InOutBags: separates data into inbag and outbag

In markusloecher/rfVarImpOOB: Unbiased Variable Importance for Random Forests

Description

convenience function to mitigate risk of improperly disentangling train/test

NOTE: the original row names (too dangerous for repeated rows) are not kept but instead recorded in a separate column

Usage

InOutBags(RF, data, k, inclRowNames = TRUE, NullRowNames = TRUE, 


    verbose = 0)

Arguments

RF	object returned by call to randomForest()
data	data which was used to train the RF. NOTE: assumes setting of inbag=TRUE while training
k	tree number
inclRowNames	create extra column of original row names
NullRowNames	if TRUE set row names to NULL
verbose	level of verbosity

Value

inbag and outbag subsets of the original data

Author(s)

Markus Loecher <[e-mail]>

Examples

rfTit = rfTitanic(nRows = 200,nodesize=10, ntree = 5)





k=1


tmp <- InOutBags(rfTit$RF, rfTit$data, k)

markusloecher/rfVarImpOOB documentation built on July 5, 2020, 6:50 p.m.