Update app.py

app.py

@@ -21,11 +21,14 @@ classifier = pipeline("text-classification", model="distilbert/distilbert-base-u
 generator = pipeline("text2text-generation", model="google/flan-t5-base")
 
 # Function to classify customer comments
-@spaces.GPU
 def classify_comments(categories):
     global df  # Ensure we're modifying the global DataFrame
     sentiments = []
     assigned_categories = []
+
+    # Debugging output
+    print("Classifying comments...")
+
     for comment in df['customer_comment']:
         # Classify sentiment
         sentiment = classifier(comment)[0]['label']
@@ -35,38 +38,59 @@ def classify_comments(categories):
         category = generator(prompt, max_length=30)[0]['generated_text']
         assigned_categories.append(category)
         sentiments.append(sentiment)
+    
     df['comment_sentiment'] = sentiments
     df['comment_category'] = assigned_categories
+    
+    # Debugging output
+    print(df.head())  
+    print(df['comment_sentiment'].value_counts())  
+    print(df['comment_category'].value_counts())  
+
     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():
-    # 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)
-        return None, None, None, "Error: Please classify comments before visualizing.", None
+    global df
+
+    # Check if DataFrame is empty
+    if df.empty:
+        return None, None, None, "Error: DataFrame is empty. Please check the data or classification step.", None
+
+    # Check for required columns
+    required_columns = ['comment_sentiment', 'comment_category', 'customer_nps', 'customer_segment']
+    if not all(col in df.columns for col in required_columns):
+        return None, None, None, "Error: Required columns are missing. Please classify comments first.", None
+
+    # Explicitly convert data types
+    df['comment_sentiment'] = df['comment_sentiment'].astype(str)
+    df['comment_category'] = df['comment_category'].astype(str)
+    df['customer_nps'] = pd.to_numeric(df['customer_nps'], errors='coerce')
+    df['customer_segment'] = df['customer_segment'].astype(str)
+
+    # Drop NaN values
+    df = df.dropna(subset=['comment_sentiment', 'comment_category', 'customer_nps', 'customer_segment'])
+
+    # Debugging output
+    print(df.head())  
+    print(df['comment_sentiment'].value_counts())  
+    print(df['comment_category'].value_counts())  
 
     # 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'}
+        title="Sentiment Distribution"
     )
-    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'}
+        title="Comment Category Distribution"
     )
-    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()
@@ -99,44 +123,36 @@ def visualize_output():
     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'}
+        title="Sentiment by Customer Segment"
     )
 
     return sentiment_pie, category_pie, stacked_bar, kpi_visualization, sentiment_by_segment_pie
 
 # Gradio Interface
 with gr.Blocks() as nps:
-    # State to store categories
     categories = gr.State([])
 
-    # Function to add a category
     def add_category(categories, new_category):
-        if new_category.strip() != "" and len(categories) < 5:  # Limit to 5 categories
+        if new_category.strip() != "" and len(categories) < 5:
             categories.append(new_category.strip())
         return categories, "", f"**Categories:**\n" + "\n".join([f"- {cat}" for cat in categories])
 
-    # Function to reset categories
     def reset_categories():
         return [], "**Categories:**\n- None"
 
-    # UI for adding categories
     with gr.Row():
         category_input = gr.Textbox(label="New Category", placeholder="Enter category name")
         add_category_btn = gr.Button("Add Category")
         reset_btn = gr.Button("Reset Categories")
         category_status = gr.Markdown("**Categories:**\n- None")
 
-    # File upload and template buttons
     uploaded_file = gr.File(label="Upload CSV", type="filepath")
     template_btn = gr.Button("Use Template")
     gr.Markdown("# NPS Comment Categorization")
 
-    # Classify button
     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")
@@ -144,56 +160,9 @@ with gr.Blocks() as nps:
     kpi_visualization = gr.Markdown()
     sentiment_by_segment_pie = gr.Plot(label="Sentiment by Customer Segment")
 
-    # Function to load data from uploaded CSV
-    def load_data(file):
-        global df  # Ensure we're modifying the global DataFrame
-        if file is not None:
-            file.seek(0)  # Reset file pointer
-            if file.name.endswith('.csv'):
-                custom_df = pd.read_csv(file, encoding='utf-8')
-            else:
-                return "Error: Uploaded file is not a CSV."
-            # Check for required columns
-            required_columns = ['customer_id', 'customer_comment', 'customer_nps', 'customer_segment']
-            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)}"
-            df = custom_df
-            return "Custom CSV loaded successfully!"
-        else:
-            return "No file uploaded."
-
-    # Function to use template categories
-    def use_template():
-        template_categories = ["Product Experience", "Customer Support", "Price of Service", "Other"]
-        return template_categories, f"**Categories:**\n" + "\n".join([f"- {cat}" for cat in template_categories])
-
-    # Event handlers
-    add_category_btn.click(
-        fn=add_category,
-        inputs=[categories, category_input],
-        outputs=[categories, category_input, category_status]
-    )
-    reset_btn.click(
-        fn=reset_categories,
-        outputs=[categories, category_status]
-    )
-    uploaded_file.change(
-        fn=load_data,
-        inputs=uploaded_file,
-        outputs=output
-    )
-    template_btn.click(
-        fn=use_template,
-        outputs=[categories, category_status]
-    )
-    classify_btn.click(
-        fn=classify_comments,
-        inputs=categories,
-        outputs=output
-    )
-    visualize_btn.click(
-        fn=visualize_output,
-        outputs=[sentiment_pie, category_pie, stacked_bar, kpi_visualization, sentiment_by_segment_pie]
-    )
+    add_category_btn.click(fn=add_category, inputs=[categories, category_input], outputs=[categories, category_input, category_status])
+    reset_btn.click(fn=reset_categories, outputs=[categories, category_status])
+    classify_btn.click(fn=classify_comments, inputs=categories, outputs=output)
+    visualize_btn.click(fn=visualize_output, outputs=[sentiment_pie, category_pie, stacked_bar, kpi_visualization, sentiment_by_segment_pie])
 
-nps.launch(share=True)
+nps.launch(share=True)