lstm_stock_predict.py

import numpy as np
import pandas as pd
from keras.models import Sequential
from keras.layers import Dense, LSTM, Dropout, Conv2D, Reshape, TimeDistributed, Flatten, Conv1D,ConvLSTM2D, MaxPooling1D
from keras.layers.core import Dense, Activation, Dropout
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import mean_squared_error
import tensorflow as tf
import matplotlib.pyplot as plt


config = tf.ConfigProto()
config.gpu_options.allow_growth=True

sess = tf.Session(config=config)
def create_dataset(signal_data, look_back=1):
    dataX, dataY = [], []
    for i in range(len(signal_data) - look_back):
        dataX.append(signal_data[i:(i + look_back), 0])
        dataY.append(signal_data[i + look_back, 0])
    return np.array(dataX), np.array(dataY)


look_back = 20


#kospi.csv is https://docs.google.com/spreadsheets/d/13qyMDbl9EsBPE6asoXkH_73Y4QVGzaiUXyir94nN3VE/edit?usp=sharing
df = pd.read_csv('kospi.csv')
signal_data = df.Close.values.astype('float32')
signal_data = signal_data.reshape(len(df), 1)


scaler = MinMaxScaler(feature_range=(0, 1))
signal_data = scaler.fit_transform(signal_data)



train_size = int(len(signal_data) * 0.80)
test_size = len(signal_data) - train_size - int(len(signal_data) * 0.05)
val_size = len(signal_data) - train_size - test_size
train = signal_data[0:train_size]
val = signal_data[train_size:train_size+val_size]
test = signal_data[train_size+val_size:len(signal_data)]



x_train, y_train = create_dataset(train, look_back)
x_val, y_val = create_dataset(val, look_back)
x_test, y_test = create_dataset(test, look_back)


x_train = np.reshape(x_train, (x_train.shape[0], x_train.shape[1], 1))
x_val = np.reshape(x_val, (x_val.shape[0], x_val.shape[1], 1))
x_test = np.reshape(x_test, (x_test.shape[0], x_test.shape[1], 1))


model = Sequential()
model.add(LSTM(128, input_shape=(None, 1),return_sequences=True))
model.add(Dropout(0.3))

model.add(LSTM(128, input_shape=(None, 1)))
model.add(Dropout(0.3))

model.add(Dense(128))
model.add(Dropout(0.3))

model.add(Dense(1))




model.compile(loss='mean_squared_error', optimizer='adam', metrics=['accuracy'])


model.summary()
hist = model.fit(x_train, y_train, epochs=20, batch_size=32, verbose=2, validation_data=(x_val, y_val))

trainScore = model.evaluate(x_train, y_train, verbose=0)
model.reset_states()
print('Train Score: ', trainScore)
valScore = model.evaluate(x_val, y_val, verbose=0)
model.reset_states()
print('Validataion Score: ', valScore)
testScore = model.evaluate(x_test, y_test, verbose=0)
model.reset_states()
print('Test Score: ', testScore)



p = model.predict(x_test)


print(mean_squared_error(y_test, p))

import matplotlib.pyplot as pplt

pplt.plot(y_test)
pplt.plot(p)
pplt.legend(['testY', 'p'], loc='upper right')
pplt.show()

#kospi.csv is https://docs.google.com/spreadsheets/d/13qyMDbl9EsBPE6asoXkH_73Y4QVGzaiUXyir94nN3VE/edit?usp=sharing