Bug fixes

src/file_processing.py

@@ -13,6 +13,8 @@ import merge_funcs
 
 def process_file(file_object):
     """
+    file_object = (filename , "file contents in one string"}
+
     Processes a single file object containing text data from a contract.
 
     This function orchestrates the full processing workflow for a single document, including:
@@ -70,10 +72,10 @@ def process_file(file_object):
     
     ################## RUN POSTPROCESSING ##################
     # combined_df = combined_df.applymap(postprocessingfuncs.sanitize_value) # Deprecated
-    combined_df = combined_df.apply(lambda x: x.map(postprocessingfuncs.sanitize_value))
+
 
     post_processed_combined_df = postprocess.postprocess_results(combined_df)
-    post_processed_combined_df.to_csv(os.path.join(output_dir, config.PROCESSED_RESULTS_NAME), index=False)
+    post_processed_combined_df.to_excel(os.path.join(output_dir, config.PROCESSED_RESULTS_NAME), index=False)
     print(f"Postprocessing Complete - {filename} ")
         
     print(f"Output Complete - {filename} ")

src/prompt_funcs.py

@@ -10,7 +10,7 @@ import utils
 import postprocessingfuncs
 
 def get_least_similar(dict_list, original_dict, field):
-    print(f"Running similarity for {field}")
+    # print(f"Running similarity for {field}")
     
     min_similarity = float('inf')
     least_similar_dict = None
@@ -31,7 +31,7 @@ def get_least_similar(dict_list, original_dict, field):
     return least_similar_dict
 
 def get_lesser_of_dict(dict_list, original_dict):
-    
+
     unique_rates = list({d['REIMBURSEMENT_RATE'] for d in dict_list})
     unique_fees = list({d['REIMBURSEMENT_FLAT_FEE'] for d in dict_list})