007*"well" + 0.006*"St" + 0.006*"progress" + 0.006*"good" + 0.006*"21" + 0.006*"receive" + 0.006*"need"
+2024-11-18 09:53:17,766 - topic diff=0.770174, rho=1.000000
+2024-11-18 09:53:17,766 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1092, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:53:17.766133', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:53:18,697 - Inspection date 2023-07-10 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:53:18,697 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:18,698 - Inspection date 2023-07-10 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:53:18,698 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:18,698 - Inspection date 2023-07-10 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:53:18,698 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:18,698 - Inspection date 2023-07-10 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:53:18,698 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:18,698 - Inspection date 2023-07-10 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:53:18,698 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:18,699 - Inspection date 2023-07-10 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:53:18,699 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:28,317 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:53:28,319 - built Dictionary<1076 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2334 corpus positions)
+2024-11-18 09:53:28,319 - Dictionary lifecycle event {'msg': "built Dictionary<1076 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2334 corpus positions)", 'datetime': '2024-11-18T09:53:28.319619', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:53:28,320 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:53:28,320 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:53:28,321 - using serial LDA version on this node
+2024-11-18 09:53:28,321 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:53:28,321 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:53:28,324 - -7.996 per-word bound, 255.2 perplexity estimate based on a held-out corpus of 1 documents with 2334 words
+2024-11-18 09:53:28,325 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:53:28,326 - topic #0 (0.333): 0.014*"’" + 0.010*"needs" + 0.006*"practice" + 0.005*"oversight" + 0.005*"health" + 0.005*"progress" + 0.005*"quality" + 0.005*"ensure" + 0.005*"Staffordshire" + 0.004*"6"
+2024-11-18 09:53:28,326 - topic #1 (0.333): 0.021*"’" + 0.012*"needs" + 0.007*"Staffordshire" + 0.007*"progress" + 0.006*"oversight" + 0.006*"quality" + 0.006*"ensure" + 0.006*"practice" + 0.006*"plans" + 0.005*"health"
+2024-11-18 09:53:28,326 - topic #2 (0.333): 0.014*"’" + 0.012*"needs" + 0.006*"quality" + 0.006*"health" + 0.005*"ensure" + 0.005*"oversight" + 0.005*"practice" + 0.005*"plans" + 0.004*"progress" + 0.004*"6"
+2024-11-18 09:53:28,326 - topic diff=0.804108, rho=1.000000
+2024-11-18 09:53:28,326 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1076, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:53:28.326841', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:53:29,161 - Inspection date 2023-11-06 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:53:29,161 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:29,162 - Inspection date 2023-11-06 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:53:29,162 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:29,162 - Inspection date 2023-11-06 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:53:29,162 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:29,162 - Inspection date 2023-11-06 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:53:29,162 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:29,162 - Inspection date 2023-11-06 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:53:29,162 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:29,162 - Inspection date 2023-11-06 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:53:29,162 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:38,202 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:53:38,204 - built Dictionary<1060 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2316 corpus positions)
+2024-11-18 09:53:38,205 - Dictionary lifecycle event {'msg': "built Dictionary<1060 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2316 corpus positions)", 'datetime': '2024-11-18T09:53:38.205092', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:53:38,206 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:53:38,206 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:53:38,206 - using serial LDA version on this node
+2024-11-18 09:53:38,206 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:53:38,206 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:53:38,210 - -7.974 per-word bound, 251.5 perplexity estimate based on a held-out corpus of 1 documents with 2316 words
+2024-11-18 09:53:38,210 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:53:38,211 - topic #0 (0.333): 0.013*"’" + 0.009*"well" + 0.008*"practice" + 0.007*"Stockport" + 0.007*"needs" + 0.006*"strong" + 0.005*"28" + 0.005*"quality" + 0.005*"risk" + 0.005*"plans"
+2024-11-18 09:53:38,211 - topic #1 (0.333): 0.012*"’" + 0.008*"well" + 0.007*"practice" + 0.006*"Stockport" + 0.006*"needs" + 0.005*"plans" + 0.005*"strong" + 0.005*"leaders" + 0.005*"ensure" + 0.005*"risk"
+2024-11-18 09:53:38,211 - topic #2 (0.333): 0.006*"well" + 0.006*"’" + 0.005*"practice" + 0.005*"needs" + 0.005*"Stockport" + 0.005*"plans" + 0.004*"risk" + 0.004*"strong" + 0.003*"1" + 0.003*"leaders"
+2024-11-18 09:53:38,211 - topic diff=0.805129, rho=1.000000
+2024-11-18 09:53:38,212 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1060, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:53:38.212049', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:53:39,081 - Inspection date 2022-03-28 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:53:39,081 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:39,082 - Inspection date 2022-03-28 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:53:39,082 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:39,082 - Inspection date 2022-03-28 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:53:39,082 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:39,082 - Inspection date 2022-03-28 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:53:39,082 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:39,082 - Inspection date 2022-03-28 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:53:39,082 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:39,083 - Inspection date 2022-03-28 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:53:39,083 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:49,089 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:53:49,091 - built Dictionary<1044 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2269 corpus positions)
+2024-11-18 09:53:49,091 - Dictionary lifecycle event {'msg': "built Dictionary<1044 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2269 corpus positions)", 'datetime': '2024-11-18T09:53:49.091695', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:53:49,092 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:53:49,092 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:53:49,093 - using serial LDA version on this node
+2024-11-18 09:53:49,093 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:53:49,093 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:53:49,096 - -7.962 per-word bound, 249.4 perplexity estimate based on a held-out corpus of 1 documents with 2269 words
+2024-11-18 09:53:49,096 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:53:49,098 - topic #0 (0.333): 0.023*"’" + 0.009*"leaders" + 0.008*"plans" + 0.008*"needs" + 0.007*"well" + 0.006*"good" + 0.006*"senior" + 0.006*"Stockton" + 0.006*"on-Tees" + 0.005*"carers"
+2024-11-18 09:53:49,098 - topic #1 (0.333): 0.019*"’" + 0.009*"plans" + 0.008*"leaders" + 0.008*"quality" + 0.007*"on-Tees" + 0.006*"Stockton" + 0.005*"good" + 0.005*"17" + 0.005*"6" + 0.005*"needs"
+2024-11-18 09:53:49,098 - topic #2 (0.333): 0.014*"’" + 0.009*"leaders" + 0.007*"well" + 0.007*"plans" + 0.006*"needs" + 0.004*"quality" + 0.004*"17" + 0.004*"Stockton" + 0.004*"on-Tees" + 0.004*"good"
+2024-11-18 09:53:49,098 - topic diff=0.775793, rho=1.000000
+2024-11-18 09:53:49,098 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1044, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:53:49.098849', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:53:49,982 - Inspection date 2023-03-06 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:53:49,982 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:49,982 - Inspection date 2023-03-06 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:53:49,982 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:49,982 - Inspection date 2023-03-06 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:53:49,983 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:49,983 - Inspection date 2023-03-06 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:53:49,983 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:49,983 - Inspection date 2023-03-06 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:53:49,983 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:49,983 - Inspection date 2023-03-06 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:53:49,983 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:53:59,989 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:53:59,991 - built Dictionary<986 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2165 corpus positions)
