Update app.py

app.py

@@ -346,7 +346,6 @@ def extract_problem_domains(df,
             
             # console_messages.append(f"top_words: {top_words}, type: {type(top_words)}")
             # console_messages.append(f"center.argsort(): {center.argsort()}, type: {type(center.argsort())}")
-
             
             # # top_word_indices = center.argsort()[-top_words:][::-1]
             # top_word_indices = center.argsort()[-top_words:][::-1].tolist() # Indexes of top words
@@ -354,24 +353,33 @@ 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}")
                 # console_messages.append(f"Center shape: {center.shape}, type: {type(center)}")
                 
-                top_word_indices = center.argsort()[-top_words:][::-1].tolist()
-                # console_messages.append(f"Top word indices: {top_word_indices}")
+                if isinstance(center, np.ndarray) and center.ndim == 1:
+                    top_word_indices = center.argsort()[-top_words:][::-1]
+                    # top_word_indices = center.argsort()[-top_words:][::-1].tolist()
+                    
+                    console_messages.append(f"Top word indices for cluster {i}: {top_word_indices}")
+                    top_words = [feature_names[index] for index in top_word_indices]
+                    console_messages.append(f"Top words: {top_words}")
+                    cluster_representations[i] = top_words
+                else:
+                    console_messages.append(f"Error: Cluster center is not a 1D array for cluster {i}")
                 
-                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}")
 
 
+            try:
+                center = kmeans.cluster_centers_[i]
+                print(f"Center for cluster {i}: {center}")
+                
+
         console_messages.append(f"Number of clusters: {optimal_n_clusters}")
         console_messages.append(f"Sample cluster words: {cluster_representations[0][:5]}...")
     
@@ -390,12 +398,7 @@ def extract_problem_domains(df,
 
 
 
-
-
-
-
-
-
+    
 
 
 # def nlp_pipeline(original_df):