Perturbation Feature Importance Base Class

Abstract base class for perturbation-based importance methods PFI, CFI, and RFI

Super class

xplainfi::FeatureImportanceMethod -> PerturbationImportance

Public fields

sampler

(FeatureSampler) Sampler object for feature perturbation

Methods

Public methods

• PerturbationImportance$new()

• PerturbationImportance$clone()

Inherited methods

• xplainfi::FeatureImportanceMethod$combine()
• xplainfi::FeatureImportanceMethod$compute()
• xplainfi::FeatureImportanceMethod$print()
• xplainfi::FeatureImportanceMethod$reset()

---

Method new()

Creates a new instance of the PerturbationImportance class

Usage

PerturbationImportance$new(
  task,
  learner,
  measure,
  resampling = NULL,
  features = NULL,
  sampler = NULL,
  relation = "difference",
  iters_perm = 1L
)

Arguments

task, learner, measure, resampling, features

Passed to FeatureImportanceMethod

sampler

(FeatureSampler) Sampler to use for feature perturbation

relation

(character(1)) How to relate perturbed scores to originals. Can be overridden in $compute().

iters_perm

(integer(1)) Number of permutation iterations. Can be overridden in $compute().

---

Method clone()

The objects of this class are cloneable with this method.

Usage

PerturbationImportance$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.