import gradio as gr
import joblib
import numpy as np

# Load assets
model = joblib.load('diabetes_model.joblib')
scaler = joblib.load('scaler.joblib')

def predict_diabetes(pregnancies, glucose, bp, skin, insulin, bmi, dpf, age):
    features = np.array([[pregnancies, glucose, bp, skin, insulin, bmi, dpf, age]])
    features_scaled = scaler.transform(features)
    prediction = model.predict(features_scaled)[0]
    probability = model.predict_proba(features_scaled)[0]
    label = 'Diabetic' if prediction == 1 else 'Non-Diabetic'
    conf = probability[1] if prediction == 1 else probability[0]
    return f'{label} ({conf:.2%})'

inputs = [
    gr.Number(label='Pregnancies'),
    gr.Number(label='Glucose'),
    gr.Number(label='Blood Pressure'),
    gr.Number(label='Skin Thickness'),
    gr.Number(label='Insulin'),
    gr.Number(label='BMI'),
    gr.Number(label='Diabetes Pedigree Function'),
    gr.Number(label='Age')
]

interface = gr.Interface(
    fn=predict_diabetes,
    inputs=inputs,
    outputs='text',
    title='Diabetes Risk Predictor',
    description='Optimized Random Forest model for diabetes classification.'
)

interface.launch()