from flask import Flask, request, jsonify, send_from_directory
from flask_cors import CORS
import joblib
import numpy as np
import json
import math
import xgboost as xgb
import os

app = Flask(__name__, static_folder='.', static_url_path='/')
CORS(app)

# Load ML models
try:
    rf = joblib.load("rf_model.pkl")
    xgb_model = xgb.Booster()
    xgb_model.load_model("xgb_model.json")
    print("✅ Models loaded successfully.")
except Exception as e:
    print(f"❌ Error loading models: {e}")
    raise e

# Load tile data
with open("tile_catalog.json", "r", encoding="utf-8") as f:
    tile_catalog = json.load(f)
with open("tile_sizes.json", "r", encoding="utf-8") as f:
    tile_sizes = json.load(f)

@app.route("/")
def index():
    return send_from_directory(".", "index.html")

@app.route("/recommend", methods=["POST"])
def recommend():
    try:
        data = request.get_json()
        tile_type = data.get("tile_type", "").lower()
        coverage = float(data.get("coverage", 1))
        area = float(data.get("area", 1))
        price_range = data.get("price_range", [1, 100])
        preferred_sizes = data.get("preferred_sizes", [])

        features = prepare_features(tile_type, coverage, area, price_range)
        xgb_pred = xgb_model.predict(xgb.DMatrix(features))[0]
        rf_pred = rf.predict_proba(features)[0][1]
        score = (xgb_pred + rf_pred) / 2

        products = filter_products(tile_type, price_range, preferred_sizes)
        return jsonify({
            "recommendation_score": round(float(score), 3),
            "recommended_products": products[:4],
            "total_matches": len(products),
        })
    except Exception as e:
        print("❌ Error in /recommend:", str(e))
        return jsonify({"error": "Server error"}), 500

@app.route("/calculate", methods=["POST"])
def calculate():
    try:
        data = request.get_json()
        tile_type = data.get("tile_type", "").lower()
        area = float(data.get("area", 0))
        tile_size = data.get("tile_size", "")

        if tile_size not in tile_sizes:
            return jsonify({"error": "Invalid tile size"}), 400

        info = tile_sizes[tile_size]
        per_tile_area = info["length"] * info["width"]
        tiles_needed = math.ceil((area / per_tile_area) * 1.1)
        boxes = math.ceil(tiles_needed / info.get("tiles_per_box", 10))

        matches = [p for p in tile_catalog if p["type"].lower() == tile_type and p["size"] == tile_size]

        return jsonify({
            "tiles_needed": tiles_needed,
            "boxes_needed": boxes,
            "matching_products": matches[:3],
            "total_matches": len(matches)
        })
    except Exception as e:
        print("❌ Error in /calculate:", str(e))
        return jsonify({"error": "Server error"}), 500

def prepare_features(tile_type, coverage, area, price_range):
    tile_type_num = 0 if tile_type == "floor" else 1
    min_price, max_price = price_range
    price_per_sqft = max_price / coverage
    efficiency = coverage / max_price
    return np.array([[tile_type_num, area, coverage, min_price, max_price, price_per_sqft, efficiency]])

def filter_products(tile_type, price_range, preferred_sizes):
    min_price, max_price = price_range
    filtered = []
    for product in tile_catalog:
        if product["type"].lower() != tile_type:
            continue
        if not (min_price <= product["price"] <= max_price):
            continue
        if preferred_sizes and product["size"] not in preferred_sizes:
            continue

        price_score = 1 - (product["price"] - min_price) / (max_price - min_price + 1e-6)
        size_score = 1 if product["size"] in preferred_sizes else 0.5
        score = round((price_score + size_score) / 2, 2)
        filtered.append({**product, "recommendation_score": score})
    return sorted(filtered, key=lambda x: x["recommendation_score"], reverse=True)

if __name__ == "__main__":
    app.run(host="0.0.0.0", port=7860)