Variable selection
Arguments
- object
(ObliqueForest) a trained oblique random forest object (see orsf).
- n_predictor_min
(integer) the minimum number of predictors allowed
- verbose_progress
(logical) not implemented yet. Should progress be printed to the console?
Value
a data.table with four columns:
n_predictors: the number of predictors used
stat_value: the out-of-bag statistic
predictors_included: the names of the predictors included
predictor_dropped: the predictor selected to be dropped
Details
tree_seeds
should be specified in object
so that each successive run
of orsf
will be evaluated in the same out-of-bag samples as the initial
run.
Examples
object <- orsf(formula = time + status ~ .,
data = pbc_orsf,
n_tree = 25,
importance = 'anova')
orsf_vs(object, n_predictor_min = 15)
#> n_predictors stat_value predictors_included
#> 1: 15 0.8474921 id,age,sex_f,ascites_1,hepato_1,spiders_1,...
#> 2: 16 0.8322308 id,age,sex_f,ascites_1,hepato_1,spiders_1,...
#> 3: 17 0.8125944 id,age,sex_f,ascites_1,hepato_1,spiders_1,...
#> 4: 18 0.8221782 id,trt_placebo,age,sex_f,ascites_1,hepato_1,...
#> predictor_dropped
#> 1: id
#> 2: trig
#> 3: platelet
#> 4: trt_placebo