app.py

import pandas as pd
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
import gradio as gr

# ✅ Load inline dataset
def load_data():
    csv_data = """area,bedrooms,age,price
1000,3,10,500000
1500,4,5,750000
800,2,20,300000
1200,3,15,450000
1600,4,7,800000
"""
    from io import StringIO
    return pd.read_csv(StringIO(csv_data))

# ✅ Train model
def train_model():
    df = load_data()
    X = df[["area", "bedrooms", "age"]]
    y = df["price"]
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
    model = LinearRegression()
    model.fit(X_train, y_train)
    return model

def predict_price(model, area, bedrooms, age):
    return model.predict([[area, bedrooms, age]])[0]

model = train_model()

# ✅ Gradio UI function
def gradio_predict(area, bedrooms, age):
    price = predict_price(model, area, bedrooms, age)
    return f"🏠 Estimated House Price: ₹{round(price, 2):,.0f}"

# ✅ Launch Gradio interface
demo = gr.Interface(
    fn=gradio_predict,
    inputs=[
        gr.Number(label="Area (sq ft)", value=1200),
        gr.Number(label="Bedrooms", value=3),
        gr.Number(label="Age of House (years)", value=10)
    ],
    outputs="text",
    title="🏠 House Price Predictor",
    description="Enter house details to predict price using a trained ML model."
)

demo.launch()