import os
import joblib
import numpy as np
from flask import Flask, request, jsonify
from supabase import create_client


SUPABASE_URL = os.getenv("SUPABASE_URL")
SUPABASE_KEY = os.getenv("SUPABASE_KEY")

supabase = create_client(SUPABASE_URL, SUPABASE_KEY)

# -----------------------------
# Load Model
# -----------------------------
model = joblib.load("predictive_model.pkl")

# -----------------------------
# Flask App
# -----------------------------
app = Flask(__name__)

# -----------------------------
# Health Check
# -----------------------------
@app.route("/", methods=["GET"])
def home():
    return jsonify({
        "status": "API is running",
        "message": "Predictive Maintenance Backend Active"
    })


# -----------------------------
# Prediction Endpoint
# -----------------------------
@app.route("/predict", methods=["POST"])
def predict():
    try:
        data = request.get_json()

        # Extract features (must match training order)
        features = [
            data["Air_temperature"],
            data["Process_temperature"],
            data["Rotational_speed"],
            data["Torque"],
            data["Tool_wear"],
            data["Type_L"],
            data["Type_M"]
        ]

        features_array = np.array([features])

        prediction = model.predict(features_array)
        probability = model.predict_proba(features_array)[0][1]

        status_text = "Failure" if prediction[0] == 1 else "No Failure"

        # -----------------------------
        # Insert into Supabase
        # -----------------------------
        supabase.table("machine_logs").insert({
            "air_temperature": data["Air_temperature"],
            "process_temperature": data["Process_temperature"],
            "rotational_speed": data["Rotational_speed"],
            "torque": data["Torque"],
            "tool_wear": data["Tool_wear"],
            "type_l": data["Type_L"],
            "type_m": data["Type_M"],
            "prediction": int(prediction[0])
        }).execute()

        return jsonify({
            "prediction": int(prediction[0]),
            "status": status_text,
            "failure_probability": float(round(probability, 4))
        })

    except Exception as e:
        return jsonify({"error": str(e)}), 500


# -----------------------------
# Get Latest Logs (Dashboard)
# -----------------------------
@app.route("/logs", methods=["GET"])
def get_logs():
    try:
        response = supabase.table("machine_logs") \
            .select("*") \
            .order("created_at", desc=True) \
            .limit(10) \
            .execute()

        return jsonify(response.data)

    except Exception as e:
        return jsonify({"error": str(e)}), 500


# -----------------------------
# Run App (for local testing)
# -----------------------------
if __name__ == "__main__":
    app.run(host="0.0.0.0", port=7860)