Update app.py

app.py

@@ -173,18 +173,22 @@ def main(file, num_clusters_to_display):
         category_sizes = df['Category'].value_counts().reset_index()
         category_sizes.columns = ['Category', 'Count']
         sorted_categories = category_sizes.sort_values(by='Count', ascending=True)['Category'].tolist()
+        sorted_categories_sm = category_sizes.sort_values(by='Count', ascending=False)['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_sm[:num_clusters_to_display]
         
         # Filter the dataframe to include only the largest categories
         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')
+        filtered_cloud_df = filtered_cloud_df.sort_values(by='Category')
         
-        wordcloud_img = generate_wordcloud(filtered_df)
-        bar_chart_img = generate_bar_chart(filtered_df, num_clusters_to_display)
+        wordcloud_img = generate_wordcloud(filtered_cloud_df)
+        bar_chart_img = generate_bar_chart(df, num_clusters_to_display)
 
         with tempfile.NamedTemporaryFile(delete=False, suffix=".csv") as tmpfile:
             filtered_df.to_csv(tmpfile.name, index=False)