SSLR (version 0.9.3.1)

fit_random_forest,RandomForestSemisupervised-method: Fit Random Forest

Description

method in classRandomForestSemisupervised used to build a Decision Tree

Usage

# S4 method for RandomForestSemisupervised
fit_random_forest(
  object,
  X,
  y,
  mtry = 2,
  trees = 500,
  min_n = 2,
  w = 0.5,
  replace = TRUE,
  tree_max_depth = Inf,
  sampsize = if (replace) nrow(X) else ceiling(0.632 * nrow(X)),
  min_samples_leaf = if (!is.null(y) && !is.factor(y)) 5 else 1,
  allowParallel = TRUE
)

Arguments

object

A RandomForestSemisupervised object

X

A object that can be coerced as data.frame. Training instances

y

A vector with the labels of the training instances. In this vector the unlabeled instances are specified with the value NA.

mtry

number of features in each decision tree

trees

number of trees. Default is 5

min_n

number of minimum samples in each tree

w

weight parameter ranging from 0 to 1

replace

replacing type in sampling

tree_max_depth

maximum tree depth. Default is Inf

sampsize

Size of sample. Default if (replace) nrow(x) else ceiling(.632*nrow(x))

min_samples_leaf

the minimum number of any terminal leaf node

allowParallel

Execute Random Forest in parallel if doParallel is loaded. Default is TRUE

Value

list of decision trees