Extract the tuning run of a final fit

extract_tune_results() returns the tuning run from which nested_final_fit() selected its parameters on all the data.

Usage

extract_tune_results(x, ...)

Arguments

x

A nested_final_fit from nested_final_fit().

...

Not used, and must be empty.

Value

tune's own tune_results object, so tune's functions apply to it. A final fit that ran no tuning gives an error.

Details

Do not report this run's metrics. They were computed on the resamples that chose the parameters, so they are optimistic on average about the final model. Report the nested estimate, from collect_metrics() on the nested run.

See also

extract_scored_candidates(), nested_final_fit(), nested_tune_grid()

Examples

data(mtcars)

rec <- recipes::recipe(mpg ~ ., data = mtcars) |>
  recipes::step_pca(recipes::all_predictors(), num_comp = tune::tune())
wf <- workflows::workflow(rec, parsnip::linear_reg())

set.seed(1)
folds <- nested_resamples(
  mtcars,
  outside = rsample::vfold_cv(v = 2),
  inside = rsample::vfold_cv(v = 2)
)
set.seed(2)
res <- nested_tune_grid(wf, folds, grid = data.frame(num_comp = 1:2))
set.seed(3)
final <- nested_final_fit(wf, res)
extract_tune_results(final)
#> # Tuning results
#> # 2-fold cross-validation 
#> # A tibble: 2 × 4
#>   splits          id    .metrics         .notes          
#>   <list>          <chr> <list>           <list>          
#> 1 <split [16/16]> Fold1 <tibble [4 × 5]> <tibble [0 × 4]>
#> 2 <split [16/16]> Fold2 <tibble [4 × 5]> <tibble [0 × 4]>