Margins of randomForest Classifier

Share:

Description

Compute or plot the margin of predictions from a randomForest classifier.

Usage

1
2
3
margin(rf, observed)
## S3 method for class 'margin'
plot(x, sort=TRUE, ...)

Arguments

rf

an object of class randomForest, whose type is not regression.

observed

the response variable (a factor) used to train rf.

x

an object of class margin, as returned by the function margin.

sort

Should the data be sorted by their class labels?

...

other graphical parameters to be passed to plot.default.

Value

For margin, the margin of observations from the randomForest classifier. The margin of a data point is defined as the proportion of votes for the correct class minus maximum proportion of votes for the other classes. Thus under majority votes, positive margin means correct classification, and vice versa.

Author(s)

Robert Gentlemen, with slight modifications by Andy Liaw

See Also

randomForest

Examples

1
2
3
4
set.seed(1)
data(iris)
iris.rf <- randomForest(Species ~ ., iris, keep.forest=FALSE)
plot(margin(iris.rf, iris$Species))