Enum InterpretationMethod

Namespace

AiDotNet.Interpretability

Assembly

AiDotNet.dll

Enumeration of interpretation methods supported by interpretable models.

public enum InterpretationMethod

Fields

Anchor = 4

Anchor explanations for rule-based interpretations.

Counterfactual = 3

Counterfactual explanations to understand decision boundaries.

FeatureImportance = 5

Feature importance analysis.

FeatureInteraction = 6

Feature interaction analysis.

LIME = 1

LIME (Local Interpretable Model-agnostic Explanations) for local explanations.

PartialDependence = 2

Partial dependence plots to show feature effects.

SHAP = 0

SHAP (SHapley Additive exPlanations) values for feature importance.