I'm trying to learn how to use RNN for time-series predictions and in all the examples I'm seeing out there they use a sequence of prices to predict the following price. In the examples each target (Y_train[n]) is associated to a sequence or matrix composed of the last 30 prices/steps ([X_train[[n-1],[n-2]....,[n-30]).
However in the real world to accurately predict you need more than the sequence of the last 30 prices, you would also need other... should I say features? Like the last 30 values of volume or the last 30 values of a sentiment index.
So my question is: How do you shape the input of an RNN with two sequences for each target (last 30 prices and last 30 volume values)? This is the example code I'm using with only 1 sequence to use as reference:
import pandas as pd
import numpy as np
from sklearn.preprocessing import MinMaxScaler
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from keras.layers import Dropout
# Dividing Dataset (Test and Train)
train_lim = int(len(df) * 2 / 3)
training_set = df[:train_lim][['Close']]
test_set = df[train_lim:][['Close']]
# Normalizing
sc = MinMaxScaler(feature_range=(0, 1))
training_set_scaled = sc.fit_transform(training_set)
# Shaping Input
X_train = []
y_train = []
X_test = []
for i in range(30, training_set_scaled.size):
X_train.append(training_set_scaled[i - 30:i, 0])
y_train.append(training_set_scaled[i, 0])
X_train, y_train = np.array(X_train), np.array(y_train)
for i in range(30, len(test_set)):
X_test.append(test_set.iloc[i - 30:i, 0])
X_test = np.array(X_test)
# Adding extra dimension ???
X_train = np.reshape(X_train, [X_train.shape[0], X_train.shape[1], 1])
X_test = np.reshape(X_test, [X_test.shape[0], X_test.shape[1], 1])
regressor = Sequential()
# LSTM layer 1
regressor.add(LSTM(units=50, return_sequences=True, input_shape=(X_train.shape[1], 1)))
regressor.add(Dropout(0.2))
# LSTM layer 2,3,4
regressor.add(LSTM(units=50, return_sequences=True))
regressor.add(Dropout(0.2))
regressor.add(LSTM(units=50, return_sequences=True))
regressor.add(Dropout(0.2))
regressor.add(LSTM(units=50, return_sequences=True))
regressor.add(Dropout(0.2))
regressor.add(LSTM(units=50, return_sequences=True))
regressor.add(Dropout(0.2))
# LSTM layer 5
regressor.add(LSTM(units=50))
regressor.add(Dropout(0.2))
# Fully connected layer
regressor.add(Dense(units=1))
# Compiling the RNN
regressor.compile(optimizer='adam', loss='mean_squared_error')
# Fitting the RNN model
regressor.fit(X_train, y_train, epochs=120, batch_size=32)
The dataframe that I'm using is a standard OHLCV with a datetime index so it will look like this:
Datetime Open High Low Close Volume
01/01/2021 102.42 103.33 100.57 101.23 1990
02/01/2021 101.23 105.22 99.45 100.11 1970
... ... ... ... ... ...
01/12/2021 203.22 210.34 199.22 201.11 2600
You can follow exactly the same process, the only difference is that the length of the last dimension of the arrays with the input sequences (X_train and X_test) will be greater than one (as it will be equal to the number of external regressors plus one, where the plus one comes from the fact that the past values of the target are also used as an input).
import pandas as pd
import numpy as np
import yfinance as yf
from sklearn.preprocessing import MinMaxScaler
from keras.models import Sequential
from keras.layers import Dense, LSTM, Dropout
pd.options.mode.chained_assignment = None
# define the target and features
target = ['Close']
features = ['Volume', 'High', 'Low']
# download the data
df = yf.download(tickers=['AAPL'], period='1y')
df = df[features + target]
# split the data
split = int(df.shape[0] * 2 / 3)
df_train = df.iloc[:split, :].copy()
df_test = df.iloc[split:, :].copy()
# scale the data
target_scaler = MinMaxScaler().fit(df_train[target])
df_train[target] = target_scaler.transform(df_train[target])
df_test[target] = target_scaler.transform(df_test[target])
features_scaler = MinMaxScaler().fit(df_train[features])
df_train[features] = features_scaler.transform(df_train[features])
df_test[features] = features_scaler.transform(df_test[features])
# extract the input sequences and output values
sequence_length = 30
X_train, y_train = [], []
for i in range(sequence_length, df_train.shape[0]):
X_train.append(df_train[features + target].iloc[i - sequence_length: i])
y_train.append(df_train[target].iloc[i])
X_train, y_train = np.array(X_train), np.array(y_train)
X_test, y_test = [], []
for i in range(sequence_length, df_test.shape[0]):
X_test.append(df_test[features + target].iloc[i - sequence_length: i])
y_test.append(df_test[target].iloc[i])
X_test, y_test = np.array(X_test), np.array(y_test)
print(X_train.shape)
# (138, 30, 4)
print(X_test.shape)
# (55, 30, 4)
# build and train the model
model = Sequential()
model.add(LSTM(units=50, return_sequences=True, input_shape=X_train.shape[1:]))
model.add(Dropout(0.2))
model.add(LSTM(units=50, return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(units=50, return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(units=50, return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(units=50, return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(units=50))
model.add(Dropout(0.2))
model.add(Dense(units=1))
model.compile(optimizer='adam', loss='mean_squared_error')
model.fit(X_train, y_train, epochs=120, batch_size=32)
model.evaluate(X_test, y_test)
# generate the test set predictions
y_pred = model.predict(X_test)
y_pred = target_scaler.inverse_transform(y_pred)
# plot the test set predictions
df['Predicted Close'] = np.nan
df['Predicted Close'].iloc[- y_pred.shape[0]:] = y_pred.flatten()
df[['Close', 'Predicted Close']].plot()