Feature Importance Methods for Global Explanations

---

Documentation for package ‘xplainfi’ version 1.1.0

• DESCRIPTION file.
• User guides, package vignettes and other documentation.
• Package NEWS.

Help Pages

%||%	Default value for 'NULL'
CFI	Conditional Feature Importance
check_groups	Check group specification
ConditionalARFSampler	ARF-based Conditional Sampler
ConditionalCtreeSampler	(experimental) Conditional Inference Tree Conditional Sampler
ConditionalGaussianSampler	Gaussian Conditional Sampler
ConditionalKNNSampler	k-Nearest Neighbors Conditional Sampler
ConditionalSAGE	Conditional SAGE
ConditionalSampler	Conditional Feature Sampler
FeatureImportanceMethod	Feature Importance Method Class
FeatureSampler	Feature Sampler Class
KnockoffGaussianSampler	Gaussian Knockoff Conditional Sampler
KnockoffSampler	Knockoff Sampler
LOCO	Leave-One-Covariate-Out (LOCO)
MarginalPermutationSampler	Marginal Permutation Sampler
MarginalReferenceSampler	Marginal Reference Sampler
MarginalSAGE	Marginal SAGE
MarginalSampler	Marginal Sampler Base Class
op-null-default	Default value for 'NULL'
PerturbationImportance	Perturbation Feature Importance Base Class
PFI	Permutation Feature Importance
RFI	Relative Feature Importance
rsmp_all_test	Create a resampling with all data being test data
SAGE	Shapley Additive Global Importance (SAGE) Base Class
sim_dgp_confounded	Simulation DGPs for Feature Importance Method Comparison
sim_dgp_correlated	Simulation DGPs for Feature Importance Method Comparison
sim_dgp_ewald	Simulate data as in Ewald et al. (2024)
sim_dgp_independent	Simulation DGPs for Feature Importance Method Comparison
sim_dgp_interactions	Simulation DGPs for Feature Importance Method Comparison
sim_dgp_mediated	Simulation DGPs for Feature Importance Method Comparison
sim_dgp_scenarios	Simulation DGPs for Feature Importance Method Comparison
wvim_design_matrix	Create Feature Selection Design Matrix
xplain_opt	xplainfi Package Options