+2024-11-18 09:53:59,991 - Dictionary lifecycle event {'msg': "built Dictionary<986 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2165 corpus positions)", 'datetime': '2024-11-18T09:53:59.991340', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:53:59,992 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:53:59,992 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:53:59,992 - using serial LDA version on this node
+2024-11-18 09:53:59,992 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:53:59,993 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:53:59,996 - -7.905 per-word bound, 239.8 perplexity estimate based on a held-out corpus of 1 documents with 2165 words
+2024-11-18 09:53:59,996 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:53:59,997 - topic #0 (0.333): 0.016*"’" + 0.009*"needs" + 0.007*"on-Trent" + 0.007*"Stoke" + 0.007*"However" + 0.006*"plans" + 0.006*"well" + 0.006*"protection" + 0.006*"ensure" + 0.005*"progress"
+2024-11-18 09:53:59,997 - topic #1 (0.333): 0.021*"’" + 0.008*"needs" + 0.007*"well" + 0.007*"Stoke" + 0.006*"on-Trent" + 0.006*"plans" + 0.006*"However" + 0.005*"progress" + 0.005*"ensure" + 0.005*"protection"
+2024-11-18 09:53:59,997 - topic #2 (0.333): 0.015*"’" + 0.008*"needs" + 0.007*"well" + 0.007*"plans" + 0.007*"However" + 0.007*"on-Trent" + 0.006*"Stoke" + 0.005*"ensure" + 0.005*"protection" + 0.005*"quality"
+2024-11-18 09:53:59,997 - topic diff=0.778582, rho=1.000000
+2024-11-18 09:53:59,998 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=986, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:53:59.998069', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:54:00,786 - Inspection date 2022-10-03 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:54:00,786 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:00,786 - Inspection date 2022-10-03 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:54:00,787 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:00,787 - Inspection date 2022-10-03 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:54:00,787 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:00,787 - Inspection date 2022-10-03 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:54:00,787 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:00,787 - Inspection date 2022-10-03 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:54:00,787 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:00,787 - Inspection date 2022-10-03 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:54:00,787 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:13,045 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:54:13,047 - built Dictionary<1126 unique tokens: ["'s", '0161', '0300', '1', '10']...> from 1 documents (total 2544 corpus positions)
+2024-11-18 09:54:13,048 - Dictionary lifecycle event {'msg': 'built Dictionary<1126 unique tokens: ["\'s", \'0161\', \'0300\', \'1\', \'10\']...> from 1 documents (total 2544 corpus positions)', 'datetime': '2024-11-18T09:54:13.048156', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:54:13,049 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:54:13,049 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:54:13,049 - using serial LDA version on this node
+2024-11-18 09:54:13,049 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:54:13,050 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:54:13,053 - -8.018 per-word bound, 259.3 perplexity estimate based on a held-out corpus of 1 documents with 2544 words
+2024-11-18 09:54:13,053 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:54:13,055 - topic #0 (0.333): 0.017*"’" + 0.012*"needs" + 0.008*"Suffolk" + 0.006*"well" + 0.005*"practice" + 0.005*"Council" + 0.004*"3" + 0.004*"leaders" + 0.004*"County" + 0.004*"7"
+2024-11-18 09:54:13,055 - topic #1 (0.333): 0.025*"’" + 0.013*"Suffolk" + 0.010*"needs" + 0.009*"well" + 0.006*"County" + 0.006*"practice" + 0.006*"protection" + 0.005*"7" + 0.005*"plans" + 0.005*"2024"
+2024-11-18 09:54:13,055 - topic #2 (0.333): 0.017*"’" + 0.008*"needs" + 0.007*"well" + 0.007*"Suffolk" + 0.005*"3" + 0.004*"Council" + 0.004*"parents" + 0.004*"protection" + 0.004*"2024" + 0.004*"including"
+2024-11-18 09:54:13,055 - topic diff=0.821575, rho=1.000000
+2024-11-18 09:54:13,055 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1126, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:54:13.055599', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:54:14,795 - Inspection date 2024-06-03 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:54:14,796 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:14,796 - Inspection date 2024-06-03 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:54:14,796 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:14,796 - Inspection date 2024-06-03 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:54:14,796 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:14,797 - Inspection date 2024-06-03 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:54:14,797 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:14,797 - Inspection date 2024-06-03 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:54:14,797 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:14,797 - Inspection date 2024-06-03 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:54:14,797 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:25,086 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:54:25,088 - built Dictionary<1128 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2409 corpus positions)
+2024-11-18 09:54:25,088 - Dictionary lifecycle event {'msg': "built Dictionary<1128 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2409 corpus positions)", 'datetime': '2024-11-18T09:54:25.088601', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:54:25,089 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:54:25,089 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:54:25,089 - using serial LDA version on this node
+2024-11-18 09:54:25,090 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:54:25,090 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:54:25,093 - -8.054 per-word bound, 265.8 perplexity estimate based on a held-out corpus of 1 documents with 2409 words
+2024-11-18 09:54:25,094 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:54:25,095 - topic #0 (0.333): 0.012*"’" + 0.007*"well" + 0.007*"needs" + 0.006*"quality" + 0.004*"Sunderland" + 0.004*"protection" + 0.004*"training" + 0.004*"council" + 0.004*"TfC" + 0.004*"plans"
+2024-11-18 09:54:25,095 - topic #1 (0.333): 0.020*"’" + 0.008*"well" + 0.008*"quality" + 0.007*"Sunderland" + 0.006*"needs" + 0.006*"experienced" + 0.005*"good" + 0.005*"practice" + 0.005*"result" + 0.005*"parents"
+2024-11-18 09:54:25,095 - topic #2 (0.333): 0.013*"’" + 0.006*"needs" + 0.005*"well" + 0.005*"Sunderland" + 0.004*"experienced" + 0.004*"quality" + 0.004*"need" + 0.004*"practice" + 0.004*"council" + 0.004*"protection"
+2024-11-18 09:54:25,095 - topic diff=0.797705, rho=1.000000
+2024-11-18 09:54:25,096 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1128, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:54:25.096011', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:54:26,130 - Inspection date 2021-06-28 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:54:26,130 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:26,131 - Inspection date 2021-06-28 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:54:26,131 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:26,131 - Inspection date 2021-06-28 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:54:26,131 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:26,131 - Inspection date 2021-06-28 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:54:26,131 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:26,131 - Inspection date 2021-06-28 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:54:26,131 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:26,132 - Inspection date 2021-06-28 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:54:26,132 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:35,878 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:54:35,880 - built Dictionary<1016 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2111 corpus positions)
+2024-11-18 09:54:35,880 - Dictionary lifecycle event {'msg': "built Dictionary<1016 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2111 corpus positions)", 'datetime': '2024-11-18T09:54:35.880554', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:54:35,881 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:54:35,881 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:54:35,881 - using serial LDA version on this node
