ggRandomForests (version 1.0.0)

gg_vimp.ggRandomForests: Variable Importance (VIMP) data object

Description

gg_vimp Extracts the variable importance (VIMP) information from a a randomForestSRC::rfsrc object.

Usage

gg_vimp.ggRandomForests(object, ...)

Arguments

object

A randomForestSRC::rfsrc object or output from randomForestSRC::vimp

...

arguments passed to the randomForestSRC::vimp.rfsrc function if the randomForestSRC::rfsrc object does not contain importance information.

Value

• a matrix of VIMP measures, in rank order.

References

Ishwaran H. (2007). Variable importance in binary regression trees and forests, Electronic J. Statist., 1:519-537.

See Also

plot.gg_vimp randomForestSRC::rfsrc randomForestSRC::vimp

Examples

## ------------------------------------------------------------
## classification example
## ------------------------------------------------------------
# iris_rf <- rfsrc(Species ~ ., data = iris)
data(iris_rf, package="ggRandomForests")
ggrf <- gg_vimp(iris_rf)
plot(ggrf)

## ------------------------------------------------------------
## regression example
## ------------------------------------------------------------

# airq.obj <- rfsrc(Ozone ~ ., airquality)
data(airq_rf, package="ggRandomForests")
ggrf <- gg_vimp(airq_rf)
plot(ggrf)

## ------------------------------------------------------------
## survival example
## ------------------------------------------------------------
data(veteran_rf, package="ggRandomForests")
ggrf <- gg_vimp(veteran_rf)
plot(ggrf)