add_all_univariate_forecast_models: Add all univariate forecast models

In ing-bank/tsforecast: Time Series Forecasting Pipeline

Description

add_all_univariate_forecast_models is a wrapper function to add multiple univariate forecast models to a (named) list of forecast models. The forecast models are created based on multiple calls of the add_univariate_forecast_model function with specific sets of parameters, which are each used to forecast a specific number of periods ahead. The fc_methods parameter can be used to control which forecast models are added.

Usage

add_all_univariate_forecast_models(
  ts_object_train,
  fc_models = list(),
  periods_ahead = 1,
  periods_history = Inf,
  fc_methods = supported_fc_methods_uni_var(),
  verbose = FALSE,
  parallel = FALSE
)

Arguments

ts_object_train	A time series object, which contains only the training data.
fc_models	A named list of forecast models, with for each forecast model a list with the model itself and a table with forecast values.
periods_ahead	A positive integer value indicating the number of periods to forecast ahead.
periods_history	A positive integer value indicating the number of historic datapoints to use for training, which is only relevant for specific forecast methods such as drift and mean.
fc_methods	A character vector specifying the forecast methods to add. For more info `?supported_fc_methods`.
verbose	Boolean, which is set to TRUE if status updates are valued, or set to FALSE if they are not.

Value

A named list of forecast models, with for each forecast model a list with the model itself and a table with forecast values.

Examples

ts_object_train <- tstools::initialize_ts_forecast_data(
      data = dummy_gasprice,
      date_col = "year_month", 
      col_of_interest = "gasprice", 
      group_cols = c("state", "oil_company"), 
      xreg_cols = c("spotprice", "gemprice")
   ) %>% 
   dplyr::filter(grouping == "state = New York   &   oil_company = CompanyA") %>% 
   tstools::transform_data_to_ts_object()
fc_models <- add_all_univariate_forecast_models(
   ts_object_train = ts_object_train,
   periods_ahead = 12,
   verbose = T
)

ing-bank/tsforecast documentation built on Sept. 18, 2020, 9:40 a.m.