Feature importance of random forest.

Description

Feature importance of random forest.

Usage

1

Arguments

object

Fitted randomForest classifier

type

Importance can be assessed in two ways:

1.

Permuted out-of-bag prediction error (default). This can only be used if the classifier was fitted with argument prediction=TRUE which is default.

2.

Total decrease in node impurity.

...

Ignored.

Value

An prediction vector with elements corresponding to variables.

Author(s)

Christofer B├Ącklin

See Also

emil, fit_randomForest, predict_randomForest, modeling_procedure


Questions? Problems? Suggestions? or email at ian@mutexlabs.com.

Please suggest features or report bugs with the GitHub issue tracker.

All documentation is copyright its authors; we didn't write any of that.