Module explainability 

Model explainability and interpretability metrics

This module provides metrics for evaluating model explainability, interpretability, and trustworthiness. These metrics help assess how well a model’s predictions can be understood and trusted by humans.

Re-exports

pub use feature_importance::*;

pub use global_explanations::*;

pub use local_explanations::*;

pub use uncertainty_quantification::*;

Modules

feature_importance

Feature importance analysis for model explainability

global_explanations

Global explanation methods for understanding overall model behavior

local_explanations

Local explanation methods for individual predictions

uncertainty_quantification

Uncertainty quantification methods for model predictions

Structs

ExplainabilityEvaluator

Explainability evaluator

ExplainabilityMetrics

Explainability metrics suite

UncertaintyMetrics

Uncertainty quantification metrics

Enums

ExplanationMethod

Explanation method types

Functions

compute_interpretability_score

Compute model interpretability score