Modeltime workflow sets ranking based on a metric

Source: R/modeltime_wfs_rank.R

generates a ranking of models generated with modeltime_wfs_fit() function.

modeltime_wfs_rank(.wfs_results, rank_metric = NULL, minimize = TRUE)

Arguments

.wfs_results

a tibble generated with the modeltime_wfs_fit() function.
rank_metric

the metric used to generate the ranking 'mae', 'mape','mase','smape','rmse','rsq'.
minimize

a boolean indicating whether to minimize (TRUE) or maximize (FALSE) the metric

Value

a tibble containing the models ranked by a specific metric.

Details

the ranking depends on the metric selected.

See also

sknifedatar website

Examples

library(dplyr)
library(modeltime)
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_rank(.wfs_results = wffits,
                                rank_metric = 'rsq',
                                minimize = FALSE)

#> # A tibble: 1 x 11
#>   .model_id      rank .model_desc .type   mae  mape  mase smape   rmse   rsq
#>   <chr>         <int> <chr>       <chr> <dbl> <dbl> <dbl> <dbl>  <dbl> <dbl>
#> 1 R_date_M_mars     1 EARTH       Test  7577.  6.79 0.542  6.33 12524. 0.553
#> # … with 1 more variable: .fit_model <list>