mlr_pipeops_multioutlrn: PipeOpMultiLearner

In mlr-org/mlr3multioutput: Multioutput extension for 'mlr3'

Description

Wraps a list of mlr3::Learners into a PipeOp.

Inherits the $param_sets (and therefore $param_set$values) from all Learners it is constructed from.

Format

R6Class object inheriting from PipeOp.

Input and Output Channels

PipeOpMultiLearner has one input channel named "input", taking a Task specific to the Learner type given to learner during construction; both during training and prediction.

PipeOpMultiLearner has one output channel named "output", producing NULL during training and a Multiplicity of Predictions during prediction; this subclass is specific to the Learner type given to learner during construction.

The output during prediction is a Multiplicity of Predictions on the input data, produced by the Learners trained on the training input data.

State

The $state is set to the $state slot of the Learner object. It is a named list with members: of states for each separate Task provided via the incoming Multiplicity.\ Each element contains the following slots:

• model :: any
  Model created by the Learner's $.train() function.

• train_log :: data.table with columns class (character), msg (character)
  Errors logged during training.

• train_time :: numeric(1)
  Training time, in seconds.

• predict_log :: NULL | data.table with columns class (character), msg (character)
  Errors logged during prediction.

• predict_time :: NULL | numeric(1) Prediction time, in seconds.

Parameters

The parameters are exactly the parameters of the Learners wrapped by this object.

Internals

The $state is currently not updated by prediction, so the $state$predict_log and $state$predict_time will always be NULL.

Methods

Methods inherited from PipeOp.

Super class

mlr3pipelines::PipeOp -> PipeOpMultiLearner

Active bindings

id

(character(1))
Access or set the id.

learners

(list())
Access the stored learners.

learner_models

(list())
Access the trained learners.

predict_types

(list())
Access the predict_types.

Methods

Public methods

• PipeOpMultiLearner$new()

• PipeOpMultiLearner$clone()

Inherited methods

• mlr3pipelines::PipeOp$predict()

• mlr3pipelines::PipeOp$print()

• mlr3pipelines::PipeOp$train()

---

Method new()

Initialize a new R6 class.

Usage

PipeOpMultiLearner$new(learners, id = NULL, param_vals = list())

Arguments

learners

list()
List of Learner | character(1), either:

• One learner for each task_type

• One learner for each target, requires list to be named with the Task's target_names.

id

character(1)
Identifier of the resulting object, internally defaulting to the combined ids of the Learner being wrapped.

param_vals

named list
List of hyperparameter settings, overwriting the hyperparameter settings that would otherwise be set during construction. Default list().

---

Method clone()

The objects of this class are cloneable with this method.

Usage

PipeOpMultiLearner$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

See Also

Other PipeOps: mlr_pipeops_multioutsplit, mlr_pipeops_multioutunite

Other Multiplicity PipeOps: mlr_pipeops_multioutsplit, mlr_pipeops_multioutunite

Other Experimental Features: mlr_pipeops_multioutsplit, mlr_pipeops_multioutunite

Examples

library("mlr3")
library("mlr3pipelines")

task = tsk("linnerud")
learners = list(
  classif = lrn("classif.rpart", cp = 0.1),
  regr = lrn("regr.rpart")
)
lrn_po = mlr_pipeops$get("multioutlrn", learners)

# Train the graph
gr = po("multioutsplit") %>>% lrn_po
gr$train(task)
gr$predict(task)

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