+2024-11-18 09:54:35,882 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:54:35,882 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:54:35,885 - -7.966 per-word bound, 250.1 perplexity estimate based on a held-out corpus of 1 documents with 2111 words
+2024-11-18 09:54:35,885 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:54:35,886 - topic #0 (0.333): 0.012*"’" + 0.009*"needs" + 0.008*"well" + 0.006*"progress" + 0.005*"plans" + 0.005*"practice" + 0.005*"17" + 0.005*"good" + 0.005*"carers" + 0.005*"Surrey"
+2024-11-18 09:54:35,886 - topic #1 (0.333): 0.015*"’" + 0.011*"needs" + 0.009*"well" + 0.009*"practice" + 0.008*"progress" + 0.006*"quality" + 0.006*"plans" + 0.005*"carers" + 0.005*"effective" + 0.005*"However"
+2024-11-18 09:54:35,887 - topic #2 (0.333): 0.012*"’" + 0.011*"well" + 0.009*"needs" + 0.006*"practice" + 0.005*"effective" + 0.005*"17" + 0.005*"progress" + 0.004*"good" + 0.004*"carers" + 0.004*"plans"
+2024-11-18 09:54:35,887 - topic diff=0.762167, rho=1.000000
+2024-11-18 09:54:35,887 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1016, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:54:35.887300', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:54:36,844 - Inspection date 2022-01-17 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:54:36,844 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:36,844 - Inspection date 2022-01-17 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:54:36,845 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:36,845 - Inspection date 2022-01-17 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:54:36,845 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:36,845 - Inspection date 2022-01-17 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:54:36,845 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:36,845 - Inspection date 2022-01-17 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:54:36,845 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:36,845 - Inspection date 2022-01-17 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:54:36,845 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:46,829 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:54:46,831 - built Dictionary<951 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2229 corpus positions)
+2024-11-18 09:54:46,832 - Dictionary lifecycle event {'msg': "built Dictionary<951 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2229 corpus positions)", 'datetime': '2024-11-18T09:54:46.832019', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:54:46,832 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:54:46,833 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:54:46,833 - using serial LDA version on this node
+2024-11-18 09:54:46,833 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:54:46,833 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:54:46,836 - -7.827 per-word bound, 227.1 perplexity estimate based on a held-out corpus of 1 documents with 2229 words
+2024-11-18 09:54:46,836 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:54:46,838 - topic #0 (0.333): 0.025*"’" + 0.014*"needs" + 0.009*"need" + 0.008*"well" + 0.008*"Swindon" + 0.007*"always" + 0.006*"health" + 0.006*"many" + 0.006*"plans" + 0.006*"impact"
+2024-11-18 09:54:46,838 - topic #1 (0.333): 0.015*"’" + 0.012*"needs" + 0.010*"Swindon" + 0.010*"need" + 0.007*"well" + 0.006*"always" + 0.005*"lack" + 0.005*"Borough" + 0.005*"impact" + 0.005*"home"
+2024-11-18 09:54:46,838 - topic #2 (0.333): 0.025*"’" + 0.012*"needs" + 0.009*"Swindon" + 0.008*"plans" + 0.008*"well" + 0.006*"need" + 0.006*"always" + 0.006*"effective" + 0.006*"Council" + 0.006*"education"
+2024-11-18 09:54:46,838 - topic diff=0.825308, rho=1.000000
+2024-11-18 09:54:46,838 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=951, num_topics=3, decay=0.5, chunksize=2000> in 0.00s', 'datetime': '2024-11-18T09:54:46.838588', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:54:47,687 - Inspection date 2023-07-17 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:54:47,688 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:47,688 - Inspection date 2023-07-17 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:54:47,688 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:47,688 - Inspection date 2023-07-17 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:54:47,688 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:47,689 - Inspection date 2023-07-17 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:54:47,689 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:47,689 - Inspection date 2023-07-17 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:54:47,689 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:47,689 - Inspection date 2023-07-17 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:54:47,689 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:58,801 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:54:58,803 - built Dictionary<1064 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2491 corpus positions)
+2024-11-18 09:54:58,803 - Dictionary lifecycle event {'msg': "built Dictionary<1064 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2491 corpus positions)", 'datetime': '2024-11-18T09:54:58.803445', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:54:58,804 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:54:58,804 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:54:58,804 - using serial LDA version on this node
+2024-11-18 09:54:58,805 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:54:58,805 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:54:58,808 - -7.940 per-word bound, 245.6 perplexity estimate based on a held-out corpus of 1 documents with 2491 words
+2024-11-18 09:54:58,808 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:54:58,809 - topic #0 (0.333): 0.019*"’" + 0.010*"needs" + 0.008*"risk" + 0.007*"quality" + 0.006*"impact" + 0.006*"experienced" + 0.006*"2023" + 0.006*"practice" + 0.005*"4" + 0.005*"Tameside"
+2024-11-18 09:54:58,810 - topic #1 (0.333): 0.010*"’" + 0.008*"needs" + 0.006*"impact" + 0.005*"risk" + 0.004*"practice" + 0.004*"experienced" + 0.004*"response" + 0.004*"effective" + 0.004*"2023" + 0.004*"planning"
+2024-11-18 09:54:58,810 - topic #2 (0.333): 0.016*"’" + 0.008*"needs" + 0.006*"impact" + 0.006*"response" + 0.005*"4" + 0.005*"experiences" + 0.005*"understand" + 0.005*"quality" + 0.005*"practice" + 0.005*"Tameside"
+2024-11-18 09:54:58,810 - topic diff=0.836831, rho=1.000000
+2024-11-18 09:54:58,810 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1064, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:54:58.810491', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:54:59,690 - Inspection date 2023-12-04 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:54:59,690 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:59,691 - Inspection date 2023-12-04 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:54:59,691 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:59,691 - Inspection date 2023-12-04 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:54:59,691 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:59,691 - Inspection date 2023-12-04 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:54:59,691 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:59,691 - Inspection date 2023-12-04 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:54:59,691 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:54:59,691 - Inspection date 2023-12-04 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:54:59,691 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:11,251 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:55:11,253 - built Dictionary<1077 unique tokens: ['00', '0161', '03', '0300', '1']...> from 1 documents (total 2452 corpus positions)
+2024-11-18 09:55:11,254 - Dictionary lifecycle event {'msg': "built Dictionary<1077 unique tokens: ['00', '0161', '03', '0300', '1']...> from 1 documents (total 2452 corpus positions)", 'datetime': '2024-11-18T09:55:11.254124', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:55:11,255 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:55:11,255 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:55:11,255 - using serial LDA version on this node
+2024-11-18 09:55:11,255 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:55:11,255 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:55:11,259 - -7.973 per-word bound, 251.2 perplexity estimate based on a held-out corpus of 1 documents with 2452 words
+2024-11-18 09:55:11,259 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:55:11,260 - topic #0 (0.333): 0.021*"’" + 0.012*"needs" + 0.009*"Wrekin" + 0.008*"Telford" + 0.006*"plans" + 0.006*"benefit" + 0.005*"well" + 0.005*"effective" + 0.005*"Family" + 0.005*"3"
+2024-11-18 09:55:11,260 - topic #1 (0.333): 0.021*"’" + 0.010*"needs" + 0.008*"Telford" + 0.007*"Wrekin" + 0.006*"well" + 0.006*"effective" + 0.005*"plans" + 0.005*"Family" + 0.005*"benefit" + 0.005*"leaders"
+2024-11-18 09:55:11,261 - topic #2 (0.333): 0.022*"’" + 0.010*"needs" + 0.007*"Telford" + 0.007*"benefit" + 0.007*"Wrekin" + 0.005*"well" + 0.005*"Family" + 0.004*"29" + 0.004*"live" + 0.004*"PAs"
