Class InterpretableModelHelper

Namespace

AiDotNet.Interpretability

Assembly

AiDotNet.dll

Provides helper methods for interpretable model functionality.

public static class InterpretableModelHelper

Inheritance

object

InterpretableModelHelper

Inherited Members

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

object.ToString()

Methods

GenerateTextExplanationAsync<T>(IInterpretableModel<T>, Tensor<T>, Tensor<T>)

Generates a text explanation for a prediction.

public static Task<string> GenerateTextExplanationAsync<T>(IInterpretableModel<T> model, Tensor<T> input, Tensor<T> prediction)

Parameters

model IInterpretableModel<T>

The model to analyze.

input Tensor<T>

The input data.

prediction Tensor<T>

The prediction made by the model.

Returns

Task<string>

A text explanation of the prediction.

Type Parameters

T

The numeric type for calculations.

GetAnchorExplanationAsync<T>(IInterpretableModel<T>, HashSet<InterpretationMethod>, Tensor<T>, T)

Gets anchor explanation for a given input.

public static Task<AnchorExplanation<T>> GetAnchorExplanationAsync<T>(IInterpretableModel<T> model, HashSet<InterpretationMethod> enabledMethods, Tensor<T> input, T threshold)

Parameters

model IInterpretableModel<T>

The model to analyze.

enabledMethods HashSet<InterpretationMethod>

The set of enabled interpretation methods.

input Tensor<T>

The input to explain.

threshold T

The threshold for anchor construction.

Returns

Task<AnchorExplanation<T>>

An anchor explanation.

Type Parameters

T

The numeric type for calculations.

GetCounterfactualAsync<T>(IInterpretableModel<T>, HashSet<InterpretationMethod>, Tensor<T>, Tensor<T>, int)

Gets counterfactual explanation for a given input and desired output.

public static Task<CounterfactualExplanation<T>> GetCounterfactualAsync<T>(IInterpretableModel<T> model, HashSet<InterpretationMethod> enabledMethods, Tensor<T> input, Tensor<T> desiredOutput, int maxChanges = 5)

Parameters

model IInterpretableModel<T>

The model to analyze.

enabledMethods HashSet<InterpretationMethod>

The set of enabled interpretation methods.

input Tensor<T>

The input to analyze.

desiredOutput Tensor<T>

The desired output.

maxChanges int

The maximum number of changes allowed.

Returns

Task<CounterfactualExplanation<T>>

A counterfactual explanation.

Type Parameters

T

The numeric type for calculations.

GetFeatureInteractionAsync<T>(HashSet<InterpretationMethod>, int, int)

Gets feature interaction effects between two features.

public static Task<T> GetFeatureInteractionAsync<T>(HashSet<InterpretationMethod> enabledMethods, int feature1Index, int feature2Index)

Parameters

enabledMethods HashSet<InterpretationMethod>

The set of enabled interpretation methods.

feature1Index int

The index of the first feature.

feature2Index int

The index of the second feature.

Returns

Task<T>

The interaction effect value.

Type Parameters

T

The numeric type for calculations.

GetGlobalFeatureImportanceAsync<T>(IInterpretableModel<T>, HashSet<InterpretationMethod>)

Gets the global feature importance across all predictions.

public static Task<Dictionary<int, T>> GetGlobalFeatureImportanceAsync<T>(IInterpretableModel<T> model, HashSet<InterpretationMethod> enabledMethods)

Parameters

model IInterpretableModel<T>

The model to analyze.

enabledMethods HashSet<InterpretationMethod>

The set of enabled interpretation methods.

Returns

Task<Dictionary<int, T>>

A dictionary mapping feature indices to importance scores.

Type Parameters

T

The numeric type for calculations.

GetLimeExplanationAsync<T>(IInterpretableModel<T>, HashSet<InterpretationMethod>, Tensor<T>, int)

Gets LIME explanation for a specific input.

public static Task<LimeExplanation<T>> GetLimeExplanationAsync<T>(IInterpretableModel<T> model, HashSet<InterpretationMethod> enabledMethods, Tensor<T> input, int numFeatures = 10)

Parameters

model IInterpretableModel<T>

The model to analyze.

enabledMethods HashSet<InterpretationMethod>

The set of enabled interpretation methods.

input Tensor<T>

The input to explain.

numFeatures int

The number of features to include in the explanation.

Returns

Task<LimeExplanation<T>>

A LIME explanation.

Type Parameters

T

The numeric type for calculations.

GetLocalFeatureImportanceAsync<T>(IInterpretableModel<T>, HashSet<InterpretationMethod>, Tensor<T>)

Gets the local feature importance for a specific input.

public static Task<Dictionary<int, T>> GetLocalFeatureImportanceAsync<T>(IInterpretableModel<T> model, HashSet<InterpretationMethod> enabledMethods, Tensor<T> input)

Parameters

model IInterpretableModel<T>

The model to analyze.

enabledMethods HashSet<InterpretationMethod>

The set of enabled interpretation methods.

input Tensor<T>

The input to analyze.

Returns

Task<Dictionary<int, T>>

A dictionary mapping feature indices to importance scores.

Type Parameters

T

The numeric type for calculations.

GetModelSpecificInterpretabilityAsync<T>(IInterpretableModel<T>)

Gets model-specific interpretability information.

public static Task<Dictionary<string, object>> GetModelSpecificInterpretabilityAsync<T>(IInterpretableModel<T> model)

Parameters

model IInterpretableModel<T>

The model to analyze.

Returns

Task<Dictionary<string, object>>

A dictionary of model-specific interpretability information.

Type Parameters

T

The numeric type for calculations.

GetPartialDependenceAsync<T>(IInterpretableModel<T>, HashSet<InterpretationMethod>, Vector<int>, int)

Gets partial dependence data for specified features.

public static Task<PartialDependenceData<T>> GetPartialDependenceAsync<T>(IInterpretableModel<T> model, HashSet<InterpretationMethod> enabledMethods, Vector<int> featureIndices, int gridResolution = 20)

Parameters

model IInterpretableModel<T>

The model to analyze.

enabledMethods HashSet<InterpretationMethod>

The set of enabled interpretation methods.

featureIndices Vector<int>

The feature indices to analyze.

gridResolution int

The grid resolution to use.

Returns

Task<PartialDependenceData<T>>

Partial dependence data.

Type Parameters

T

The numeric type for calculations.

GetShapValuesAsync<T>(IInterpretableModel<T>, HashSet<InterpretationMethod>, Tensor<T>)

Gets SHAP values for the given inputs.

public static Task<Matrix<T>> GetShapValuesAsync<T>(IInterpretableModel<T> model, HashSet<InterpretationMethod> enabledMethods, Tensor<T> inputs)

Parameters

model IInterpretableModel<T>

The model to analyze.

enabledMethods HashSet<InterpretationMethod>

The set of enabled interpretation methods.

inputs Tensor<T>

The inputs to analyze.

Returns

Task<Matrix<T>>

A matrix containing SHAP values.

Type Parameters

T

The numeric type for calculations.

ValidateFairnessAsync<T>(List<FairnessMetric>)

Validates fairness metrics for the given inputs.

public static Task<FairnessMetrics<T>> ValidateFairnessAsync<T>(List<FairnessMetric> fairnessMetrics)

Parameters

fairnessMetrics List<FairnessMetric>

The fairness metrics to validate.

Returns

Task<FairnessMetrics<T>>

Fairness metrics results.

Type Parameters

T

The numeric type for calculations.