Update app.py

app.py

@@ -353,7 +353,6 @@ def extract_problem_domains(df,
             # top_words = [feature_names[index] for index in top_word_indices]
             # cluster_representations[i] = top_words
 
-
             try:
                 center = kmeans.cluster_centers_[i]
                 console_messages.append(f"Processing cluster {i}")
@@ -361,28 +360,28 @@ def extract_problem_domains(df,
                 
                 if not isinstance(center, np.ndarray):
                     center = np.array(center)
-                    
-                sorted_indices = center.argsort()
-                if isinstance(sorted_indices, list):
-                    sorted_indices = np.array(sorted_indices)
-                    
+                
+                # Remove NaN values
+                center = center[~np.isnan(center)]
+                
+                sorted_indices = np.array(center.argsort())
+                
                 top_word_indices = sorted_indices[-top_words:][::-1]
-
-                    
-                # Debug output
-                console_messages.append(f"Sorted indices: {sorted_indices}")
-                console_messages.append(f"Top word indices for cluster {i}: {top_word_indices}")
-
+                
+                # Check for valid indices
+                if np.any(top_word_indices < 0) or np.any(top_word_indices >= len(feature_names)):
+                    console_messages.append(f"Invalid top word indices for cluster {i}")
+                    continue
+                
                 top_words = [feature_names[index] for index in top_word_indices]
                 console_messages.append(f"Top words: {top_words}")
                 cluster_representations[i] = top_words
                 
-
-                
             except Exception as e:
                 console_messages.append(f"Error processing cluster {i}: {str(e)}")
                 console_messages.append(f"Center: {center}")
                 
+                
 
         console_messages.append(f"Number of clusters: {optimal_n_clusters}")
         console_messages.append(f"Sample cluster words: {cluster_representations[0][:5]}...")