emil (version 1.1-6)

vimp: Variable importance of a fitted model

Description

Note that different methods calculates variable importance in different ways and that they are not directly comparable.

Usage

vimp(object, model, ...)

Arguments

object

Modeling procedure.

model

Fitted model.

...

Sent on to the procedure's variable importance scoring function.

Value

• A vector of length p or an p-x-c matrix of variable importance scores where p is the number of descriptors and c is the number of classes.

See Also

emil

Examples

proc <- modeling.procedure("randomForest")
mod <- fit(proc, x=iris[-5], y=iris$Species)
vimp(proc, mod)