SurrogateExplanation<T>
Models & Types · AiDotNet.Interpretability.Explainers
Represents a global surrogate model explanation.
Constructors
| Constructor |
Summary |
SurrogateExplanation(Vector<T> coefficients, T intercept, T fidelity, string[] featureNames) |
Initializes a new surrogate explanation. |
Properties
| Property |
Summary |
T Fidelity { get; } |
Gets the fidelity (R²) indicating how well the surrogate approximates the black box. |
T Intercept { get; } |
Gets the intercept of the linear surrogate model. |
Vector<T> Coefficients { get; } |
Gets the coefficients of the linear surrogate model. |
int NumFeatures { get; } |
Gets the number of features. |
string[] FeatureNames { get; } |
Gets the feature names, if available. |
Methods
| Method |
Summary |
IEnumerable<ValueTuple<int, string, T>> GetSortedFeatures() |
Gets features sorted by absolute coefficient (most important first). |
IEnumerable<ValueTuple<int, string, T>> GetTopFeatures(int n) |
Gets the top N most important features according to the surrogate model. |
string ToString() |
Returns a human-readable summary. |