+2024-11-18 09:55:11,261 - topic diff=0.821393, rho=1.000000
+2024-11-18 09:55:11,261 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1077, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:55:11.261213', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:55:12,146 - Inspection date 2024-04-29 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:55:12,146 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:12,146 - Inspection date 2024-04-29 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:55:12,146 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:12,146 - Inspection date 2024-04-29 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:55:12,147 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:12,147 - Inspection date 2024-04-29 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:55:12,147 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:12,147 - Inspection date 2024-04-29 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:55:12,147 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:12,147 - Inspection date 2024-04-29 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:55:12,147 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:23,020 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:55:23,022 - built Dictionary<1119 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2395 corpus positions)
+2024-11-18 09:55:23,023 - Dictionary lifecycle event {'msg': "built Dictionary<1119 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2395 corpus positions)", 'datetime': '2024-11-18T09:55:23.022970', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:55:23,024 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:55:23,024 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:55:23,024 - using serial LDA version on this node
+2024-11-18 09:55:23,024 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:55:23,024 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:55:23,028 - -8.047 per-word bound, 264.5 perplexity estimate based on a held-out corpus of 1 documents with 2395 words
+2024-11-18 09:55:23,028 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:55:23,029 - topic #0 (0.333): 0.019*"’" + 0.012*"Thurrock" + 0.007*"well" + 0.006*"time" + 0.006*"needs" + 0.006*"PAs" + 0.005*"receive" + 0.005*"leaders" + 0.005*"progress" + 0.005*"need"
+2024-11-18 09:55:23,029 - topic #1 (0.333): 0.016*"’" + 0.009*"Thurrock" + 0.007*"well" + 0.005*"PAs" + 0.005*"leaders" + 0.005*"16" + 0.005*"receive" + 0.005*"need" + 0.005*"needs" + 0.005*"progress"
+2024-11-18 09:55:23,030 - topic #2 (0.333): 0.016*"’" + 0.007*"Thurrock" + 0.006*"PAs" + 0.005*"receive" + 0.005*"leaders" + 0.004*"well" + 0.004*"needs" + 0.004*"progress" + 0.004*"September" + 0.004*"comprehensive"
+2024-11-18 09:55:23,030 - topic diff=0.786213, rho=1.000000
+2024-11-18 09:55:23,030 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1119, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:55:23.030320', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:55:23,822 - Inspection date 2024-09-16 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:55:23,822 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:23,823 - Inspection date 2024-09-16 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:55:23,823 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:23,823 - Inspection date 2024-09-16 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:55:23,823 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:23,823 - Inspection date 2024-09-16 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:55:23,823 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:23,824 - Inspection date 2024-09-16 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:55:23,824 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:23,824 - Inspection date 2024-09-16 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:55:23,824 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:33,209 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:55:33,211 - built Dictionary<1054 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2065 corpus positions)
+2024-11-18 09:55:33,211 - Dictionary lifecycle event {'msg': "built Dictionary<1054 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2065 corpus positions)", 'datetime': '2024-11-18T09:55:33.211615', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:55:33,212 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:55:33,212 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:55:33,212 - using serial LDA version on this node
+2024-11-18 09:55:33,213 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:55:33,213 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:55:33,216 - -8.042 per-word bound, 263.5 perplexity estimate based on a held-out corpus of 1 documents with 2065 words
+2024-11-18 09:55:33,216 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:55:33,218 - topic #0 (0.333): 0.017*"’" + 0.011*"well" + 0.007*"Torbay" + 0.007*"needs" + 0.005*"effective" + 0.005*"21" + 0.005*"good" + 0.004*"March" + 0.004*"2022" + 0.004*"1"
+2024-11-18 09:55:33,218 - topic #1 (0.333): 0.018*"’" + 0.008*"good" + 0.008*"well" + 0.007*"Torbay" + 0.006*"needs" + 0.005*"team" + 0.005*"progress" + 0.005*"21" + 0.004*"effective" + 0.004*"timely"
+2024-11-18 09:55:33,218 - topic #2 (0.333): 0.012*"’" + 0.008*"well" + 0.007*"Torbay" + 0.005*"progress" + 0.005*"needs" + 0.005*"effective" + 0.004*"timely" + 0.004*"good" + 0.004*"team" + 0.004*"plans"
+2024-11-18 09:55:33,218 - topic diff=0.749998, rho=1.000000
+2024-11-18 09:55:33,218 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1054, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:55:33.218620', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:55:34,143 - Inspection date 2022-03-21 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:55:34,143 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:34,143 - Inspection date 2022-03-21 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:55:34,143 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:34,143 - Inspection date 2022-03-21 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:55:34,144 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:34,144 - Inspection date 2022-03-21 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:55:34,144 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:34,144 - Inspection date 2022-03-21 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:55:34,144 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:34,144 - Inspection date 2022-03-21 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:55:34,144 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:45,709 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:55:45,711 - built Dictionary<1038 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2448 corpus positions)
+2024-11-18 09:55:45,712 - Dictionary lifecycle event {'msg': "built Dictionary<1038 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2448 corpus positions)", 'datetime': '2024-11-18T09:55:45.712007', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:55:45,713 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:55:45,713 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:55:45,713 - using serial LDA version on this node
+2024-11-18 09:55:45,713 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:55:45,713 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:55:45,717 - -7.911 per-word bound, 240.7 perplexity estimate based on a held-out corpus of 1 documents with 2448 words
+2024-11-18 09:55:45,717 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:55:45,718 - topic #0 (0.333): 0.018*"’" + 0.010*"needs" + 0.009*"well" + 0.008*"quality" + 0.007*"plans" + 0.007*"Trafford" + 0.006*"leaders" + 0.005*"ensure" + 0.005*"2022" + 0.005*"education"
+2024-11-18 09:55:45,718 - topic #1 (0.333): 0.015*"’" + 0.008*"needs" + 0.008*"Trafford" + 0.007*"plans" + 0.006*"well" + 0.005*"leaders" + 0.005*"practice" + 0.005*"placed" + 0.005*"quality" + 0.005*"impact"
+2024-11-18 09:55:45,718 - topic #2 (0.333): 0.016*"’" + 0.009*"needs" + 0.009*"Trafford" + 0.006*"practice" + 0.006*"plans" + 0.005*"quality" + 0.005*"leaders" + 0.005*"team" + 0.005*"well" + 0.005*"impact"
+2024-11-18 09:55:45,718 - topic diff=0.822761, rho=1.000000
+2024-11-18 09:55:45,718 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1038, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:55:45.718957', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:55:46,659 - Inspection date 2022-11-21 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:55:46,659 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:46,659 - Inspection date 2022-11-21 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:55:46,660 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:46,660 - Inspection date 2022-11-21 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:55:46,660 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:46,660 - Inspection date 2022-11-21 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:55:46,660 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:46,661 - Inspection date 2022-11-21 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:55:46,661 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:46,661 - Inspection date 2022-11-21 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:55:46,661 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:57,668 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:55:57,671 - built Dictionary<1162 unique tokens: ["'s", '0161', '0300', '1', '10']...> from 1 documents (total 2626 corpus positions)
