predict.etree {etree}

Predictions for Energy Trees

Description

Compute predictions for objects of class "etree" (i.e., fitted Energy Trees as returned by etree(), or as contained in the ensemble element of a fitted Random Energy Forest).

Usage

## S3 method for class 'etree'
predict(object, newdata = NULL, perm = NULL, ...)

Arguments

object

A fitted Energy Tree of class "etree".

newdata

Optional set of new covariates used to make predictions. Must be provided as a list, where each element is a different variable. Currently available types and the form they need to have to be correctly recognized are the following:

• Numeric: numeric or integer vectors;

• Nominal: factors;

• Functions: objects of class "fdata";

• Graphs: (lists of) objects of class "igraph".

Each element (i.e., variable) in the covariates list must have the same length(), which corresponds to the (new) sample size. If newdata is omitted, fitted values are returned.

perm

Optional character vector of variable names. Splits of nodes with a primary split in any of these variables will be permuted (after dealing with surrogates). Note that surrogate split in the perm variables will not be permuted.

...

Additional arguments.

Details

The predict() method for "etree" objects yields predictions for fitted Energy Trees as returned by etree() or as contained in the ensemble element of a fitted Random Energy Forest. Predictions are based either on fitted values (if newdata is NULL) or on the new set of covariates (if newdata is provided). The values of split_type and coeff_split_type, as well as the number of components for each structured covariate (needed to compute an equivalent representation for the covariates in newdata when split_type = "coeff"), are automatically retrieved from the object of class "etree".

Value

Predictions, in the form of a factor for classification or as a numeric vector for regression.