python RNN LSTM error

Question

This is a recurrent neural network LSTM model meant to predict the future values of forex market movement.

The data set shape is (1713, 50), the first column is the Date time index and the others are numeric values. but right after printing the Training data and Validation data shapes the error start.

When I tried to implement this code:

from sklearn.preprocessing import MinMaxScaler
from keras.layers.core import Dense, Activation, Dropout
from keras.layers.recurrent import LSTM
from keras.models import Sequential
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd

df = pd.read_csv(r"E:\Business\Stocks\StocksDF.csv", parse_dates=[0], index_col=[0], low_memory=False, dtype='object')
features = len(df.columns)
val_ratio = 0.2
epochs = 500
batch_size = df.__len__()
sequence_length = 822

data = df.as_matrix()
data_processed = []
for index in range(len(data) - sequence_length):
    data_processed.append(data[index: index + sequence_length])
data_processed = np.array(data_processed)

val_split = round((1 - val_ratio) * data_processed.shape[0])
train = data_processed[:, int(val_split), :]
val = data_processed[int(val_split):, :]

print('Training data: {}'.format(train.shape))
print('Validation data: {}'.format(val.shape))



train_samples, train_nx, train_ny = train.shape
val_samples, val_nx, val_ny = val.shape

train = train.reshape((train_samples, train_nx * train_ny))
val = val.reshape((val_samples, val_nx * val_ny))

preprocessor = MinMaxScaler().fit(train)
train = preprocessor.transform(train)
val = preprocessor.transform(val)

train = train.reshape((train_samples, train_nx, train_ny))
val = val.reshape((val_samples, val_nx, val_ny))

X_train = train[:, : -1]
y_train = train[:, -1][:, -1]
X_val = val[:, : -1]
y_val = val[:, -1][:, -1]

X_train = np.reshape(X_train, (X_train.shape[0], X_train.shape[1], features))
X_val = np.reshape(X_val, (X_val.shape[0], X_val.shape[1], features))

model = Sequential()
model.add(LSTM(input_shape=(X_train.shape[1:]), units=100, return_sequences=True))
model.add(Dropout(0.5))
model.add(LSTM(2, return_sequences=False))
model.add(Dropout(0.25))
model.add(Dense(units=1))
model.add(Activation("relu"))

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

history = model.fit(
    X_train,
    y_train,
    batch_size=batch_size,
    epochs=epochs,
    verbose=2)

preds_val = model.predict(X_val)
diff = []
for i in range(len(y_val)):
    pred = preds_val[i][0]
    diff.append(y_val[i] - pred)

real_min = preprocessor.data_min_[104]
real_max = preprocessor.data_max_[104]
print(preprocessor.data_min_[:1])
print(preprocessor.data_max_[:1])

preds_real = preds_val * (real_max - real_min) + real_min
y_val_real = y_val * (real_max - real_min) + real_min

plt.plot(preds_real, label='Predictions')
plt.plot(y_val_real, label='Actual values')
plt.xlabel('test')
plt.legend(loc=0)
plt.show()
print(model.summary())

I got this error:

Using TensorFlow backend.

Traceback (most recent call last):

Training data: (891, 50)

File "E:/Tutorial/new.py", line 31, in Validation data: (178, 822, 50)

train_samples, train_nx, train_ny = train.shape

ValueError: not enough values to unpack (expected 3, got 2)

Answer 1

There's an error in this line:

train = data_processed[:, int(val_split), :]

It should be:

train = data_processed[:int(val_split), :, :]
val = data_processed[int(val_split):, :, :]