app.py

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

app = Flask(__name__)

# Load the saved model and scaler
model = tf.keras.models.load_model('aqi_model.h5')
scaler = joblib.load('scaler.pkl')

@app.route('/predict', methods=['POST'])
def predict():
    try:
        # Get the input features from the JSON request
        data = request.get_json()
        features = [
            data['PM10'],
            data['PM2.5'],
            data['NO2'],
            data['O3'],
            data['CO'],
            data['SO2'],
            data['NH3']
        ]

        # Convert to numpy array and reshape for a single prediction
        features_array = np.array(features).reshape(1, -1)

        # Scale the input features using the loaded scaler
        features_scaled = scaler.transform(features_array)

        # Make prediction using the loaded model
        prediction = model.predict(features_scaled)
        predicted_aqi = prediction[0][0]

        # Convert the result to a standard Python float
        predicted_aqi = float(predicted_aqi)

        # Return the predicted AQI
        return jsonify({'predicted_aqi': predicted_aqi})

    except Exception as e:
        return jsonify({'error': str(e)}), 400

if __name__ == "__main__":
    app.run(host='0.0.0.0', port=8080)