I tried to use LSTM network using reset callback for expected future predictions as follows:
import numpy as np, pandas as pd, matplotlib.pyplot as plt
from keras.models import Sequential
from keras.layers import Dense, LSTM
from keras.callbacks import LambdaCallback
from sklearn.metrics import mean_squared_error
from sklearn.preprocessing import MinMaxScaler
from sklearn.preprocessing import StandardScaler
raw = np.sin(2*np.pi*np.arange(1024)/float(1024/2)).reshape(-1,1)
scaler = MinMaxScaler(feature_range=(-1, 1))
scaled = scaler.fit_transform(raw)
data = pd.DataFrame(scaled)
window_size = 3
data_s = data.copy()
for i in range(window_size):
data = pd.concat([data, data_s.shift(-(i+1))], axis = 1)
data.dropna(axis=0, inplace=True)
ds = data.values
n_rows = ds.shape[0]
ts = int(n_rows * 0.8)
train_data = ds[:ts,:]
test_data = ds[ts:,:]
train_X = train_data[:,:-1]
train_y = train_data[:,-1]
test_X = test_data[:,:-1]
test_y = test_data[:,-1]
print (train_X.shape)
print (train_y.shape)
print (test_X.shape)
print (test_y.shape)
batch_size = 3
n_feats = 1
train_X = train_X.reshape(train_X.shape[0], batch_size, n_feats)
test_X = test_X.reshape(test_X.shape[0], batch_size, n_feats)
print(train_X.shape, train_y.shape)
regressor = Sequential()
regressor.add(LSTM(units = 64, batch_input_shape=(1, batch_size, n_feats),
activation = 'sigmoid',
stateful=True, return_sequences=False))
regressor.add(Dense(units = 1))
regressor.compile(optimizer = 'adam', loss = 'mean_squared_error')
resetCallback = LambdaCallback(on_epoch_begin=lambda epoch,logs: regressor.reset_states())
regressor.fit(train_X, train_y, batch_size=1, epochs = 1, callbacks=[resetCallback])
previous_inputs = test_X
regressor.reset_states()
previous_predictions = regressor.predict(previous_inputs, batch_size=1)
previous_predictions = scaler.inverse_transform(previous_predictions).reshape(-1)
test_y = scaler.inverse_transform(test_y.reshape(-1,1)).reshape(-1)
plt.plot(test_y, color = 'blue')
plt.plot(previous_predictions, color = 'red')
plt.show()
inputs = test_X
future_predicitons = regressor.predict(inputs, batch_size=1)
n_futures = 7
regressor.reset_states()
predictions = regressor.predict(previous_inputs, batch_size=1)
print (predictions)
future_predicts = []
currentStep = predictions[:,-1:,:]
for i in range(n_futures):
currentStep = regressor.predict(currentStep, batch_size=1)
future_predicts.append(currentStep)
regressor.reset_states()
future_predicts = np.array(future_predicts, batch_size=1).reshape(-1,1)
future_predicts = scaler.inverse_transform(future_predicts).reshape(-1)
all_predicts = np.concatenate([predicts, future_predicts])
plt.plot(all_predicts, color='red')
plt.show()
but i got the following error. I could not figure out how to solve it for expected predictions.
currentStep = predictions[:,-1:,:]
IndexError: too many indices for array
PS this code has been adapted from https://github.com/danmoller/TestRepo/blob/master/testing%20the%20blog%20code%20-%20train%20and%20pred.ipynb
When you defined the regressor, you used return_sequences=False.
So, the regressor is returning 2D, tensors (without the steps), not 3D.
So you can't get elements from predictions using three indices as you did.
Possibilities:
return_sequences=False, every prediction will be only the last step. return_sequences=True, every prediction will contain steps, even if only one step.