PredictionMultioutput: Prediction Object for MultiOutputer Analysis

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

Description

This object wraps the predictions returned by a learner of class LearnerMultiOutput, i.e. the predicted partition and MultiOutputer probability.

Super class

mlr3::Prediction -> PredictionMultioutput

Active bindings

predictions

(list())
Access the stored predictions.

missing

(integer())
Returns row_ids for which the predictions are missing or incomplete.

row_ids

(integer())
Access the stored row_ids.

Methods

Public methods

• PredictionMultioutput$new()

• PredictionMultioutput$print()

• PredictionMultioutput$score_separate()

• PredictionMultioutput$clone()

Inherited methods

• mlr3::Prediction$format()

• mlr3::Prediction$help()

• mlr3::Prediction$score()

---

Method new()

Creates a new instance of this R6 class.

Usage

PredictionMultioutput$new(
  task = NULL,
  row_ids = task$row_ids,
  predictions = list(),
  check = TRUE,
  ...
)

Arguments

task

(TaskMultioutput)
Task, used to extract defaults for row_ids.

row_ids

(integer())
Row ids of the predicted observations, i.e. the row ids of the test set.

predictions

(list())
(Named) list of per-target predictions. Used to construct the Prediction-object.

check

(logical(1))
If TRUE, performs argument checks and predict type conversions.

...

(list())
(Named) list of per-target truths. Only used for compatibility with Prediction$new().

---

Method print()

Printer for the Prediction object.

Usage

PredictionMultioutput$print(...)

Arguments

...

(any)
Not used.

---

Method score_separate()

Returns scores for each measure separately.

Usage

PredictionMultioutput$score_separate(measures, task)

Arguments

measures

list
List of MeasureMultioutput to score.

task

TaskMultioutput
Task to use for scoring

Returns

A numeric() vector of scores.

---

Method clone()

The objects of this class are cloneable with this method.

Usage

PredictionMultioutput$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

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