Modeltime workflow sets refit

applies the modeltime_refit() function from 'modeltime' package to the object generated from the modeltime_wfs_fit() function (or the filtered version after the modeltime_wfs_bestmodel() is applied).

modeltime_wfs_refit(.wfs_results, .serie)

Arguments

.wfs_results	tibble of combination of recipes and models fitted, generated with the modeltime_wfs_fit() function.
.serie	a time series dataframe.

Value

a tibble containing the re-trained models.

Details

each workflow is now re-trained using all the available data.

Examples

library(modeltime)
library(dplyr)
library(earth)

data <- sknifedatar::data_avellaneda %>% 
  mutate(date=as.Date(date)) %>% 
  filter(date<'2012-06-01')

recipe_date <- recipes::recipe(value ~ ., data = data) %>% 
  recipes::step_date(date, features = c('dow','doy','week','month','year')) 

mars <- parsnip::mars(mode = 'regression') %>%
  parsnip::set_engine('earth')

wfsets <- workflowsets::workflow_set(
  preproc = list(
    R_date = recipe_date),
  models  = list(M_mars = mars),
  cross   = TRUE)

wffits <- sknifedatar::modeltime_wfs_fit(.wfsets = wfsets, 
                                         .split_prop = 0.8, 
                                         .serie = data)
#> ── MODEL: R_date_M_mars 
#> ✓ Training finished OK.
#> 
#> 
#> ── 1 models fitted ♥ ───────────────────────────────────────────────────────────
#> 
#> ── 0 models deleted x ──
#> 

sknifedatar::modeltime_wfs_refit(.wfs_results = wffits,
                                 .serie = data)
#> # Modeltime Table
#> # A tibble: 1 x 3
#>   .model_id     .model     .model_desc
#>   <chr>         <list>     <chr>      
#> 1 R_date_M_mars <workflow> EARTH