shipunov (version 1.0)

BootRF: Bootstrap with 'randomForest()'

Description

How to bootstrap with 'randomForest()'

Usage

BootRF(data, classes, sub="none", nsam=4, nboot=1000, misclass=TRUE)

Arguments

data

Data frame to classify

classes

Character vector of class names

sub

Subsample to use (see example)

nsam

Number of training items from each level of grouping factor, default 4

nboot

Number of iterations

misclass

Calculate misclassification table?

Value

Returns all predictions as character matrix, each boot is a column

Details

This an example of how to bootstrap with 'randomForest::randomForest()'.

Samples equal numbers ('nsam') of training items from each level of grouping factor.

Allows to use subset of data which will be used for subsampling of training data.

See Also

randomForest::randomForest, Dev

Examples

# NOT RUN {
iris.sub <- 1:nrow(iris) %in% seq(1, nrow(iris), 5)
# }
# NOT RUN {
## could be slow
iris.bootrf <- BootRF(iris[, -5], iris[, 5], sub=iris.sub)
iris.bootrf <- BootRF(iris[, -5], iris[, 5])
## naturally, in the second case misclassification rate is lower
# }