Update app.py

app.py

@@ -169,24 +169,25 @@ def generate_bar_chart(df, num_clusters_to_display):
     img = Image.open(buf)
     return img
 
-def main(file, num_clusters_to_display):
+def main(file, num_categories_to_display):
     try:
         df = pd.read_csv(file)
         
-        # Filter by 'Fallback Message shown'
-        df = df[df['Answer'] == 'Fallback Message shown']
         
         df = preprocess_data(df)
+
+        df = df[df['Category'] != 'Miscellaneous']
         
-        # Get category sizes and sort by size in ascending order
+        # Get category sizes and sort by size in descending order
         category_sizes = df['Category'].value_counts().reset_index()
         category_sizes.columns = ['Category', 'Count']
         sorted_categories = category_sizes.sort_values(by='Count', ascending=False)['Category'].tolist()
         sorted_categories_sm = category_sizes.sort_values(by='Count', ascending=True)['Category'].tolist()
+
         
-        # Get the largest x categories as specified by num_clusters_to_display
-        largest_categories = sorted_categories[:num_clusters_to_display]
-        smallest_categories = sorted_categories[:num_clusters_to_display]
+        # Get the largest x categories as specified by num_categories_to_display
+        largest_categories = sorted_categories[:num_categories_to_display]
+        smallest_categories = sorted_categories_sm[:num_categories_to_display]
         
         # Filter the dataframe to include only the largest categories
         filtered_df = df[df['Category'].isin(largest_categories)]
@@ -196,18 +197,15 @@ def main(file, num_clusters_to_display):
         filtered_df = filtered_df.sort_values(by='Category')
         filtered_cloud_df = filtered_cloud_df.sort_values(by='Category')
         
-        wordcloud_img = generate_wordcloud(filtered_cloud_df)
-        bar_chart_img = generate_bar_chart(filtered_df, num_clusters_to_display)
+        wordcloud_img = generate_wordcloud(filtered_cloud_df)  # Word cloud based on the entire dataframe
+        bar_chart_img = generate_bar_chart(df, num_categories_to_display)  # Bar chart based on the filtered dataframe
 
         with tempfile.NamedTemporaryFile(delete=False, suffix=".csv") as tmpfile:
             filtered_df.to_csv(tmpfile.name, index=False)
-            csv_file_path = tmpfile.name
-
-        return csv_file_path, wordcloud_img, bar_chart_img
-    except Exception as e:
         print(f"Error: {e}")
         return str(e), None, None
 
+
 interface = gr.Interface(
     fn=main,
     inputs=[