mlr_graphs_stacking: Create A Graph to Perform Stacking.

In mlr3pipelines: Preprocessing Operators and Pipelines for 'mlr3'

Create A Graph to Perform Stacking.

Description

Create a new Graph for stacking. A stacked learner uses predictions of several base learners and fits a super learner using these predictions as features in order to predict the outcome.

All input arguments are cloned and have no references in common with the returned Graph.

Usage

pipeline_stacking(
  base_learners,
  super_learner,
  method = "cv",
  folds = 3,
  use_features = TRUE
)

Arguments

base_learners	list of Learner A list of base learners.
super_learner	Learner The super learner that makes the final prediction based on the base learners.
method	character(1) "cv" (default) for building a super learner using cross-validated predictions of the base learners or "insample" for building a super learner using the predictions of the base learners trained on all training data.
folds	integer(1) Number of cross-validation folds. Only used for method = "cv". Default 3.
use_features	logical(1) Whether the original features should also be passed to the super learner. Default TRUE.

Value

Graph

Examples

if (requireNamespace("kknn")) {
library(mlr3)
library(mlr3learners)

base_learners = list(
  lrn("classif.rpart", predict_type = "prob"),
  lrn("classif.kknn", predict_type = "prob")
)
super_learner = lrn("classif.log_reg")

graph_stack = pipeline_stacking(base_learners, super_learner)
graph_learner = as_learner(graph_stack)
graph_learner$train(tsk("german_credit"))
}

mlr3pipelines documentation built on May 31, 2023, 9:26 p.m.