Fit a workflow_set object over multiple time series

allows a workflow_set object to be fitted over multiple time series, using models from the 'modeltime' package.

modeltime_wfs_multifit(serie, .prop, .wfs)

Arguments

serie	nested time series.
.prop	series train/test partition ratio.
.wfs	worklows_set object.

Value

A list of 2 items. The first component is a tibble with a first column that contains the name of the series, and a second column called 'nested_column' that stores the time series, then a column for each workflow for each series are stored. The last 2 columns, 'nested_model' and 'calibration', store the 'n' trained workflows for each series and the adjustment metrics on the test partition. The second element is a tibble saved with the name of 'models_accuracy', it allows to visualize the performance of each workflow for each series according to a set of metrics.

Examples

library(dplyr)
library(earth)

df <- sknifedatar::emae_series

datex <- '2020-02-01'
df_emae <- df %>%
dplyr::filter(date <= datex) %>% 
tidyr::nest(nested_column=-sector) %>% 
head(2)

receta_base <- recipes::recipe(value ~ ., data = df %>% select(-sector))

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

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

sknifedatar::modeltime_wfs_multifit(.wfs = wfsets,
                                    .prop = 0.8, 
                                    serie = df_emae)
#> ✓ Workflow training finished OK.
#> ✓ Workflow training finished OK.
#> 
#> ── 1 models fitted ♥ ───────────────────────────────────────────────────────────
#> 
#> ── 0 models deleted x ──
#> 
#> $table_time
#> # A tibble: 2 x 5
#>   sector    nested_column     R_date_M_mars nested_model       calibration      
#>   <chr>     <list>            <list>        <list>             <list>           
#> 1 Comercio  <tibble [194 × 2… <workflow>    <model_time [1 × … <model_time [1 ×…
#> 2 Ensenanza <tibble [194 × 2… <workflow>    <model_time [1 × … <model_time [1 ×…
#> 
#> $models_accuracy
#> # A tibble: 2 x 11
#>   name_serie .model_id .model_names  .model_desc .type   mae  mape  mase smape
#>   <chr>          <int> <chr>         <chr>       <chr> <dbl> <dbl> <dbl> <dbl>
#> 1 Comercio           1 R_date_M_mars EARTH       Test  10.8   7.33 0.848  7.29
#> 2 Ensenanza          1 R_date_M_mars EARTH       Test   5.15  3.23 3.74   3.16
#> # … with 2 more variables: rmse <dbl>, rsq <dbl>
#>