app.py

import gradio as gr
import joblib
import pandas as pd
from huggingface_hub import hf_hub_download

# 1. Download your model from your repo
model_path = hf_hub_download(repo_id="Aaravkumar/heart-disease-prediction", filename="heart_disease_model.joblib")
model = joblib.load(model_path)

# 2. Define the prediction function
def predict(age, sex, cp, trestbps, chol, fbs, restecg, thalach, exang, oldpeak, slope, ca, thal):
    # Create a dataframe matching your training columns
    input_data = pd.DataFrame([[age, sex, cp, trestbps, chol, fbs, restecg, thalach, exang, oldpeak, slope, ca, thal]], 
                              columns=['Age', 'Sex', 'Chest pain type', 'BP', 'Cholesterol', 'FBS over 120', 
                                       'EKG results', 'Max HR', 'Exercise angina', 'ST depression', 
                                       'Slope of ST', 'Number of vessels fluro', 'Thallium'])
    
    prediction = model.predict(input_data)[0]
    probability = model.predict_proba(input_data)[0][1]
    
    result = "❤️ Heart Disease Detected" if prediction == 1 else "✅ No Heart Disease Detected"
    return f"{result} (Confidence: {probability:.2%})"

# 3. Create a beautiful UI
demo = gr.Interface(
    fn=predict,
    inputs=[
        gr.Slider(20, 90, value=50, label="Age"),
        gr.Radio([0, 1], label="Sex (1=M, 0=F)"),
        gr.Slider(1, 4, step=1, label="Chest Pain Type"),
        gr.Number(label="Resting BP (trestbps)"),
        gr.Number(label="Cholesterol"),
        gr.Radio([0, 1], label="Fasting Blood Sugar > 120 (1=True)"),
        gr.Slider(0, 2, step=1, label="Resting EKG"),
        gr.Number(label="Max Heart Rate"),
        gr.Radio([0, 1], label="Exercise Induced Angina"),
        gr.Number(label="ST Depression (oldpeak)"),
        gr.Slider(1, 3, step=1, label="Slope of ST"),
        gr.Slider(0, 3, step=1, label="Major Vessels (ca)"),
        gr.Slider(1, 3, step=1, label="Thallium")
    ],
    outputs="text",
    title="Heart Disease Risk Analyzer",
    description="Enter patient vitals to predict cardiac risk using Aarav's Random Forest Model."
)

demo.launch()