Control aspects of the grid search racing process
control_race( verbose = FALSE, verbose_elim = FALSE, allow_par = TRUE, extract = NULL, save_pred = FALSE, burn_in = 3, num_ties = 10, alpha = 0.05, randomize = TRUE, pkgs = NULL, save_workflow = FALSE, event_level = "first", parallel_over = "everything" )
verbose | A logical for logging results as they are generated. Despite
this argument, warnings and errors are always shown. If using a dark IDE
theme, some logging messages might be hard to see. If this is the case,
try setting the |
---|---|
verbose_elim | A logical for whether logging of the elimination of tuning parameter combinations should occur. |
allow_par | A logical to allow parallel processing (if a parallel backend is registered). |
extract | An optional function with at least one argument (or |
save_pred | A logical for whether the out-of-sample predictions should be saved for each model evaluated. |
burn_in | An integer for how many resamples should be completed for all grid combinations before parameter filtering begins. |
num_ties | An integer for when tie-breaking should occur. If there are
two final parameter combinations being evaluated, |
alpha | The alpha level for a one-sided confidence interval for each parameter combination. |
randomize | Should the resamples be evaluated in a random order? By default, the resamples are evaluated in a random order so the random number seed should be control prior to calling this method (to be reproducible). For repeated cross-validation the randomization occurs within each repeat. |
pkgs | An optional character string of R package names that should be loaded (by namespace) during parallel processing. |
save_workflow | A logical for whether the workflow should be appended to the output as an attribute. |
event_level | A single string containing either "first" or "second".
This argument is passed on to |
parallel_over | A single string containing either If If If |
control_race()#> Racing method control object