GlobalFeatureAblationResult<T>

Models & Types · AiDotNet.Interpretability.Explainers

Global feature ablation result across a dataset.

Constructors

Constructor Summary
GlobalFeatureAblationResult(int[][] featureGroups, string[] featureNames, Vector<T> meanAttributions, Vector<T> meanAbsoluteAttributions, Vector<T> stdAttributions, int numSamples) Initializes a new global feature ablation result.

Properties

Property Summary
Vector<T> MeanAbsoluteAttributions { get; } Gets mean absolute attributions (importance magnitude).
Vector<T> MeanAttributions { get; } Gets mean attributions (can be positive or negative).
Vector<T> StdAttributions { get; } Gets standard deviation of attributions.
int NumSamples { get; } Gets the number of samples analyzed.
int[][] FeatureGroups { get; } Gets the feature groups.
string[] FeatureNames { get; } Gets feature/group names.

Methods

Method Summary
IEnumerable<ValueTuple<string, T, T, T>> GetSortedFeatures() Gets features sorted by importance.
IEnumerable<ValueTuple<string, T, T, T>> GetTopFeatures(int k) Gets the top K most important features globally.
string ToString() Returns a human-readable summary.