tskeras {forecasteR}R Documentation

keras model for time series.

Description

keras model for time series.

Usage

tskeras(x, model, lag = 1, batch_size = 1, epochs = 20, verbose = 0)

Arguments

x

a ts object.

model

a keras model.

lag

indicates by value to test alpha, beta and gamma.

batch_size

indicates by value to test alpha, beta and gamma.

epochs

indicates by value to test alpha, beta and gamma.

verbose

indicates by value to test alpha, beta and gamma.

Value

keras model

Author(s)

Diego Jimenez <diego.jimenez@promidat.com>

Examples


  library(keras)
  modelo.deep <- keras_model_sequential() %>% 
  layer_lstm(
    units = 10, activation = 'tanh', batch_input_shape = c(1, 12, 1),
    return_sequences = TRUE, stateful = TRUE) %>%
  layer_dense(units = 1) %>%
  compile(loss = 'mse', optimizer = 'adam', metrics = 'mse')
  tskeras(AirPassengers, modelo.deep, lag = 12, epochs = 1)



[Package forecasteR version 2.0.2 Index]