readForest: Read forest

In sumbose/iRF: Iterative Random Forests

Description

Read out metadata from random forest decision paths

Usage

readForest(rand.forest, x, return.node.feature = TRUE,
  return.node.obs = TRUE, varnames.grp = NULL, oob.importance = TRUE,
  first.split = TRUE, n.core = 1)

Arguments

rand.forest	an object of class randomForest.
x	numeric feature matrix.
return.node.feature	if True, will return sparse matrix indicating features used on each decision path of the rand.forest.
return.node.obs	if True, will return sparse matrix indicating observations in x that fall in each leaf node of rand.forest.
varnames.grp	grouping "hyper-features" for RIT search. Features with the same name will be treated as identical for interaction search.
oob.importance	if TRUE, importance measures are evaluated on OOB samples.
first.split	if True, splitting threshold will only be evaluated for the first time a feature is selected.
n.core	number of cores to use. If -1, all available cores are used.

Value

a list containing the following entries

• tree.infodata frame of metadata for each leaf node in rand.forest

• node.featureoptional sparse matrix indicating feature usage on each decision path

• node.obsoptional sparse matrix indicating observations appearing in each leaf node

sumbose/iRF documentation built on March 12, 2021, 7:36 a.m.