preorder2: recursive traversal of tree assigning row numbers of data for...

In rfVarImpOOB: Unbiased Variable Importance for Random Forests

recursive traversal of tree assigning row numbers of data for each node and leaf

Description

Recursive calling stops at leaf after which the function propagates back up the tree

Usage

preorder2(treeRow, bag, tree, verbose = 0)

Arguments

treeRow	current row of tree dataframe to be
bag	The data for the current row
tree	tree (from randomForest::getTree to be traversed
verbose	level of verbosity

Value

tree with rownames in column node

Author(s)

Markus Loecher <[e-mail]>

Examples

data("titanic_train", package = "rfVarImpOOB",  envir = environment())



set.seed(123)

ranRows=sample(nrow(titanic_train), 300)



RF = randomForest::randomForest(formula = Survived ~ Sex + Pclass + PassengerId,

                    data=titanic_train[ranRows,],

                    ntree=5,importance=TRUE,

                    mtry=3,keep.inbag=TRUE, 

                    nodesize = 1)

k=2

tree = randomForest::getTree(RF, k, labelVar = TRUE) 

tree$node=NA

attr(tree, "rflib") = "randomForest"
inbag = rep(rownames(RF$inbag),time=RF$inbag[,k])

#trainBag=titanic_train[inbag,]

trainBag=titanic_train[ranRows,][inbag,]

tree=preorder2(1,trainBag,tree)

rfVarImpOOB documentation built on July 1, 2022, 5:05 p.m.