Remove bag of words size from main

text_based_datasets_experiment.py

@@ -54,11 +54,11 @@ def run_gnn(structuredDataset: Base, entity_name, datasetName, results_dir):
         
     return model
 
-def load_datasets(dataset_name, bag_of_words_size) -> Base:
+def load_datasets(dataset_name) -> Base:
     if dataset_name == 'dblp':
-        return DBLP(bag_of_words_size=bag_of_words_size)
+        return DBLP()
     else:
-        return IMDB(bag_of_words_size=bag_of_words_size)
+        return IMDB()
     
 def fetch_high_level_concepts(dataset: Base, num_groups, group_keyword_file):
     return dataset.fetch_themes(num_groups, group_keyword_file)
@@ -206,7 +206,7 @@ def summarize_aggregated_results(aggregated_results, results_dir, dataset_name):
 
     print(f"Summary results saved to {summary_filename}")
 
-def experiment(grouped_keyword_dir, dataset_name, entity_name, iterations=5, num_groups_list=[0, 5, 10, 15, 20, 25], create_high_level_concepts_as_boolean=True, bag_of_words_size=300, selected_labels=None):
+def experiment(grouped_keyword_dir, dataset_name, entity_name, iterations=5, num_groups_list=[0, 5, 10, 15, 20, 25], create_high_level_concepts_as_boolean=True, selected_labels=None):
     """
     Handles dataset loading and evaluation for experiments.
     Manages the experiment based on specified number of groups and boolean concept creation settings.
@@ -228,7 +228,7 @@ def experiment(grouped_keyword_dir, dataset_name, entity_name, iterations=5, num
         # Create run-specific directory
         run_dir = create_directory(results_dir, f"run_{run}")
         
-        dataset = load_datasets(dataset_name=dataset_name, bag_of_words_size=bag_of_words_size)
+        dataset = load_datasets(dataset_name=dataset_name)
         model = run_gnn(dataset, entity_name, dataset_name, run_dir)
 
         write_header = True