+2024-11-18 09:55:57,671 - Dictionary lifecycle event {'msg': 'built Dictionary<1162 unique tokens: ["\'s", \'0161\', \'0300\', \'1\', \'10\']...> from 1 documents (total 2626 corpus positions)', 'datetime': '2024-11-18T09:55:57.671222', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:55:57,672 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:55:57,672 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:55:57,672 - using serial LDA version on this node
+2024-11-18 09:55:57,673 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:55:57,673 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:55:57,676 - -8.048 per-word bound, 264.7 perplexity estimate based on a held-out corpus of 1 documents with 2626 words
+2024-11-18 09:55:57,676 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:55:57,678 - topic #0 (0.333): 0.021*"’" + 0.007*"needs" + 0.006*"leaders" + 0.006*"Walsall" + 0.005*"well" + 0.005*"information" + 0.005*"Senior" + 0.005*"good" + 0.004*"need" + 0.004*"risk"
+2024-11-18 09:55:57,678 - topic #1 (0.333): 0.024*"’" + 0.008*"leaders" + 0.007*"needs" + 0.006*"well" + 0.005*"4" + 0.004*"oversight" + 0.004*"Walsall" + 0.004*"information" + 0.004*"Senior" + 0.004*"good"
+2024-11-18 09:55:57,678 - topic #2 (0.333): 0.018*"’" + 0.007*"leaders" + 0.006*"Walsall" + 0.006*"needs" + 0.005*"4" + 0.005*"well" + 0.004*"15" + 0.004*"information" + 0.004*"oversight" + 0.004*"positive"
+2024-11-18 09:55:57,678 - topic diff=0.810739, rho=1.000000
+2024-11-18 09:55:57,678 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1162, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:55:57.678660', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:55:58,497 - Inspection date 2021-10-04 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:55:58,498 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:58,498 - Inspection date 2021-10-04 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:55:58,498 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:58,498 - Inspection date 2021-10-04 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:55:58,498 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:58,498 - Inspection date 2021-10-04 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:55:58,498 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:58,499 - Inspection date 2021-10-04 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:55:58,499 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:55:58,499 - Inspection date 2021-10-04 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:55:58,499 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:11,660 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:56:11,662 - built Dictionary<1158 unique tokens: ["'s", '0161', '0300', '1', '10']...> from 1 documents (total 2700 corpus positions)
+2024-11-18 09:56:11,663 - Dictionary lifecycle event {'msg': 'built Dictionary<1158 unique tokens: ["\'s", \'0161\', \'0300\', \'1\', \'10\']...> from 1 documents (total 2700 corpus positions)', 'datetime': '2024-11-18T09:56:11.663125', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:56:11,664 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:56:11,664 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:56:11,664 - using serial LDA version on this node
+2024-11-18 09:56:11,664 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:56:11,665 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:56:11,668 - -8.029 per-word bound, 261.2 perplexity estimate based on a held-out corpus of 1 documents with 2700 words
+2024-11-18 09:56:11,668 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:56:11,670 - topic #0 (0.333): 0.018*"’" + 0.006*"effective" + 0.006*"Warrington" + 0.006*"experiences" + 0.006*"2024" + 0.005*"needs" + 0.005*"leaders" + 0.005*"well" + 0.005*"practice" + 0.004*"plans"
+2024-11-18 09:56:11,670 - topic #1 (0.333): 0.018*"’" + 0.008*"needs" + 0.007*"Warrington" + 0.007*"well" + 0.006*"14" + 0.006*"effective" + 0.006*"leaders" + 0.005*"10" + 0.005*"experiences" + 0.005*"plans"
+2024-11-18 09:56:11,670 - topic #2 (0.333): 0.021*"’" + 0.008*"experiences" + 0.007*"needs" + 0.007*"Warrington" + 0.006*"effective" + 0.006*"carers" + 0.005*"leaders" + 0.005*"practice" + 0.005*"plans" + 0.005*"strong"
+2024-11-18 09:56:11,670 - topic diff=0.809154, rho=1.000000
+2024-11-18 09:56:11,670 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1158, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:56:11.670631', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:56:12,567 - Inspection date 2024-06-10 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:56:12,567 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:12,568 - Inspection date 2024-06-10 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:56:12,568 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:12,568 - Inspection date 2024-06-10 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:56:12,568 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:12,568 - Inspection date 2024-06-10 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:56:12,568 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:12,568 - Inspection date 2024-06-10 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:56:12,568 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:12,569 - Inspection date 2024-06-10 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:56:12,569 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:22,602 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:56:22,604 - built Dictionary<1040 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2113 corpus positions)
+2024-11-18 09:56:22,604 - Dictionary lifecycle event {'msg': "built Dictionary<1040 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2113 corpus positions)", 'datetime': '2024-11-18T09:56:22.604549', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:56:22,605 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:56:22,605 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:56:22,605 - using serial LDA version on this node
+2024-11-18 09:56:22,606 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:56:22,606 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:56:22,609 - -8.003 per-word bound, 256.6 perplexity estimate based on a held-out corpus of 1 documents with 2113 words
+2024-11-18 09:56:22,609 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:56:22,610 - topic #0 (0.333): 0.011*"’" + 0.006*"plans" + 0.006*"Warwickshire" + 0.005*"needs" + 0.005*"well" + 0.004*"clear" + 0.004*"progress" + 0.004*"Senior" + 0.004*"effective" + 0.004*"carers"
+2024-11-18 09:56:22,611 - topic #1 (0.333): 0.012*"’" + 0.008*"needs" + 0.007*"well" + 0.006*"Warwickshire" + 0.006*"plans" + 0.006*"good" + 0.005*"practice" + 0.005*"3" + 0.005*"progress" + 0.005*"22"
+2024-11-18 09:56:22,611 - topic #2 (0.333): 0.012*"’" + 0.007*"well" + 0.006*"plans" + 0.006*"needs" + 0.005*"carers" + 0.005*"practice" + 0.005*"Warwickshire" + 0.004*"ensure" + 0.004*"good" + 0.004*"effective"
+2024-11-18 09:56:22,611 - topic diff=0.755551, rho=1.000000
+2024-11-18 09:56:22,611 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1040, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:56:22.611439', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:56:23,408 - Inspection date 2021-11-22 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:56:23,408 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:23,409 - Inspection date 2021-11-22 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:56:23,409 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:23,409 - Inspection date 2021-11-22 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:56:23,409 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:23,409 - Inspection date 2021-11-22 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:56:23,409 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:23,409 - Inspection date 2021-11-22 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:56:23,409 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:23,410 - Inspection date 2021-11-22 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:56:23,410 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:32,902 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:56:32,904 - built Dictionary<1115 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2146 corpus positions)
+2024-11-18 09:56:32,904 - Dictionary lifecycle event {'msg': "built Dictionary<1115 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2146 corpus positions)", 'datetime': '2024-11-18T09:56:32.904955', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:56:32,905 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:56:32,906 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:56:32,906 - using serial LDA version on this node
