multiple_lstm.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, StandardScaler
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), :])
        dataY.append(signal_data[i + look_back, -1])
    return np.array(dataX), np.array(dataY)


look_back = 20



df = pd.read_csv('kospi.csv') # data can download as https://docs.google.com/spreadsheets/d/13qyMDbl9EsBPE6asoXkH_73Y4QVGzaiUXyir94nN3VE/edit#gid=535424417
total_data = df[["open", "low", "high", "volume", "close"]].values.astype('float32')
signal_data = df[["open", "low", "high", "volume", "close"]].values.astype('float32')

#preprocessing
scaler = StandardScaler()
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)



#model
model = Sequential()
model.add(LSTM(128, input_shape=(None, 5),return_sequences=True))
model.add(Dropout(0.3))

model.add(LSTM(128, input_shape=(None, 5)))
model.add(Dropout(0.3))

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

model.add(Dense(1))


#predict
forecast = 20
inputs = total_data[len(total_data) - forecast - look_back:]

inputs = inputs.reshape(-1,5)
inputs = scaler.transform(inputs)
X_test = []
for i in range(look_back, inputs.shape[0]):
    X_test.append(inputs[i-look_back:i, 0:5])
X_test = np.array(X_test)
X_test = np.reshape(X_test, (X_test.shape[0], X_test.shape[1], 5))
# X_test = np.reshape(X_test, (-1, 5))
predicted = model.predict(X_test)
real_last = scaler.inverse_transform(inputs[-1])
real_last = real_last[-1]
predicted = predicted.reshape(-1, 5)
predicted_stock_price = scaler.inverse_transform(predicted)
print(predicted_stock_price)

result is

[[  4378.342    4247.811    4512.2803 402961.7      4369.876 ]
 [  4377.433    4245.599    4509.893  402643.2      4368.5737]
 [  4378.431    4246.4004   4508.5093 402258.94     4365.7065]
 [  4374.951    4242.766    4502.827  400327.62     4354.177 ]]

what I want is get only close