import tensorflow as tf
import numpy as np
import joblib
import os

def predict_marks(num_courses, time_study):
    # Load model and scalers
    if not (os.path.exists('student_marks_rnn_model.h5') and 
            os.path.exists('scaler_X.pkl') and 
            os.path.exists('scaler_y.pkl')):
        return "Error: Model or scalers not found. Please run train_rnn.py first."

    model = tf.keras.models.load_model('student_marks_rnn_model.h5')
    scaler_X = joblib.load('scaler_X.pkl')
    scaler_y = joblib.load('scaler_y.pkl')
    
    # Preprocess input
    input_data = np.array([[num_courses, time_study]])
    input_scaled = scaler_X.transform(input_data)
    
    # Reshape for RNN (Samples, TimeSteps, Features)
    input_reshaped = input_scaled.reshape((1, 1, 2))
    
    # Predict
    prediction_scaled = model.predict(input_reshaped)
    prediction = scaler_y.inverse_transform(prediction_scaled)
    
    return prediction[0][0]

if __name__ == "__main__":
    print("--- Student Marks Prediction RNN ---")
    try:
        nc = float(input("Enter number of courses: "))
        ts = float(input("Enter time spent studying (hours): "))
        
        result = predict_marks(nc, ts)
        if isinstance(result, str):
            print(result)
        else:
            print(f"\nPredicted Marks: {result:.2f}")
    except ValueError:
        print("Invalid input. Please enter numeric values.")
    except Exception as e:
        print(f"Error: {e}")