+2024-11-18 09:56:32,906 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:56:32,906 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:56:32,910 - -8.104 per-word bound, 275.2 perplexity estimate based on a held-out corpus of 1 documents with 2146 words
+2024-11-18 09:56:32,910 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:56:32,911 - topic #0 (0.333): 0.011*"’" + 0.007*"well" + 0.007*"Berkshire" + 0.007*"West" + 0.005*"need" + 0.004*"14" + 0.004*"plans" + 0.004*"agency" + 0.004*"needs" + 0.004*"education"
+2024-11-18 09:56:32,911 - topic #1 (0.333): 0.010*"’" + 0.005*"Berkshire" + 0.005*"well" + 0.005*"West" + 0.004*"needs" + 0.004*"working" + 0.003*"progress" + 0.003*"18" + 0.003*"14" + 0.003*"need"
+2024-11-18 09:56:32,911 - topic #2 (0.333): 0.019*"’" + 0.007*"West" + 0.006*"Berkshire" + 0.006*"well" + 0.005*"plans" + 0.004*"early" + 0.004*"agency" + 0.004*"18" + 0.004*"need" + 0.004*"needs"
+2024-11-18 09:56:32,911 - topic diff=0.720556, rho=1.000000
+2024-11-18 09:56:32,911 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1115, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:56:32.911961', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:56:33,733 - Inspection date 2022-03-14 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:56:33,733 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:33,733 - Inspection date 2022-03-14 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:56:33,733 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:33,734 - Inspection date 2022-03-14 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:56:33,734 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:33,734 - Inspection date 2022-03-14 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:56:33,734 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:33,734 - Inspection date 2022-03-14 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:56:33,734 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:33,734 - Inspection date 2022-03-14 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:56:33,734 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:43,365 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:56:43,367 - built Dictionary<1087 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2224 corpus positions)
+2024-11-18 09:56:43,367 - Dictionary lifecycle event {'msg': "built Dictionary<1087 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2224 corpus positions)", 'datetime': '2024-11-18T09:56:43.367214', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:56:43,368 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:56:43,368 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:56:43,368 - using serial LDA version on this node
+2024-11-18 09:56:43,368 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:56:43,368 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:56:43,372 - -8.045 per-word bound, 264.1 perplexity estimate based on a held-out corpus of 1 documents with 2224 words
+2024-11-18 09:56:43,372 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:56:43,373 - topic #0 (0.333): 0.019*"’" + 0.008*"Northamptonshire" + 0.008*"West" + 0.008*"well" + 0.007*"quality" + 0.006*"needs" + 0.005*"practice" + 0.005*"NCT" + 0.005*"3" + 0.005*"experiences"
+2024-11-18 09:56:43,373 - topic #1 (0.333): 0.014*"’" + 0.008*"Northamptonshire" + 0.006*"quality" + 0.005*"West" + 0.005*"practice" + 0.004*"impact" + 0.004*"need" + 0.004*"plans" + 0.004*"well" + 0.004*"experiences"
+2024-11-18 09:56:43,373 - topic #2 (0.333): 0.018*"’" + 0.007*"Northamptonshire" + 0.006*"well" + 0.006*"quality" + 0.005*"practice" + 0.005*"NCT" + 0.005*"However" + 0.005*"West" + 0.005*"plans" + 0.005*"14"
+2024-11-18 09:56:43,374 - topic diff=0.763004, rho=1.000000
+2024-11-18 09:56:43,374 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1087, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:56:43.374117', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:56:44,201 - Inspection date 2022-10-03 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:56:44,201 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:44,201 - Inspection date 2022-10-03 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:56:44,201 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:44,202 - Inspection date 2022-10-03 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:56:44,202 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:44,202 - Inspection date 2022-10-03 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:56:44,202 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:44,202 - Inspection date 2022-10-03 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:56:44,202 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:44,202 - Inspection date 2022-10-03 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:56:44,202 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:56,054 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:56:56,056 - built Dictionary<1233 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2720 corpus positions)
+2024-11-18 09:56:56,057 - Dictionary lifecycle event {'msg': "built Dictionary<1233 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2720 corpus positions)", 'datetime': '2024-11-18T09:56:56.057079', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:56:56,058 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:56:56,058 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:56:56,058 - using serial LDA version on this node
+2024-11-18 09:56:56,059 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:56:56,059 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:56:56,066 - -8.123 per-word bound, 278.8 perplexity estimate based on a held-out corpus of 1 documents with 2720 words
+2024-11-18 09:56:56,066 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:56:56,068 - topic #0 (0.333): 0.015*"’" + 0.007*"plans" + 0.007*"well" + 0.006*"Sussex" + 0.005*"needs" + 0.005*"West" + 0.005*"number" + 0.005*"quality" + 0.005*"13" + 0.004*"health"
+2024-11-18 09:56:56,068 - topic #1 (0.333): 0.016*"’" + 0.006*"well" + 0.006*"plans" + 0.006*"needs" + 0.006*"West" + 0.005*"practice" + 0.005*"supported" + 0.004*"number" + 0.004*"13" + 0.004*"Sussex"
+2024-11-18 09:56:56,069 - topic #2 (0.333): 0.009*"’" + 0.005*"needs" + 0.005*"13" + 0.004*"plans" + 0.004*"Sussex" + 0.004*"well" + 0.004*"24" + 0.004*"practice" + 0.004*"good" + 0.003*"actively"
+2024-11-18 09:56:56,069 - topic diff=0.815061, rho=1.000000
+2024-11-18 09:56:56,069 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1233, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:56:56.069404', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:56:57,030 - Inspection date 2023-03-13 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:56:57,030 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:57,030 - Inspection date 2023-03-13 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:56:57,030 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:57,031 - Inspection date 2023-03-13 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:56:57,031 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:57,031 - Inspection date 2023-03-13 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:56:57,031 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:57,031 - Inspection date 2023-03-13 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:56:57,031 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:56:57,031 - Inspection date 2023-03-13 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:56:57,031 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:08,996 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:57:08,998 - built Dictionary<1076 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2451 corpus positions)
+2024-11-18 09:57:08,998 - Dictionary lifecycle event {'msg': "built Dictionary<1076 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2451 corpus positions)", 'datetime': '2024-11-18T09:57:08.998956', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:57:09,000 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:57:09,000 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:57:09,000 - using serial LDA version on this node
+2024-11-18 09:57:09,000 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:57:09,000 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:57:09,004 - -7.963 per-word bound, 249.5 perplexity estimate based on a held-out corpus of 1 documents with 2451 words
+2024-11-18 09:57:09,004 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:57:09,005 - topic #0 (0.333): 0.014*"’" + 0.009*"needs" + 0.009*"Westmorland" + 0.007*"plans" + 0.007*"Furness" + 0.007*"need" + 0.006*"appropriate" + 0.006*"protection" + 0.005*"well" + 0.005*"progress"
+2024-11-18 09:57:09,005 - topic #1 (0.333): 0.010*"’" + 0.005*"plans" + 0.005*"Furness" + 0.005*"quality" + 0.004*"protection" + 0.004*"appropriate" + 0.004*"Westmorland" + 0.004*"needs" + 0.004*"3" + 0.004*"April"
+2024-11-18 09:57:09,005 - topic #2 (0.333): 0.013*"’" + 0.009*"plans" + 0.006*"appropriate" + 0.006*"Furness" + 0.006*"need" + 0.006*"quality" + 0.005*"progress" + 0.005*"needs" + 0.004*"Westmorland" + 0.004*"22"
