Create app.py

app.py

@@ -0,0 +1,74 @@
+# Necessary imports
+pip install pandas numpy scipy statsmodels patsy dtale scikit-learn pandas_profiling pycaret
+import gradio as gr
+import pandas as pd
+from pycaret.classification import load_model, predict_model
+
+# Load the tuned model
+tuned_gbc_classifier = load_model('tuned_gbc_classifier')
+
+def predict_ten_year_chd(male, age, education, currentSmoker, cigsPerDay, BPMeds, prevalentStroke,
+                         prevalentHyp, diabetes, totChol, sysBP, diaBP, BMI, heartRate, glucose):
+    try:
+        # Convert categorical variables to numerical representation
+        male = 1 if male == "Male" else 0
+        education_mapping = {
+            "Some High School": 0,
+            "High School Graduate": 1,
+            "Some College": 2,
+            "College Graduate": 3
+        }
+        education = education_mapping.get(education, 0)
+
+        # Create a DataFrame with the input values
+        data = pd.DataFrame(
+            data=[[male, age, education, currentSmoker, cigsPerDay, BPMeds, prevalentStroke,
+                   prevalentHyp, diabetes, totChol, sysBP, diaBP, BMI, heartRate, glucose]],
+            columns=['male', 'age', 'education', 'currentSmoker', 'cigsPerDay', 'BPMeds', 'prevalentStroke',
+                     'prevalentHyp', 'diabetes', 'totChol', 'sysBP', 'diaBP', 'BMI', 'heartRate', 'glucose']
+        )
+
+        # Make a prediction
+        pred = predict_model(tuned_gbc_classifier, data=data)
+
+        # Extract the prediction and the confidence using the correct keys
+        prediction = pred['prediction_label'].iloc[0]
+        confidence = pred['prediction_score'].iloc[0]
+
+        # Return the prediction with 'At Risk' category for No CHD with confidence < 0.8
+        if prediction == 0 and confidence < 0.8:
+            return f"Prediction: No CHD (At Risk), Confidence: {confidence:.2f}"
+        else:
+            return f"Prediction: {'Has CHD' if prediction == 1 else 'No CHD'}, Confidence: {confidence:.2f}"
+
+    except Exception as e:
+        return f"An error occurred: {str(e)}"
+
+# Create the Gradio interface
+iface = gr.Interface(
+    fn=predict_ten_year_chd,
+    inputs=[
+        gr.inputs.Radio(["Male", "Female"], label="Gender"),
+        gr.inputs.Slider(minimum=18, maximum=100, label="Age"),
+        gr.inputs.Dropdown(["Some High School", "High School Graduate", "Some College", "College Graduate"], label="Education"),
+        gr.inputs.Checkbox(label="Current Smoker"),
+        gr.inputs.Slider(minimum=0, maximum=50, default=0, label="Cigarettes Per Day"),
+        gr.inputs.Checkbox(label="On Blood Pressure Medication"),
+        gr.inputs.Checkbox(label="History of Prevalent Stroke"),
+        gr.inputs.Checkbox(label="History of Prevalent Hypertension"),
+        gr.inputs.Checkbox(label="Diabetes"),
+        gr.inputs.Slider(minimum=100, maximum=400, default=200, label="Total Cholesterol"),
+        gr.inputs.Slider(minimum=90, maximum=200, default=120, label="Systolic BP"),
+        gr.inputs.Slider(minimum=60, maximum=120, default=80, label="Diastolic BP"),
+        gr.inputs.Slider(minimum=15, maximum=50, default=25, label="BMI"),
+        gr.inputs.Slider(minimum=40, maximum=120, default=75, label="Heart Rate"),
+        gr.inputs.Slider(minimum=40, maximum=300, default=100, label="Glucose Level")
+    ],
+    outputs=gr.outputs.Textbox(),
+    live=False,  # set live to False to add a submit button
+    title="CHD Prediction",
+    description="By Abderrahim Benmoussa, Ph.D."
+)
+
+# Run the app
+iface.launch(share=True)