Boruta (version 1.6)

Boruta plot: Plotting boxplots of importance

Description

plot.Boruta visualises ZScoreHistory element of the Boruta object. Each attribute (including randomised meta-attributes, randMax, randMean, randMin) is represented as a boxplot. Its colour corresponds to a Boruta decision; see colCode argument note. Boxplots are ordered due to their median ZScore.

Usage

## S3 method for class 'Boruta':
plot(x,colCode=c('green','yellow','red','blue'),sort=TRUE,
		whichRand=c(TRUE,TRUE,TRUE),col=NULL,
		xlab='Attributes',ylab='Importance',...)

Arguments

x

an object of class Boruta.

colCode

a vector containing colour codes for attribute decisions, respectively Confirmed, Tentative, Rejected, Random.

sort

controls weather boxplots should be ordered, or left in original order.

whichRand

a vector controlling which randomised meta-attributes should be drawn; respectively randMax, randMean, randMin.

col

standard col attribute. If given, suppresses colCode.

xlab,ylab,...

additional graphical parameters that will be passed to boxplot.

Value

• None.

Examples

library(mlbench); data(HouseVotes84);
na.omit(HouseVotes84)->hvo;
#Takes some time, so be patient
Boruta(Class~.,data=hvo,doTrace=2)->Bor.hvo;
print(Bor.hvo);
plot(Bor.hvo);