CU-8694vxbkh: Medcat v1.12 support (#14)

* CU-8694vxbkh: Remove use of deprecated method * CU-8694vxbkh: Bump medcat requirement to 1.12 * Pushing change to accommodate for changed signature The medcat.utils.meta_cat.data_utils.encode_category_values method has a different signature. In working_with_cogstack, the medcat/evaluate_mct_export/mct_analysis.py file relies on old behaviour. * CU-8694vxbkh: Pin spacy to working versions locally --------- Co-authored-by: shubham-s-agarwal <[email protected]>
CogStack · Oct 8, 2024 · 08d65ed · 08d65ed
1 parent 69a225d
commit 08d65ed
Show file tree

Hide file tree

Showing 3 changed files with 10 additions and 9 deletions.
diff --git a/medcat/2_train_model/2_supervised_training/supervised training.ipynb b/medcat/2_train_model/2_supervised_training/supervised training.ipynb
@@ -90,13 +90,13 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "cat.train_supervised(data_path=mctrainer_export_path, \n",
-    "                     nepochs=3,\n",
-    "                     reset_cui_count=False,\n",
-    "                     print_stats=True,\n",
-    "                     use_filters=True,\n",
-    "                     extra_cui_filter=snomed_filter,  # If not filter is set remove this line\n",
-    "                     )\n"
+    "cat.train_supervised_from_json(data_path=mctrainer_export_path, \n",
+    "                               nepochs=3,\n",
+    "                               reset_cui_count=False,\n",
+    "                               print_stats=True,\n",
+    "                               use_filters=True,\n",
+    "                               extra_cui_filter=snomed_filter,  # If not filter is set remove this line\n",
+    "                               )\n"
    ]
   },
   {

diff --git a/medcat/evaluate_mct_export/mct_analysis.py b/medcat/evaluate_mct_export/mct_analysis.py
@@ -313,7 +313,7 @@ def _eval(self, metacat_model, mct_export) -> dict:
 
         # We already have everything, just get the data
         category_value2id = g_config['category_value2id']
-        data, _ = encode_category_values(data, existing_category_value2id=category_value2id)
+        data, data_undersampled, _ = encode_category_values(data, existing_category_value2id=category_value2id)
         print(_)
         print(len(data))
         # Run evaluation

diff --git a/requirements.txt b/requirements.txt
@@ -1,4 +1,5 @@
-medcat~=1.10.2
+spacy<3.8.0
+medcat~=1.12.0
 plotly~=5.19.0
 eland==8.12.1
 en_core_web_md @ https://github.com/explosion/spacy-models/releases/download/en_core_web_md-3.6.0/en_core_web_md-3.6.0-py3-none-any.whl