app.py

from flask import Flask, request, jsonify
from flask_cors import CORS
import tensorflow as tf
import numpy as np
import pickle

app = Flask(__name__)
CORS(app)  # Allow frontend (CodePen) to access this API

# Load trained LSTM model
model = tf.keras.models.load_model("nse_lstm_model_fixed.h5")  # Update with correct model path

# Load MinMaxScaler for inverse transformation
with open("close_price_scaler.pkl", "rb") as f:
    close_scaler = pickle.load(f)

@app.route('/predict', methods=['POST'])
def predict():
    try:
        data = request.json['features']  # Receive stock data from frontend
        input_data = np.array(data).reshape(1, 60, 7)  # Ensure correct shape
        
        # Make prediction
        prediction = model.predict(input_data)
        predicted_price = close_scaler.inverse_transform(prediction.reshape(-1, 1)).flatten()[0]

        return jsonify({'predicted_price': round(predicted_price, 2)})

    except Exception as e:
        return jsonify({'error': str(e)})
        if __name__ == '__main__':
    app.run(host='0.0.0.0', port=5000, debug=True)