mlr (version 1.1-18)

makeBaggingWrapper: Fuse learner with the bagging technique.

Description

Fuses a learner with the bagging method (i.e., similar to what a randomForest does). Creates a learner object, which can be used like any other learner object. Models can easily be accessed via getBaggingModels.

Usage

makeBaggingWrapper(learner, bag.iters = 10L,
    bag.replace = TRUE, bag.size, bag.feats = 1)

Value

[Learner].

Details

Bagging is implemented as follows: For each iteration a random data subset is sampled (with or without replacement) and potentially the number of features is also restricted to a random subset. Note that this is usually handled in a slightly different way in the random forest where features are sampled at each tree split).

Prediction works as follows: For classification we do majority voting to create a discrete label and probabilites are predicted by considering the proportions of all predicted labels. For regression the mean value accross predictions is computed. Prediction of local standard error for regression is a current TODO and currently not implemented.