Update output rq2 table

app.py

@@ -1,4 +1,4 @@
-# app.py 
+# app.py
 import pandas as pd
 import numpy as np
 import matplotlib.pyplot as plt
@@ -8,20 +8,17 @@ from sklearn.preprocessing import StandardScaler
 from sklearn.ensemble import RandomForestClassifier
 from sklearn.model_selection import train_test_split
 from sklearn.metrics import classification_report, roc_auc_score
-from tabulate import tabulate
 import warnings
-import traceback
 import gradio as gr
 import os
 import git
 
-# --- Main Class (Slightly Refactored for Interactivity) ---
+# --- Main Class ---
 warnings.filterwarnings('ignore')
 plt.style.use('default')
 sns.set_palette("husl")
 
 class EnhancedAIvsRealGazeAnalyzer:
-    # ... (The entire class from before remains unchanged up to run_prediction_model) ...
     def __init__(self):
         self.questions = ['Q1', 'Q2', 'Q3', 'Q4', 'Q5', 'Q6']
         self.correct_answers = {'Pair1': 'B', 'Pair2': 'B', 'Pair3': 'B', 'Pair4': 'B', 'Pair5': 'B', 'Pair6': 'B'}
@@ -77,7 +74,6 @@ class EnhancedAIvsRealGazeAnalyzer:
         return fig, summary
 
     def run_prediction_model(self, test_size, n_estimators):
-        """Runs the RandomForest model with given parameters for RQ2."""
         leaky_features = ['Total_Correct', 'Overall_Accuracy', 'Correct']
         features_to_use = [col for col in self.numeric_cols if col not in leaky_features]
         features = self.combined_data[features_to_use].copy()
@@ -96,9 +92,11 @@ class EnhancedAIvsRealGazeAnalyzer:
         report = classification_report(y_test, y_pred, target_names=['Incorrect', 'Correct'], output_dict=True)
         auc_score = roc_auc_score(y_test, y_pred_proba)
         
-        # --- CHANGE 1: Use tabulate to create a clean markdown table ---
+        # --- THIS IS THE KEY FIX ---
+        # 1. Convert the report dictionary to a DataFrame
         report_df = pd.DataFrame(report).transpose().round(3)
-        report_table = tabulate(report_df, headers='keys', tablefmt='pipe')
+        # 2. Use the built-in .to_markdown() method for perfect formatting
+        report_table = report_df.to_markdown()
 
         report_md = f"""
         ### Model Performance
@@ -108,6 +106,7 @@ class EnhancedAIvsRealGazeAnalyzer:
         **Classification Report:**
         {report_table}
         """
+        # --- END OF FIX ---
 
         feature_importance = pd.DataFrame({'Feature': features.columns, 'Importance': model.feature_importances_})
         feature_importance = feature_importance.sort_values('Importance', ascending=False).head(15)
@@ -117,7 +116,7 @@ class EnhancedAIvsRealGazeAnalyzer:
         plt.tight_layout()
         return report_md, fig
 
-# --- DATA SETUP (RUNS ONCE AT STARTUP) ---
+# --- DATA SETUP ---
 def setup_and_load_data():
     repo_url = "https://github.com/RextonRZ/GenAIEyeTrackingCleanedDataset"
     repo_dir = "GenAIEyeTrackingCleanedDataset"
@@ -152,47 +151,31 @@ description = """
 Explore the eye-tracking dataset by interacting with the controls below. The data is automatically loaded from the public GitHub repository.
 """
 
-# --- CHANGE 2: Restructure the layout with columns ---
 with gr.Blocks(theme=gr.themes.Soft()) as demo:
     gr.Markdown(description)
-
     with gr.Tabs():
         with gr.TabItem("RQ1: Viewing Time vs. Correctness"):
-            gr.Markdown("### Does viewing time differ based on whether a participant's answer was correct?")
             with gr.Row():
                 with gr.Column(scale=1):
-                    rq1_metric_dropdown = gr.Dropdown(
-                        choices=analyzer.time_metrics,
-                        label="Select a Time-Based Metric to Analyze",
-                        value=analyzer.time_metrics[0] if analyzer.time_metrics else None
-                    )
+                    rq1_metric_dropdown = gr.Dropdown(choices=analyzer.time_metrics, label="Select a Time-Based Metric", value=analyzer.time_metrics[0] if analyzer.time_metrics else None)
                     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"):
-            gr.Markdown("### Can we build a model to predict answer correctness from gaze patterns?")
             with gr.Row():
-                # --- LEFT COLUMN FOR CONTROLS ---
                 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)"
-                    )
-                # --- RIGHT COLUMN FOR OUTPUTS ---
+                    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)")
                 with gr.Column(scale=2):
-                    rq2_report_output = gr.Markdown(label="Model Performance Report") # Use gr.Markdown
+                    # Ensure this is gr.Markdown()
+                    rq2_report_output = gr.Markdown(label="Model Performance Report")
                     rq2_plot_output = gr.Plot(label="Feature Importance")
 
-    # Wire up the interactive components
     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])
     
-    # Load initial state
     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])