tile_api.py

from flask import Flask, request, jsonify
import joblib
import numpy as np

app = Flask(__name__)

# Load models (make sure these files exist)
xgb = joblib.load("xgb_model.json")
rf = joblib.load("rf_model.pkl")

@app.route("/recommend", methods=["POST"])
def recommend():
    data = request.get_json()

    # Extract input features
    length = float(data["length"])
    width = float(data["width"])
    price = float(data["price"])
    coverage = float(data["coverage"])
    area_range = float(data["area_range"])
    tile_type = data["tile_type"].lower()

    # Feature engineering
    tile_type_num = 0 if tile_type == "floor" else 1
    tile_area = length * width
    price_per_sqft = price / coverage
    budget_eff = coverage / price

    features = np.array([[tile_type_num, length, width, price, coverage,
                          area_range, tile_area, price_per_sqft, budget_eff]])

    # Predict using both models and average
    prob = (xgb.predict_proba(features)[0][1] + rf.predict_proba(features)[0][1]) / 2
    result = "✅ Recommended" if prob >= 0.5 else "❌ Not Recommended"

    return jsonify({"result": result, "score": round(float(prob), 3)})

if __name__ == "__main__":
    app.run(debug=True)