LSTM.py

import os
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

from sklearn.preprocessing import StandardScaler, MinMaxScaler
from keras.models import Sequential
from keras.layers import LSTM, Dense, Dropout
from tensorflow.keras.optimizers import Adagrad

# load the data using pandas
data = pd.read_csv('S&P500 historical data.csv')
data = data.dropna()

# split the data into training and testing sets
train_size = int(len(data) * 0.7)
train_data = data.iloc[:train_size, :]
test_data = data.iloc[train_size:, :]
# normalize the data
scaler = StandardScaler()
train_data = scaler.fit_transform(train_data)
test_data = scaler.transform(test_data)

def create_sequences(data, sequence_length):
    X = []
    y = []
    for ii in range(sequence_length, len(data)):
        X.append(data[ii-sequence_length:ii, :])
        y.append(data[ii,0])
    return np.array(X), np.array(y)

sequence_length = 10 # number of time steps to look back
X_train, y_train = create_sequences(train_data, sequence_length)
X_test, y_test = create_sequences(test_data, sequence_length)

# reshape the data
y_train = np.reshape(y_train, (y_train.shape[0], 1))
y_test = np.reshape(y_test, (y_test.shape[0], 1))

# create the LSTM model
model = Sequential()
model.add(LSTM(150, input_shape=(sequence_length, X_train.shape[2])))
model.add(Dense(y_train.shape[1]))
model.compile(loss='mse', optimizer=Adagrad(learning_rate=0.01))

# train the model
model.fit(X_train, y_train, epochs=50, batch_size=16, verbose=0)

# evaluate the model on the test set
mse = model.evaluate(X_test, y_test, verbose=0)
print('MSE:', mse)

model.save('model.h5')