Update app.py

app.py

@@ -241,8 +241,8 @@ import numpy as np
 def extract_problem_domains(df, 
                             text_column='Processed_ProblemDescription_forDomainExtraction', 
                             # text_column='Problem_Description', 
-                            cluster_range=(10, 50), 
-                            top_words=30,
+                            cluster_range=(10, 25), 
+                            top_words=17,
                             method='sentence_transformers'
                             # method='tfidf_kmeans'
                            ):
@@ -375,10 +375,13 @@ def nlp_pipeline(original_df):
     
 
     # Starting the Pipeline for Domain Extraction
-    console_messages.append("Entering Text processing function for Domain identification")
+    console_messages.append("Executing Text processing function for Domain identification")
     # Apply the text_processing_for_domain function to the DataFrame
     processed_df['Processed_ProblemDescription_forDomainExtraction'] = processed_df['Problem_Description'].apply(text_processing_for_domain)
-    console_messages.append("Exiting Text processing function for Domain identification")
+    
+    console_messages.append("Removing entries which could not be allocated to any Problem Domain")
+    processed_df = processed_df.dropna(subset=['Processed_ProblemDescription_forDomainExtraction'], axis=0)
+    
 
     
     # Domain Clustering
@@ -459,7 +462,7 @@ interface = gr.Interface(
     
     outputs=[
         gr.File(label="Download the processed Excel File containing the ** Project Proposals ** for each Location~Problem paired combination"),  # File download output
-        gr.Textbox(label="Console Messages", lines=100, interactive=False)  # Console messages output
+        gr.Textbox(label="Console Messages", lines=25, interactive=False)  # Console messages output
         ],