caretPredict: Prediction wrapper for 'train'

In zachmayer/caretEnsemble: Ensembles of Caret Models

Prediction wrapper for train

Description

This is a prediction wrapper for train with several features: - If newdata is null, return stacked predictions from the training job, rather than in-sample predictions. - Always returns probabilities for classification models. - Optionally drops one predicted class for classification models. - Always returns a data.table

Usage

caretPredict(
  object,
  newdata = NULL,
  excluded_class_id = 1L,
  aggregate_resamples = TRUE,
  ...
)

Arguments

object	a train object
newdata	New data to use for predictions. If NULL, stacked predictions from the training data are returned.
excluded_class_id	an integer indicating the class to exclude. If 0L, no class is excluded
aggregate_resamples	logical, whether to aggregate resamples by keys. Default is TRUE.
...	additional arguments to pass to predict.train, if newdata is not NULL

Value

a data.table

zachmayer/caretEnsemble documentation built on Dec. 19, 2024, 5:17 p.m.