TSLSTMplus (version 1.0.6)

LSTMModel: LSTMModel class

Description

LSTMModel class for further use in predict function

Usage

LSTMModel(
  lstm_model,
  scale_output,
  scaler_output,
  scale_input,
  scaler_input,
  tsLag,
  xregLag,
  model_structure,
  batch_size,
  lags_as_sequences,
  stateful
)

Value

LSTMModel object

Arguments

lstm_model

LSTM 'keras' model

scale_output

indicate which type of scaler is used in the output

scaler_output

Scaler of output variable (and lags)

scale_input

indicate which type of scaler is used in the input(s)

scaler_input

Scaler of input variable(s) (and lags)

tsLag

Lag of time series data

xregLag

Lag of exogenous variables

model_structure

Summary of the LSTM model previous to training

batch_size

Batch size used during training of the model

lags_as_sequences

Flag to indicate the model has been trained statefully

stateful

Flag to indicate if LSTM layers shall retain its state between batches.

References

Paul, R.K. and Garai, S. (2021). Performance comparison of wavelets-based machine learning technique for forecasting agricultural commodity prices, Soft Computing, 25(20), 12857-12873

Examples

# \donttest{
if (keras::is_keras_available()){
  y<-rnorm(100,mean=100,sd=50)
  x1<-rnorm(100,mean=50,sd=50)
  x2<-rnorm(100, mean=50, sd=25)
  x<-cbind(x1,x2)
  TSLSTM<-ts.lstm(ts=y,
                  xreg = x,
                  tsLag=2,
                  xregLag = 0,
                  LSTMUnits=5,
                  ScaleInput = 'scale',
                  ScaleOutput = 'scale',
                  Epochs=2)
}
# }