Update app.py

app.py

@@ -194,7 +194,14 @@ def main(file, num_clusters_to_display):
         df = df[df['Answer'] == 'Fallback Message shown']
         
         df = preprocess_data(df)
-
+        
+        # Perform clustering before categorization
+        num_clusters = 5  # Or any other appropriate number of clusters
+        df, kmeans = cluster_data(df, num_clusters)
+        
+        # Categorize the texts after clustering
+        df['Category'] = df['texts'].apply(categorize_question)
+        
         df = df[df['Category'] != 'Miscellaneous']
         
         # Get category sizes and sort by size in ascending order
@@ -211,8 +218,8 @@ def main(file, num_clusters_to_display):
         filtered_df = df[df['Category'].isin(largest_categories)]
         filtered_cloud_df = df[df['Category'].isin(smallest_categories)]
         
-        # Sort the dataframe by Category
-        filtered_df = filtered_df.sort_values(by='Category')
+        # Sort the dataframe by Category and Cluster
+        filtered_df = filtered_df.sort_values(by=['Category', 'Cluster'])
         filtered_cloud_df = filtered_cloud_df.sort_values(by='Category')
         
         wordcloud_img = generate_wordcloud(filtered_cloud_df)
@@ -242,4 +249,3 @@ interface = gr.Interface(
 )
 
 interface.launch(share=True)
-