Update app.py

app.py

@@ -137,18 +137,21 @@ def generate_wordcloud(df):
     return img
 
 def generate_bar_chart(df, num_clusters_to_display):
-    top_clusters = df['Cluster'].value_counts().index[1:num_clusters_to_display+1]
-    df_top_clusters = df[df['Cluster'].isin(top_clusters)]
+    # Exclude common words from the top words
+    common_words = {'i', 'you', 'thanks', 'thank', 'ok', 'okay', 'sure', 'done'}
     
-    cluster_top_words = df_top_clusters.groupby('Cluster', observed=False)['texts'].apply(lambda x: ' '.join(x)).reset_index()
-    cluster_top_words['top_word'] = cluster_top_words['texts'].apply(lambda x: pd.Series(x.split()).value_counts().index[0] if len(x.split()) > 0 else '')
-    cluster_sizes = df_top_clusters['Cluster'].value_counts().reset_index()
-    cluster_sizes.columns = ['Cluster', 'Count']
-    cluster_sizes = cluster_sizes.merge(cluster_top_words[['Cluster', 'top_word']], on='Cluster')
+    top_categories = df['Category'].value_counts().index[:num_clusters_to_display]
+    df_top_categories = df[df['Category'].isin(top_categories)]
     
-    fig = px.bar(cluster_sizes, x='Cluster', y='Count', text='top_word', title='Top Clusters by Frequency with Top Word/Phrase')
+    category_top_words = df_top_categories.groupby('Category', observed=False)['texts'].apply(lambda x: ' '.join(x)).reset_index()
+    category_top_words['top_word'] = category_top_words['texts'].apply(lambda x: ' '.join([word for word in pd.Series(x.split()).value_counts().index if word not in common_words][:3]))
+    category_sizes = df_top_categories['Category'].value_counts().reset_index()
+    category_sizes.columns = ['Category', 'Count']
+    category_sizes = category_sizes.merge(category_top_words[['Category', 'top_word']], on='Category')
+    
+    fig = px.bar(category_sizes, x='Category', y='Count', text='top_word', title='Category Frequency with Top Words (excluding common words)')
     fig.update_traces(textposition='outside')
-    fig.update_layout(xaxis_title='Cluster', yaxis_title='Frequency', showlegend=False)
+    fig.update_layout(xaxis_title='Category', yaxis_title='Frequency', showlegend=False)
     
     buf = BytesIO()
     fig.write_image(buf, format='png')