update gensim to 4.3.2

data/nlp/text_summarization.py

@@ -10,7 +10,7 @@
 # output dataset name
 output_dataset_name = "data_with_summary"
 
-_global_modules_needed_by_name = ["gensim==3.8.0"]
+_global_modules_needed_by_name = ["gensim==4.3.2"]
 
 
 class TextSummarizationClass(CustomData):

data/nlp/topic_modeling.py

@@ -20,7 +20,7 @@
 # number of top words to be represented in the column name
 n_words_colname = 10
 
-_global_modules_needed_by_name = ["gensim==3.8.0"]
+_global_modules_needed_by_name = ["gensim==4.3.2"]
 
 stop_words = ['i', 'me', 'my', 'myself', 'we', 'our', 'ours', 'ourselves', 'you', "you're", "you've", "you'll", "you'd",
               'your', 'yours', 'yourself', 'yourselves', 'he', 'him', 'his', 'himself', 'she', "she's", 'her', 'hers',

models/unsupervised/TextKMeansIsolationForest.py

@@ -214,7 +214,7 @@ class TextLDATopicUnsupervisedTransformer(CustomUnsupervisedTransformer):
     """Transformer to extract topics from text column using LDA"""
     _is_reproducible = False
     _testing_can_skip_failure = False  # ensure tested as if shouldn't fail
-    _modules_needed_by_name = ["gensim==3.8.0"]
+    _modules_needed_by_name = ["gensim==4.3.2"]
 
     def __init__(self, n_topics, **kwargs):
         super().__init__(**kwargs)

models/unsupervised/lda.py

@@ -11,7 +11,7 @@ class TextLDATopicTransformer(CustomUnsupervisedTransformer):
     """Transformer to extract topics from text column using LDA"""
     _is_reproducible = False
     _testing_can_skip_failure = False  # ensure tested as if shouldn't fail
-    _modules_needed_by_name = ["gensim==3.8.0"]
+    _modules_needed_by_name = ["gensim==4.3.2"]
 
     def __init__(self, n_topics, **kwargs):
         super().__init__(**kwargs)

transformers/nlp/text_embedding_similarity_transformers.py

@@ -9,7 +9,7 @@
 class EmbeddingSimilarityTransformer(CustomTransformer):
     _unsupervised = True
 
-    _modules_needed_by_name = ["gensim==3.8.0", 'regex==2024.5.15', 'flair==0.4.1', 'segtok==1.5.7']
+    _modules_needed_by_name = ["gensim==4.3.2", 'regex==2024.5.15', 'flair==0.4.1', 'segtok==1.5.7']
     _is_reproducible = False
     _can_use_gpu = True
     _repl_val = 0

transformers/nlp/text_topic_modeling_transformer.py

@@ -11,7 +11,7 @@ class TextLDATopicTransformer(CustomTransformer):
     """Transformer to extract topics from text column using LDA"""
     _is_reproducible = False
     _testing_can_skip_failure = False  # ensure tested as if shouldn't fail
-    _modules_needed_by_name = ["gensim==3.8.0"]
+    _modules_needed_by_name = ["gensim==4.3.2"]
 
     def __init__(self, n_topics, **kwargs):
         super().__init__(**kwargs)

transformers/nlp/text_url_summary_transformer.py

@@ -9,7 +9,7 @@ class TextURLSummaryTransformer(CustomTransformer):
 
     _numeric_output = False
     _testing_can_skip_failure = False  # ensure tested as if shouldn't fail
-    _modules_needed_by_name = ["gensim==3.8.0", "beautifulsoup4==4.9.2"]
+    _modules_needed_by_name = ["gensim==4.3.2", "beautifulsoup4==4.9.2"]
     _display_name = 'TextURLSummaryTransformer'
 
     @staticmethod