Class GroupFairnessEvaluator<T>

Namespace

AiDotNet.Interpretability

Assembly

AiDotNet.dll

Group-level fairness evaluator that focuses on equalized performance across groups. Computes equal opportunity and equalized odds when actual labels are available. Focuses on ensuring similar error rates across demographic groups.

public class GroupFairnessEvaluator<T> : FairnessEvaluatorBase<T>, IFairnessEvaluator<T>

Type Parameters

T

The numeric type for calculations.

Inheritance

object

FairnessEvaluatorBase<T>

GroupFairnessEvaluator<T>

Implements

IFairnessEvaluator<T>

Inherited Members

FairnessEvaluatorBase<T>._numOps

FairnessEvaluatorBase<T>._isHigherFairnessBetter

FairnessEvaluatorBase<T>.EvaluateFairness(IFullModel<T, Matrix<T>, Vector<T>>, Matrix<T>, int, Vector<T>)

FairnessEvaluatorBase<T>.IsHigherFairnessBetter

FairnessEvaluatorBase<T>.IsBetterFairnessScore(T, T)

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

object.ToString()

Constructors

GroupFairnessEvaluator()

Initializes a new instance of the GroupFairnessEvaluator class.

public GroupFairnessEvaluator()

Methods

GetFairnessMetrics(IFullModel<T, Matrix<T>, Vector<T>>, Matrix<T>, int, Vector<T>?)

Computes group-level fairness metrics focusing on performance equity.

protected override FairnessMetrics<T> GetFairnessMetrics(IFullModel<T, Matrix<T>, Vector<T>> model, Matrix<T> inputs, int sensitiveFeatureIndex, Vector<T>? actualLabels)

Parameters

model IFullModel<T, Matrix<T>, Vector<T>>

inputs Matrix<T>

sensitiveFeatureIndex int

actualLabels Vector<T>

Returns

FairnessMetrics<T>