Update app.py

app.py

@@ -39,71 +39,88 @@ def classify_comments(categories):
     df['comment_category'] = assigned_categories
     return df[['customer_id', 'customer_comment', 'comment_sentiment', 'comment_category', 'customer_nps', 'customer_segment']].to_html(index=False)
 
-# Function to generate visualizations
 def visualize_output():
+    # Debug: Print the columns in the DataFrame
+    print("Columns in DataFrame:", df.columns.tolist())
+
     # Ensure the required columns exist
     if 'comment_sentiment' not in df.columns or 'comment_category' not in df.columns:
-        # Return 5 values (None for plots and an error message for markdown)
+        print("Error: Required columns missing. Please classify comments first.")
         return None, None, None, "Error: Please classify comments before visualizing.", None
 
-    # Pie Chart of Sentiment
-    sentiment_counts = df['comment_sentiment'].value_counts()
-    sentiment_pie = px.pie(
-        values=sentiment_counts.values,
-        names=sentiment_counts.index,
-        title="Sentiment Distribution",
-        hover_data=[sentiment_counts.values],
-        labels={'value': 'Count', 'names': 'Sentiment'}
-    )
-    sentiment_pie.update_traces(textinfo='percent+label', hovertemplate="Sentiment: %{label}<br>Count: %{value}<br>Percentage: %{percent}")
-
-    # Pie Chart of Comment Categories
-    category_counts = df['comment_category'].value_counts()
-    category_pie = px.pie(
-        values=category_counts.values,
-        names=category_counts.index,
-        title="Comment Category Distribution",
-        hover_data=[category_counts.values],
-        labels={'value': 'Count', 'names': 'Category'}
-    )
-    category_pie.update_traces(textinfo='percent+label', hovertemplate="Category: %{label}<br>Count: %{value}<br>Percentage: %{percent}")
-
-    # Stacked Bar Chart of Sentiment by Category
-    sentiment_by_category = df.groupby(['comment_category', 'comment_sentiment']).size().unstack()
-    stacked_bar = px.bar(
-        sentiment_by_category,
-        barmode='stack',
-        title="Sentiment by Comment Category",
-        labels={'value': 'Count', 'comment_category': 'Category', 'comment_sentiment': 'Sentiment'}
-    )
-
-    # KPI Visualizations
-    avg_nps = df['customer_nps'].mean()
-    avg_nps_positive = df[df['comment_sentiment'] == 'POSITIVE']['customer_nps'].mean()
-    avg_nps_negative = df[df['comment_sentiment'] == 'NEGATIVE']['customer_nps'].mean()
-    avg_nps_by_category = df.groupby('comment_category')['customer_nps'].mean().reset_index()
-    avg_nps_by_segment = df.groupby('customer_segment')['customer_nps'].mean().reset_index()
-
-    kpi_visualization = f"""
-    **Average NPS Scores:**
-    - Overall: {avg_nps:.2f}
-    - Positive Sentiment: {avg_nps_positive:.2f}
-    - Negative Sentiment: {avg_nps_negative:.2f}
-    **Average NPS by Category:**
-    {avg_nps_by_category.to_markdown(index=False)}
-    **Average NPS by Segment:**
-    {avg_nps_by_segment.to_markdown(index=False)}
-    """
-
-    # Pie Chart of Sentiment by Customer Segment
-    sentiment_by_segment = df.groupby(['customer_segment', 'comment_sentiment']).size().unstack()
-    sentiment_by_segment_pie = px.pie(
-        sentiment_by_segment,
-        title="Sentiment by Customer Segment",
-        labels={'value': 'Count', 'customer_segment': 'Segment', 'comment_sentiment': 'Sentiment'}
-    )
-
-    return sentiment_pie, category_pie, stacked_bar, kpi_visualization, sentiment_by_segment_pie
+    # Debug: Print the first few rows of the DataFrame
+    print("First few rows of DataFrame:")
+    print(df.head())
+
+    try:
+        # Pie Chart of Sentiment
+        sentiment_counts = df['comment_sentiment'].value_counts()
+        print("Sentiment counts:", sentiment_counts)
+        sentiment_pie = px.pie(
+            values=sentiment_counts.values,
+            names=sentiment_counts.index,
+            title="Sentiment Distribution",
+            hover_data=[sentiment_counts.values],
+            labels={'value': 'Count', 'names': 'Sentiment'}
+        )
+        sentiment_pie.update_traces(textinfo='percent+label', hovertemplate="Sentiment: %{label}<br>Count: %{value}<br>Percentage: %{percent}")
+
+        # Pie Chart of Comment Categories
+        category_counts = df['comment_category'].value_counts()
+        print("Category counts:", category_counts)
+        category_pie = px.pie(
+            values=category_counts.values,
+            names=category_counts.index,
+            title="Comment Category Distribution",
+            hover_data=[category_counts.values],
+            labels={'value': 'Count', 'names': 'Category'}
+        )
+        category_pie.update_traces(textinfo='percent+label', hovertemplate="Category: %{label}<br>Count: %{value}<br>Percentage: %{percent}")
+
+        # Stacked Bar Chart of Sentiment by Category
+        sentiment_by_category = df.groupby(['comment_category', 'comment_sentiment']).size().unstack()
+        print("Sentiment by Category:")
+        print(sentiment_by_category)
+        stacked_bar = px.bar(
+            sentiment_by_category,
+            barmode='stack',
+            title="Sentiment by Comment Category",
+            labels={'value': 'Count', 'comment_category': 'Category', 'comment_sentiment': 'Sentiment'}
+        )
+
+        # KPI Visualizations
+        avg_nps = df['customer_nps'].mean()
+        avg_nps_positive = df[df['comment_sentiment'] == 'POSITIVE']['customer_nps'].mean()
+        avg_nps_negative = df[df['comment_sentiment'] == 'NEGATIVE']['customer_nps'].mean()
+        avg_nps_by_category = df.groupby('comment_category')['customer_nps'].mean().reset_index()
+        avg_nps_by_segment = df.groupby('customer_segment')['customer_nps'].mean().reset_index()
+
+        kpi_visualization = f"""
+        **Average NPS Scores:**
+        - Overall: {avg_nps:.2f}
+        - Positive Sentiment: {avg_nps_positive:.2f}
+        - Negative Sentiment: {avg_nps_negative:.2f}
+        **Average NPS by Category:**
+        {avg_nps_by_category.to_markdown(index=False)}
+        **Average NPS by Segment:**
+        {avg_nps_by_segment.to_markdown(index=False)}
+        """
+
+        # Pie Chart of Sentiment by Customer Segment
+        sentiment_by_segment = df.groupby(['customer_segment', 'comment_sentiment']).size().unstack()
+        print("Sentiment by Segment:")
+        print(sentiment_by_segment)
+        sentiment_by_segment_pie = px.pie(
+            sentiment_by_segment,
+            title="Sentiment by Customer Segment",
+            labels={'value': 'Count', 'customer_segment': 'Segment', 'comment_sentiment': 'Sentiment'}
+        )
+
+        return sentiment_pie, category_pie, stacked_bar, kpi_visualization, sentiment_by_segment_pie
+
+    except Exception as e:
+        print(f"Error in visualize_output: {e}")
+        return None, None, None, f"Error: {str(e)}", None
 
 # Gradio Interface
 with gr.Blocks() as nps: