Update app.py

app.py

@@ -2,6 +2,7 @@ import gradio as gr
 from transformers import pipeline
 import pandas as pd
 import spaces
+import plotly.express as px
 
 # Load dataset
 from datasets import load_dataset
@@ -37,6 +38,56 @@ def classify_comments(categories):
     df['comment_category'] = assigned_categories
     return df[['customer_comment', 'comment_sentiment', 'comment_category']].to_html(index=False)
 
+# Function to generate visualizations
+def visualize_output():
+    # 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()
+
+    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)}
+    """
+
+    return sentiment_pie, category_pie, stacked_bar, kpi_visualization
+
 # Gradio Interface
 with gr.Blocks() as nps:
     # State to store categories
@@ -68,6 +119,13 @@ with gr.Blocks() as nps:
     classify_btn = gr.Button("Classify Comments")
     output = gr.HTML()
 
+    # Visualize button
+    visualize_btn = gr.Button("Visualize Output")
+    sentiment_pie = gr.Plot(label="Sentiment Distribution")
+    category_pie = gr.Plot(label="Comment Category Distribution")
+    stacked_bar = gr.Plot(label="Sentiment by Comment Category")
+    kpi_visualization = gr.Markdown()
+
     # Function to load data from uploaded CSV
     def load_data(file):
         if file is not None:
@@ -76,8 +134,10 @@ with gr.Blocks() as nps:
                 custom_df = pd.read_csv(file, encoding='utf-8')
             else:
                 return "Error: Uploaded file is not a CSV."
-            if 'customer_comment' not in custom_df.columns:
-                return "Error: Uploaded CSV must contain a column named 'customer_comment'"
+            # Check for required columns
+            required_columns = ['customer_comment', 'customer_nps']
+            if not all(col in custom_df.columns for col in required_columns):
+                return f"Error: Uploaded CSV must contain the following columns: {', '.join(required_columns)}"
             global df
             df = custom_df
             return "Custom CSV loaded successfully!"
@@ -113,5 +173,9 @@ with gr.Blocks() as nps:
         inputs=categories,
         outputs=output
     )
+    visualize_btn.click(
+        fn=visualize_output,
+        outputs=[sentiment_pie, category_pie, stacked_bar, kpi_visualization]
+    )
 
 nps.launch(share=True)