Update app.py

app.py

@@ -314,7 +314,7 @@ def extract_location_clusters(df,
 
 
 
-
+import copy
 
 
 # def nlp_pipeline(original_df):
@@ -323,7 +323,6 @@ def nlp_pipeline(original_df):
     
     # Data Preprocessing
     processed_df = data_pre_processing(original_df) # merged_dataset
-    
 
     # Starting the Pipeline for Domain Extraction
     console_messages.append("Executing Text processing function for Domain identification")
@@ -334,44 +333,31 @@ def nlp_pipeline(original_df):
     # processed_df = processed_df.dropna(subset=['Processed_ProblemDescription_forDomainExtraction'], axis=0)
     # Drop rows where 'Processed_ProblemDescription_forDomainExtraction' contains empty arrays
     processed_df = processed_df[processed_df['Processed_ProblemDescription_forDomainExtraction'].apply(lambda x: len(x) > 0)]
-
-
     
     # Domain Clustering
     try:
-        domain_df, optimal_n_clusters = extract_problem_domains(processed_df)
-        # print(f"Optimal clusters: {optimal_clusters}")
-        # print(result_df.head())
-        # console_messages.append(f"Optimal clusters: {optimal_n_clusters}")
-
-        console_messages.append("NLP pipeline completed.")
-        return domain_df
+        processed_df, optimal_n_clusters = extract_problem_domains(processed_df)
+        console_messages.append(f"Optimal clusters for Domain extraction: {optimal_n_clusters}")
     except Exception as e:
-        # print(f"Error in extract_problem_domains: {e}")
         console_messages.append(f"Error in extract_problem_domains: {str(e)}")
-        return processed_df
-        # return domain_df
+    console_messages.append("NLP pipeline for Problem Domain extraction completed.")
 
     
-    # problem_clusters, problem_model = perform_clustering(processed_df['Problem_Description'], n_clusters=10)
-    # location_clusters, location_model = perform_clustering(processed_df['Geographical_Location'], n_clusters=5)
-    
-    console_messages.append("Starting NLP pipeline for location extraction...")
-    
+    console_messages.append("Starting NLP pipeline for Location extraction with text processing.")
     # Apply the text_processing_for_location function to the DataFrame
     processed_df['Processed_LocationText_forClustering'] = processed_df['Problem_Description'].apply(text_processing_for_location)
         
     # Location Clustering
     try:
-        location_df, optimal_n_clusters = extract_location_clusters(processed_df)
-        console_messages.append("NLP pipeline for location extraction completed.")
-        return location_df
+        processed_df, optimal_n_clusters = extract_location_clusters(processed_df)
+        console_messages.append(f"Optimal clusters for Location extraction: {optimal_n_clusters}")
     except Exception as e:
         console_messages.append(f"Error in extract_location_clusters: {str(e)}")
-        return processed_df
-
+    console_messages.append("NLP pipeline for location extraction completed.")
 
 
+    console_messages.append("NLP pipeline completed.")
+    return processed_df