Update app.py

app.py

@@ -15,6 +15,29 @@ cutoff = 42  # Custom cutoff probability
 # Use TreeExplainer for XGBoost models
 explainer = shap.TreeExplainer(model)
 
+# Define the function to draw the semicircular scale
+def draw_scale(probability):
+    fig, ax = plt.subplots(figsize=(6, 3))
+    
+    # Plot the semicircular scale
+    ax.barh(0, 1, color='green', left=0, height=0.3)
+    ax.barh(0, 1, color='red', left=cutoff / 100, height=0.3)
+    
+    # Add arrow indicator based on predicted probability
+    arrow_position = probability / 100
+    color = 'green' if probability < cutoff else 'red'
+    ax.annotate('', xy=(arrow_position, 0.15), xytext=(arrow_position, 0.3),
+                arrowprops=dict(facecolor=color, shrink=0.05))
+    
+    # Remove axes and add labels
+    ax.set_xlim(0, 1)
+    ax.set_ylim(-0.5, 0.5)
+    ax.axis('off')
+    
+    # Save the image
+    plt.savefig('scale_plot.png', bbox_inches='tight')
+    plt.close()
+
 # Define the prediction function with preprocessing, scaling, and SHAP analysis
 def predict_heart_attack(Gender, age, cigsPerDay, BPMeds, prevalentHyp, diabetes, totChol, sysBP, diaBP, BMI, heartRate, glucose):
     # Define feature names in the same order as the training data
@@ -30,10 +53,10 @@ def predict_heart_attack(Gender, age, cigsPerDay, BPMeds, prevalentHyp, diabetes
     proba = model.predict_proba(scaled_features)[:, 1]  # Probability of class 1 (heart attack)
     
     # Apply custom cutoff
-    if proba[0]*100 >= cutoff:
+    if proba[0] * 100 >= cutoff:
         prediction_class = "Heart_Attack_Risk.Consult your doctor"
     else:
-        prediction_class = "No_Heart_Attack_Risk.Still make regular checkup "
+        prediction_class = "No_Heart_Attack_Risk.Still make regular checkup"
     
     # Generate SHAP values for the prediction using the explainer
     shap_values = explainer(features)
@@ -43,9 +66,12 @@ def predict_heart_attack(Gender, age, cigsPerDay, BPMeds, prevalentHyp, diabetes
     shap.waterfall_plot(shap_values[0])  # Using the SHAP Explanation object
     plt.savefig('shap_plot.png')  # Save SHAP plot to a file
     
-    result = f"Predicted Probability: {proba[0]*100:.2f}%. Predicted Class with cutoff {cutoff}%: {prediction_class}"
+    # Draw semicircular scale
+    draw_scale(proba[0] * 100)
+    
+    result = f"Predicted Probability: {proba[0] * 100:.2f}%. Predicted Class with cutoff {cutoff}%: {prediction_class}"
     
-    return result, 'shap_plot.png'  # Return the prediction and SHAP plot
+    return result, 'scale_plot.png', 'shap_plot.png'  # Return the prediction, scale, and SHAP plot
 
 # Create the Gradio interface with preprocessing, prediction, and SHAP visualization
 with gr.Blocks() as app:
@@ -66,9 +92,12 @@ with gr.Blocks() as app:
             BMI = gr.Slider(15, 40, step=0.1, label="Body Mass Index (BMI) in kg/m2")
             glucose = gr.Slider(50, 250, step=1, label="Fasting Glucose Level")
     
-    # Center-aligned prediction output
+    # Display disclaimer in red uppercase letters above the scale
+    gr.HTML("<div style='text-align: center; color: red; font-weight: bold; font-size: 16px;'>RESULTS ARE NOT A SUBSTITUTE FOR ADVICE OF QUALIFIED MEDICAL PROFESSIONAL</div>")
+    
+    # Center-aligned prediction output and semicircular scale
     with gr.Row():
-        gr.HTML("<div style='text-align: center; width: 100%'>Heart Attack Prediction</div>")
+        scale_output = gr.Image(label="Risk Indicator Scale")
     
     with gr.Row():
         prediction_output = gr.Textbox(label="", interactive=False, elem_id="prediction_output")
@@ -78,6 +107,6 @@ with gr.Blocks() as app:
 
     # Link inputs and prediction output
     submit_btn = gr.Button("Submit")
-    submit_btn.click(fn=predict_heart_attack, inputs=[Gender, age, cigsPerDay, BPMeds, prevalentHyp, diabetes, totChol, sysBP, diaBP, BMI, heartRate, glucose], outputs=[prediction_output, shap_plot_output])
+    submit_btn.click(fn=predict_heart_attack, inputs=[Gender, age, cigsPerDay, BPMeds, prevalentHyp, diabetes, totChol, sysBP, diaBP, BMI, heartRate, glucose], outputs=[prediction_output, scale_output, shap_plot_output])
 
-app.launch(share = True)
+app.launch(share=True)