Skip to contents

Feature Importance Learner Class

Source: R/FeatureImportanceLearner.R
FeatureImportanceLearner.Rd

Feature Importance Learner Class

Feature Importance Learner Class

Public fields

label

(character(1)) Method label

task

(mlr3::Task)

learner

(mlr3::Learner)

measure

(mlr3::Measure)

resampling

(mlr3::Resampling)

resample_result

(mlr3::ResampleResult)

features

(list())

param_set

(paradox::ps())

importance

(data.table::data.table()) Aggregated importance scores

scores

(data.table::data.table()) Individual performance scores used to compute $importance

Methods

Public methods

Method new()

Creates a new instance of this R6 class. This is typically intended for use by derived classes.

Usage

FeatureImportanceLearner$new(
  task,
  learner,
  measure,
  resampling = NULL,
  features = NULL,
  param_set = paradox::ps(),
  label
)

Arguments

task, learner, measure, resampling, features, param_set, label

Used to set fields

Method combine()

Combine two FeatureImportanceLearner objects with computed scores.

Usage

FeatureImportanceLearner$combine(y, ...)

Arguments

y

(FeatureImportanceLearner) Object to combine. Must have computed scores.

...

(any) Unused.

Returns

A new FeatureImportanceLearner of the same subclass as x and y. Currently this method merges the following:

  • $scores is combined, with iter_rsmp increased for y.

  • $importance is re-computed from the combined $scores.

  • $resample_result is combined to a mlr3::BenchmarkResult

  • $resampling is combined into a mlr3::ResamplingCustom, again continuing te iteration count from x with that of y.

Method print()

Print importance scores

Usage

FeatureImportanceLearner$print(...)

Arguments

...

Passed to print()

Method clone()

The objects of this class are cloneable with this method.

Usage

FeatureImportanceLearner$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.