Update app.py

app.py

@@ -1,4 +1,4 @@
-# app.py
+# app.py 
 import pandas as pd
 import numpy as np
 import matplotlib.pyplot as plt
@@ -81,40 +81,37 @@ class EnhancedAIvsRealGazeAnalyzer:
         valid_indices = target.notna()
         features, target = features[valid_indices], target[valid_indices]
         features = features.fillna(features.median()).fillna(0)
-        if len(target.unique()) < 2: return "Not enough classes to train the model.", None
+        if len(target.unique()) < 2: return "Not enough classes to train.", None, None
         X_train, X_test, y_train, y_test = train_test_split(features, target, test_size=test_size, random_state=42, stratify=target)
         scaler = StandardScaler()
         X_train_scaled, X_test_scaled = scaler.fit_transform(X_train), scaler.transform(X_test)
         model = RandomForestClassifier(n_estimators=n_estimators, random_state=42, class_weight='balanced')
         model.fit(X_train_scaled, y_train)
-        y_pred_proba = model.predict_proba(X_test_scaled)[:, 1]
         y_pred = model.predict(X_test_scaled)
         report = classification_report(y_test, y_pred, target_names=['Incorrect', 'Correct'], output_dict=True)
-        auc_score = roc_auc_score(y_test, y_pred_proba)
+        auc_score = roc_auc_score(y_test, model.predict_proba(X_test_scaled)[:, 1])
         
         # --- THIS IS THE KEY FIX ---
-        # 1. Convert the report dictionary to a DataFrame
-        report_df = pd.DataFrame(report).transpose().round(3)
-        # 2. Use the built-in .to_markdown() method for perfect formatting
-        report_table = report_df.to_markdown()
-
-        report_md = f"""
+        # 1. Create the summary text separately.
+        summary_md = f"""
         ### Model Performance
         - **AUC Score:** **{auc_score:.4f}**
         - **Overall Accuracy:** {report['accuracy']:.3f}
-        
-        **Classification Report:**
-        {report_table}
         """
-        # --- END OF FIX ---
-
+        # 2. Create the report DataFrame.
+        report_df = pd.DataFrame(report).transpose().round(3)
+        
+        # 3. Create the feature importance plot.
         feature_importance = pd.DataFrame({'Feature': features.columns, 'Importance': model.feature_importances_})
         feature_importance = feature_importance.sort_values('Importance', ascending=False).head(15)
         fig, ax = plt.subplots(figsize=(10, 8))
         sns.barplot(data=feature_importance, x='Importance', y='Feature', ax=ax, palette='viridis')
         ax.set_title(f'Top 15 Predictive Features (n_estimators={n_estimators})', fontsize=14)
         plt.tight_layout()
-        return report_md, fig
+        
+        # 4. Return the three items separately.
+        return summary_md, report_df, fig
+        # --- END OF FIX ---
 
 # --- DATA SETUP ---
 def setup_and_load_data():
@@ -124,7 +121,7 @@ def setup_and_load_data():
         print(f"Cloning data repository from {repo_url}...")
         git.Repo.clone_from(repo_url, repo_dir)
     else:
-        print("Data repository already exists.")
+        print("Data repository already. Skipping clone.")
     base_path = repo_dir 
     response_file = os.path.join(repo_dir, "GenAI Response.xlsx")
     analyzer = EnhancedAIvsRealGazeAnalyzer().load_and_process_data(base_path, response_file)
@@ -142,8 +139,9 @@ def update_rq1_visuals(metric_choice):
 
 def update_rq2_model(test_size, n_estimators):
     n_estimators = int(n_estimators)
-    report, plot = analyzer.run_prediction_model(test_size, n_estimators)
-    return report, plot
+    # The function now returns three items
+    summary, report_df, plot = analyzer.run_prediction_model(test_size, n_estimators)
+    return summary, report_df, plot
 
 # --- GRADIO INTERFACE DEFINITION ---
 description = """
@@ -161,23 +159,35 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
                     rq1_summary_output = gr.Markdown(label="Statistical Summary")
                 with gr.Column(scale=2):
                     rq1_plot_output = gr.Plot(label="Metric Comparison")
+        
         with gr.TabItem("RQ2: Predicting Correctness from Gaze"):
             with gr.Row():
                 with gr.Column(scale=1):
                     gr.Markdown("#### Tune Model Hyperparameters")
                     rq2_test_size_slider = gr.Slider(minimum=0.1, maximum=0.5, step=0.05, value=0.3, label="Test Set Size")
                     rq2_estimators_slider = gr.Slider(minimum=10, maximum=200, step=10, value=100, label="Number of Trees (n_estimators)")
+                
+                # --- THIS IS THE KEY UI FIX ---
                 with gr.Column(scale=2):
-                    # Ensure this is gr.Markdown()
-                    rq2_report_output = gr.Markdown(label="Model Performance Report")
+                    # 1. A Markdown component for the summary text.
+                    rq2_summary_output = gr.Markdown(label="Model Performance Summary")
+                    # 2. A Dataframe component for the table.
+                    rq2_table_output = gr.Dataframe(label="Classification Report", interactive=False)
+                    # 3. A Plot component for the chart.
                     rq2_plot_output = gr.Plot(label="Feature Importance")
+                # --- END OF UI FIX ---
 
+    # --- THIS IS THE KEY WIRING FIX ---
+    # The outputs list now has 3 items to match the 3 components
+    outputs_rq2 = [rq2_summary_output, rq2_table_output, rq2_plot_output]
+    
     rq1_metric_dropdown.change(fn=update_rq1_visuals, inputs=[rq1_metric_dropdown], outputs=[rq1_plot_output, rq1_summary_output])
-    rq2_test_size_slider.release(fn=update_rq2_model, inputs=[rq2_test_size_slider, rq2_estimators_slider], outputs=[rq2_report_output, rq2_plot_output])
-    rq2_estimators_slider.release(fn=update_rq2_model, inputs=[rq2_test_size_slider, rq2_estimators_slider], outputs=[rq2_report_output, rq2_plot_output])
+    rq2_test_size_slider.release(fn=update_rq2_model, inputs=[rq2_test_size_slider, rq2_estimators_slider], outputs=outputs_rq2)
+    rq2_estimators_slider.release(fn=update_rq2_model, inputs=[rq2_test_size_slider, rq2_estimators_slider], outputs=outputs_rq2)
     
     demo.load(fn=update_rq1_visuals, inputs=[rq1_metric_dropdown], outputs=[rq1_plot_output, rq1_summary_output])
-    demo.load(fn=update_rq2_model, inputs=[rq2_test_size_slider, rq2_estimators_slider], outputs=[rq2_report_output, rq2_plot_output])
+    demo.load(fn=update_rq2_model, inputs=[rq2_test_size_slider, rq2_estimators_slider], outputs=outputs_rq2)
+    # --- END OF WIRING FIX ---
 
 if __name__ == "__main__":
     demo.launch()