app.py

from flask import Flask, request, jsonify
import numpy as np
import tensorflow as tf
from sklearn.preprocessing import StandardScaler
import json
import os

# Load the trained model
model = tf.keras.models.load_model('flood_risk_model.h5')

# Initialize Flask app
app = Flask(__name__)

# Initialize StandardScaler (ensure it matches the scaler used during training)
scaler = StandardScaler()
scaler.mean_ = np.array([0, 0, 0, 0, 0])  # Replace with actual mean of your training data
scaler.scale_ = np.array([1, 1, 1, 1, 1])  # Replace with actual scale of your training data

@app.route('/predict', methods=['POST'])
def predict():
    try:
        # Parse input JSON data
        data = request.get_json()
        features = [
            data['altitude'],
            data['flow_rate'],
            data['duration'],
            data['slope_factor'],
            data['barrier_factor']
        ]

        # Preprocess input data
        features = np.array(features).reshape(1, -1)
        features_scaled = scaler.transform(features)

        # Make prediction
        prediction = model.predict(features_scaled)

        # Format prediction output
        response = {
            'red_radius': float(prediction[0][0]),
            'orange_radius': float(prediction[0][1]),
            'yellow_radius': float(prediction[0][2])
        }

        return jsonify(response)

    except Exception as e:
        return jsonify({'error': str(e)})

@app.route('/health', methods=['GET'])
def health_check():
    return jsonify({'status': 'healthy'})

if __name__ == '__main__':
    port = int(os.environ.get('PORT', 5000))
    app.run(host='0.0.0.0', port=port)