import numpy as np
import pandas as pd
import yfinance as yf
from keras.models import load_model
from sklearn.preprocessing import MinMaxScaler

# Load model
model = load_model("stock_dl_model.h5")

def predict(stock_symbol="POWERGRID.NS"):
    start = pd.to_datetime("2000-01-01")
    end = pd.to_datetime("2024-10-01")
    df = yf.download(stock_symbol, start=start, end=end)

    data_training = pd.DataFrame(df['Close'][0:int(len(df)*0.70)])
    data_testing = pd.DataFrame(df['Close'][int(len(df)*0.70): int(len(df))])

    scaler = MinMaxScaler(feature_range=(0, 1))
    data_training_array = scaler.fit_transform(data_training)

    past_100_days = data_training.tail(100)
    final_df = past_100_days.append(data_testing, ignore_index=True)
    input_data = scaler.fit_transform(final_df)

    x_test, y_test = [], []
    for i in range(100, input_data.shape[0]):
        x_test.append(input_data[i-100:i])
        y_test.append(input_data[i, 0])
    
    x_test, y_test = np.array(x_test), np.array(y_test)

    y_predicted = model.predict(x_test)

    scaler = scaler.scale_
    scale_factor = 1 / scaler[0]
    y_predicted = y_predicted * scale_factor
    y_test = y_test * scale_factor

    return {
        "prediction": y_predicted.tolist()
    }

def __call__(self, inputs):
    stock_symbol = inputs.get("inputs", "POWERGRID.NS")
    return predict(stock_symbol)