selecttrain_rf: Select and train final random forest

In messamat/globalIRmap: What the Package Does (One Line, Title Case)

Description

Select final random forest learner and train it, optionally adjusting inner sampling strategy for hyperparameter tuning (i.e., cross-validation strategy).

Usage

selecttrain_rf(
  in_rf,
  in_learnerid = NULL,
  in_task = NULL,
  insamp_nfolds = NULL,
  insamp_nevals = NULL
)

Arguments

in_rf	ResampleResult of learner to use or BenchmarkResult from which to extract learner.
in_task	Task containing predictor variables to subset.
insamp_nfolds	(optional) number of cross-validation folds to adjust in inner (hyperparameter tuning) cross-validation
insamp_nevals	(optional) number of cross-validation repetitions in inner (hyperparameter tuning) cross-validation
in_lrnid	id of learner to extract from BenchmarkResult (e.g., "oversample.classif.ranger")

Value

list containing the outer resampling (i.e. performance cross-validation) results named ('rf_outer'), the trained learner ('rf_inner') and the task on which it was trained ('task').

messamat/globalIRmap documentation built on July 4, 2021, 10:48 a.m.