+2024-11-18 09:57:09,005 - topic diff=0.815170, rho=1.000000
+2024-11-18 09:57:09,006 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1076, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:57:09.005992', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:57:09,834 - Inspection date 2024-04-22 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:57:09,834 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:09,835 - Inspection date 2024-04-22 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:57:09,835 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:09,835 - Inspection date 2024-04-22 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:57:09,835 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:09,835 - Inspection date 2024-04-22 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:57:09,835 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:09,835 - Inspection date 2024-04-22 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:57:09,835 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:09,836 - Inspection date 2024-04-22 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:57:09,836 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:19,849 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:57:19,851 - built Dictionary<1064 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2416 corpus positions)
+2024-11-18 09:57:19,851 - Dictionary lifecycle event {'msg': "built Dictionary<1064 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2416 corpus positions)", 'datetime': '2024-11-18T09:57:19.851356', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:57:19,852 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:57:19,852 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:57:19,852 - using serial LDA version on this node
+2024-11-18 09:57:19,853 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:57:19,853 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:57:19,856 - -7.961 per-word bound, 249.2 perplexity estimate based on a held-out corpus of 1 documents with 2416 words
+2024-11-18 09:57:19,856 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:57:19,857 - topic #0 (0.333): 0.014*"’" + 0.008*"May" + 0.006*"plans" + 0.006*"practice" + 0.006*"appropriate" + 0.006*"needs" + 0.005*"Wigan" + 0.005*"quality" + 0.004*"leaders" + 0.004*"20"
+2024-11-18 09:57:19,858 - topic #1 (0.333): 0.013*"’" + 0.008*"May" + 0.007*"plans" + 0.006*"quality" + 0.006*"Wigan" + 0.006*"practice" + 0.006*"9" + 0.006*"appropriate" + 0.005*"needs" + 0.005*"2022"
+2024-11-18 09:57:19,858 - topic #2 (0.333): 0.010*"’" + 0.007*"practice" + 0.007*"needs" + 0.006*"May" + 0.006*"plans" + 0.006*"Wigan" + 0.005*"leaders" + 0.005*"quality" + 0.004*"timely" + 0.004*"well"
+2024-11-18 09:57:19,858 - topic diff=0.790780, rho=1.000000
+2024-11-18 09:57:19,858 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1064, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:57:19.858491', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:57:20,711 - Inspection date 2022-05-09 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:57:20,711 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:20,711 - Inspection date 2022-05-09 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:57:20,711 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:20,712 - Inspection date 2022-05-09 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:57:20,712 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:20,712 - Inspection date 2022-05-09 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:57:20,712 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:20,712 - Inspection date 2022-05-09 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:57:20,712 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:20,712 - Inspection date 2022-05-09 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:57:20,712 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:30,665 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:57:30,668 - built Dictionary<1090 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2600 corpus positions)
+2024-11-18 09:57:30,668 - Dictionary lifecycle event {'msg': "built Dictionary<1090 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2600 corpus positions)", 'datetime': '2024-11-18T09:57:30.668270', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:57:30,669 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:57:30,669 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:57:30,669 - using serial LDA version on this node
+2024-11-18 09:57:30,669 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:57:30,670 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:57:30,673 - -7.952 per-word bound, 247.6 perplexity estimate based on a held-out corpus of 1 documents with 2600 words
+2024-11-18 09:57:30,673 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:57:30,674 - topic #0 (0.333): 0.015*"’" + 0.010*"well" + 0.007*"including" + 0.006*"needs" + 0.006*"progress" + 0.006*"Wiltshire" + 0.006*"need" + 0.006*"parents" + 0.005*"quality" + 0.005*"plans"
+2024-11-18 09:57:30,674 - topic #1 (0.333): 0.014*"’" + 0.012*"well" + 0.009*"needs" + 0.007*"need" + 0.006*"progress" + 0.005*"ensure" + 0.005*"parents" + 0.005*"risk" + 0.005*"29" + 0.005*"plans"
+2024-11-18 09:57:30,675 - topic #2 (0.333): 0.016*"’" + 0.011*"well" + 0.007*"risk" + 0.007*"Wiltshire" + 0.006*"needs" + 0.006*"supported" + 0.006*"need" + 0.006*"including" + 0.006*"parents" + 0.006*"plans"
+2024-11-18 09:57:30,675 - topic diff=0.826817, rho=1.000000
+2024-11-18 09:57:30,675 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1090, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:57:30.675239', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:57:31,559 - Inspection date 2023-09-25 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:57:31,560 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:31,560 - Inspection date 2023-09-25 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:57:31,560 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:31,560 - Inspection date 2023-09-25 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:57:31,560 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:31,560 - Inspection date 2023-09-25 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:57:31,560 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:31,560 - Inspection date 2023-09-25 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:57:31,560 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:31,561 - Inspection date 2023-09-25 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:57:31,561 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:42,524 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:57:42,526 - built Dictionary<1000 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2233 corpus positions)
+2024-11-18 09:57:42,526 - Dictionary lifecycle event {'msg': "built Dictionary<1000 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2233 corpus positions)", 'datetime': '2024-11-18T09:57:42.526816', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:57:42,527 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:57:42,527 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:57:42,528 - using serial LDA version on this node
+2024-11-18 09:57:42,528 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:57:42,528 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:57:42,531 - -7.909 per-word bound, 240.3 perplexity estimate based on a held-out corpus of 1 documents with 2233 words
+2024-11-18 09:57:42,531 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:57:42,532 - topic #0 (0.333): 0.012*"’" + 0.010*"needs" + 0.009*"Wirral" + 0.007*"ensure" + 0.007*"plans" + 0.006*"practice" + 0.006*"good" + 0.005*"response" + 0.005*"2023" + 0.005*"18"
+2024-11-18 09:57:42,533 - topic #1 (0.333): 0.012*"’" + 0.008*"needs" + 0.007*"plans" + 0.006*"small" + 0.006*"well" + 0.006*"Wirral" + 0.006*"ensure" + 0.005*"practice" + 0.005*"number" + 0.005*"risk"
+2024-11-18 09:57:42,533 - topic #2 (0.333): 0.010*"needs" + 0.008*"ensure" + 0.008*"’" + 0.006*"Wirral" + 0.006*"practice" + 0.005*"plans" + 0.005*"well" + 0.005*"number" + 0.004*"29" + 0.004*"appropriate"
+2024-11-18 09:57:42,533 - topic diff=0.809956, rho=1.000000
+2024-11-18 09:57:42,533 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1000, num_topics=3, decay=0.5, chunksize=2000> in 0.00s', 'datetime': '2024-11-18T09:57:42.533403', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:57:43,490 - Inspection date 2023-09-18 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:57:43,490 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:43,491 - Inspection date 2023-09-18 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:57:43,491 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:43,491 - Inspection date 2023-09-18 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:57:43,491 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:43,491 - Inspection date 2023-09-18 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:57:43,491 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:43,491 - Inspection date 2023-09-18 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:57:43,491 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:43,491 - Inspection date 2023-09-18 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:57:43,491 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:54,004 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:57:54,006 - built Dictionary<1096 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2214 corpus positions)
