TaskMultioutput: Multioutput Task

Description Super classes Public fields Methods

Description

This task specializes mlr3::Task for multi-output problems. The task_type is set to "multioutput".

Predefined tasks are stored in the dictionary mlr_tasks. Properties for this mlr3::Task are 'multilabel' if the mlr3::Task has only binary classification targets and 'multioutput' else.

Super classes

mlr3::Task -> mlr3::TaskSupervised -> TaskMultioutput

Public fields

task_types

(character())
See initialize.

Methods

Public methods

Inherited methods

Method new()

Creates a new instance of this R6 class.

Usage
TaskMultioutput$new(
  id,
  backend,
  target,
  task_types = NULL,
  task_type = "multioutput"
)
Arguments
id

(character(1))
Identifier for the new instance.

backend

(DataBackend)
Either a DataBackend, or any object which is convertible to a DataBackend with as_data_backend(). E.g., a data.frame() will be converted to a DataBackendDataTable.

target

(character)
Name of the target columns.

task_types

character
Named character vector of per-target task-types. E.g. c(tgt1 = "regr", tgt2 = "classif")

task_type

(character(1))
Task type of the constructed task. Defautls to "multioutput".


Method formula()

Usage
TaskMultioutput$formula(rhs = ".")

Method clone()

The objects of this class are cloneable with this method.

Usage
TaskMultioutput$clone(deep = FALSE)
Arguments
deep

Whether to make a deep clone.


mlr-org/mlr3multioutput documentation built on Nov. 22, 2020, 1:17 p.m.