RangerModel {MachineShop} | R Documentation |
Fast implementation of random forests or recursive partitioning.
RangerModel( num.trees = 500, mtry = NULL, importance = c("impurity", "impurity_corrected", "permutation"), min.node.size = NULL, replace = TRUE, sample.fraction = ifelse(replace, 1, 0.632), splitrule = NULL, num.random.splits = 1, alpha = 0.5, minprop = 0.1, split.select.weights = NULL, always.split.variables = NULL, respect.unordered.factors = NULL, scale.permutation.importance = FALSE, verbose = FALSE )
num.trees |
number of trees. |
mtry |
number of variables to possibly split at in each node. |
importance |
variable importance mode. |
min.node.size |
minimum node size. |
replace |
logical indicating whether to sample with replacement. |
sample.fraction |
fraction of observations to sample. |
splitrule |
splitting rule. |
num.random.splits |
number of random splits to consider for each
candidate splitting variable in the |
alpha |
significance threshold to allow splitting in the
|
minprop |
lower quantile of covariate distribution to be considered for
splitting in the |
split.select.weights |
numeric vector with weights between 0 and 1, representing the probability to select variables for splitting. |
always.split.variables |
character vector with variable names to be
always selected in addition to the |
respect.unordered.factors |
handling of unordered factor covariates. |
scale.permutation.importance |
scale permutation importance by standard error. |
verbose |
show computation status and estimated runtime. |
factor
, numeric
, Surv
mtry
, min.node.size
*, splitrule
*
* included only in randomly sampled grid points
Default values for the NULL
arguments and further model details can be
found in the source link below.
MLModel
class object.
## Requires prior installation of suggested package ranger to run fit(Species ~ ., data = iris, model = RangerModel)