+2024-11-18 09:57:54,006 - Dictionary lifecycle event {'msg': "built Dictionary<1096 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2214 corpus positions)", 'datetime': '2024-11-18T09:57:54.006419', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:57:54,007 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:57:54,007 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:57:54,007 - using serial LDA version on this node
+2024-11-18 09:57:54,008 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:57:54,008 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:57:54,011 - -8.060 per-word bound, 266.9 perplexity estimate based on a held-out corpus of 1 documents with 2214 words
+2024-11-18 09:57:54,011 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:57:54,013 - topic #0 (0.333): 0.011*"’" + 0.007*"plans" + 0.007*"needs" + 0.006*"progress" + 0.005*"well" + 0.005*"17" + 0.005*"impact" + 0.005*"provided" + 0.005*"experiences" + 0.005*"effective"
+2024-11-18 09:57:54,013 - topic #1 (0.333): 0.014*"’" + 0.007*"effective" + 0.007*"plans" + 0.006*"progress" + 0.006*"well" + 0.005*"provided" + 0.005*"needs" + 0.005*"experiences" + 0.004*"ensure" + 0.004*"March"
+2024-11-18 09:57:54,013 - topic #2 (0.333): 0.012*"’" + 0.006*"plans" + 0.006*"effective" + 0.006*"needs" + 0.005*"quality" + 0.005*"progress" + 0.005*"17" + 0.004*"parents" + 0.004*"well" + 0.004*"6"
+2024-11-18 09:57:54,013 - topic diff=0.751691, rho=1.000000
+2024-11-18 09:57:54,013 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1096, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:57:54.013628', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:57:54,807 - Inspection date 2023-03-06 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:57:54,807 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:54,808 - Inspection date 2023-03-06 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:57:54,808 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:54,808 - Inspection date 2023-03-06 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:57:54,808 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:54,808 - Inspection date 2023-03-06 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:57:54,808 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:54,808 - Inspection date 2023-03-06 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:57:54,808 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:57:54,808 - Inspection date 2023-03-06 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:57:54,809 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:58:04,442 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:58:04,444 - built Dictionary<1095 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2233 corpus positions)
+2024-11-18 09:58:04,444 - Dictionary lifecycle event {'msg': "built Dictionary<1095 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2233 corpus positions)", 'datetime': '2024-11-18T09:58:04.444545', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:58:04,445 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:58:04,445 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:58:04,445 - using serial LDA version on this node
+2024-11-18 09:58:04,446 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:58:04,446 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:58:04,449 - -8.048 per-word bound, 264.7 perplexity estimate based on a held-out corpus of 1 documents with 2233 words
+2024-11-18 09:58:04,449 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:58:04,451 - topic #0 (0.333): 0.018*"’" + 0.009*"needs" + 0.006*"Wolverhampton" + 0.006*"effective" + 0.006*"risks" + 0.005*"risk" + 0.005*"leaders" + 0.005*"plans" + 0.005*"quality" + 0.005*"receive"
+2024-11-18 09:58:04,451 - topic #1 (0.333): 0.011*"’" + 0.007*"needs" + 0.006*"plans" + 0.006*"supported" + 0.005*"quality" + 0.005*"effective" + 0.005*"Wolverhampton" + 0.005*"receive" + 0.004*"education" + 0.004*"leaders"
+2024-11-18 09:58:04,451 - topic #2 (0.333): 0.011*"’" + 0.006*"effective" + 0.006*"needs" + 0.005*"well" + 0.004*"Wolverhampton" + 0.004*"risks" + 0.004*"education" + 0.004*"leaders" + 0.004*"strong" + 0.004*"receive"
+2024-11-18 09:58:04,451 - topic diff=0.739746, rho=1.000000
+2024-11-18 09:58:04,451 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1095, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:58:04.451665', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:58:05,288 - Inspection date 2022-03-28 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:58:05,288 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:58:05,288 - Inspection date 2022-03-28 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:58:05,288 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:58:05,289 - Inspection date 2022-03-28 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:58:05,289 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:58:05,289 - Inspection date 2022-03-28 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:58:05,289 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:58:05,289 - Inspection date 2022-03-28 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:58:05,289 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:58:05,289 - Inspection date 2022-03-28 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:58:05,289 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:58:16,325 - adding document #0 to Dictionary<0 unique tokens: []>
+2024-11-18 09:58:16,327 - built Dictionary<1041 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2343 corpus positions)
+2024-11-18 09:58:16,327 - Dictionary lifecycle event {'msg': "built Dictionary<1041 unique tokens: ['0161', '0300', '1', '10', '11']...> from 1 documents (total 2343 corpus positions)", 'datetime': '2024-11-18T09:58:16.327453', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:58:16,328 - using symmetric alpha at 0.3333333333333333
+2024-11-18 09:58:16,328 - using symmetric eta at 0.3333333333333333
+2024-11-18 09:58:16,328 - using serial LDA version on this node
+2024-11-18 09:58:16,329 - running online (single-pass) LDA training, 3 topics, 1 passes over the supplied corpus of 1 documents, updating model once every 1 documents, evaluating perplexity every 1 documents, iterating 50x with a convergence threshold of 0.001000
+2024-11-18 09:58:16,329 - too few updates, training might not converge; consider increasing the number of passes or iterations to improve accuracy
+2024-11-18 09:58:16,332 - -7.944 per-word bound, 246.3 perplexity estimate based on a held-out corpus of 1 documents with 2343 words
+2024-11-18 09:58:16,332 - PROGRESS: pass 0, at document #1/1
+2024-11-18 09:58:16,333 - topic #0 (0.333): 0.014*"’" + 0.008*"well" + 0.007*"plans" + 0.007*"leaders" + 0.006*"Worcestershire" + 0.006*"needs" + 0.005*"progress" + 0.005*"appropriate" + 0.005*"15" + 0.004*"making"
+2024-11-18 09:58:16,334 - topic #1 (0.333): 0.023*"’" + 0.009*"well" + 0.009*"needs" + 0.007*"progress" + 0.007*"Worcestershire" + 0.006*"plans" + 0.006*"appropriate" + 0.006*"ensure" + 0.005*"26" + 0.005*"leaders"
+2024-11-18 09:58:16,334 - topic #2 (0.333): 0.019*"’" + 0.010*"plans" + 0.008*"leaders" + 0.008*"well" + 0.008*"Worcestershire" + 0.007*"needs" + 0.007*"ensure" + 0.006*"progress" + 0.005*"PAs" + 0.005*"Senior"
+2024-11-18 09:58:16,334 - topic diff=0.808035, rho=1.000000
+2024-11-18 09:58:16,334 - LdaModel lifecycle event {'msg': 'trained LdaModel<num_terms=1041, num_topics=3, decay=0.5, chunksize=2000> in 0.01s', 'datetime': '2024-11-18T09:58:16.334455', 'gensim': '4.3.3', 'python': '3.10.13 (main, Jul 11 2024, 16:23:02) [GCC 9.4.0]', 'platform': 'Linux-6.5.0-1025-azure-x86_64-with-glibc2.31', 'event': 'created'}
+2024-11-18 09:58:17,299 - Inspection date 2023-05-15 / Column 'overall_effectiveness' not found in the DataFrame.
+2024-11-18 09:58:17,299 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:58:17,299 - Inspection date 2023-05-15 / Column 'impact_of_leaders' not found in the DataFrame.
+2024-11-18 09:58:17,299 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:58:17,299 - Inspection date 2023-05-15 / Column 'help_and_protection' not found in the DataFrame.
+2024-11-18 09:58:17,299 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:58:17,300 - Inspection date 2023-05-15 / Column 'in_care' not found in the DataFrame.
+2024-11-18 09:58:17,300 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:58:17,300 - Inspection date 2023-05-15 / Column 'care_leavers' not found in the DataFrame.
+2024-11-18 09:58:17,300 - Index(['judgement', 'grade'], dtype='object')
+2024-11-18 09:58:17,300 - Inspection date 2023-05-15 / Column 'in_care_and_care_leavers' not found in the DataFrame.
+2024-11-18 09:58:17,300 - Index(['judgement', 'grade'], dtype='object')