Update app.py

app.py

@@ -199,7 +199,7 @@ from collections import Counter
 
 def extract_problem_domains(df, 
                             text_column='Processed_ProblemDescription_forDomainExtraction',
-                            cluster_range=(5, 15), 
+                            cluster_range=(5, 25), 
                             top_words=10):
     console_messages.append("Extracting Problem Domains...")
     
@@ -280,9 +280,14 @@ def text_processing_for_location(text):
     
 
 def extract_location_clusters(df, 
-                              text_column='Processed_LocationText_forClustering', 
-                              cluster_range=(3, 10), 
+                              text_column1='Processed_LocationText_forClustering', # Extracted through NLP
+                              text_column2='Geographical_Location', # User Input
+                              cluster_range=(5, 25), 
                               top_words=5):
+    # Combine the two text columns
+    text_column = "Combined_Location_Text"
+    df[text_column] = df[text_column1] + ' ' + df[text_column2]
+    
     console_messages.append("Extracting Location Clusters...")
     
     # Sentence Transformers approach for embeddings
@@ -313,7 +318,8 @@ def extract_location_clusters(df,
     # Map cluster labels to representative words
     df["Location_Cluster"] = cluster_labels
     df['Location_Category_Words'] = [cluster_representations[label] for label in cluster_labels]
-    
+
+    df = df.drop(text_column, axis=1)
     console_messages.append("Location Clustering completed.")    
     return df, optimal_n_clusters