LocalExplainers

All registered LocalExplainer components in DashAI.

Name	Description
ContrastiveShap	Contrastive local explainer: why class P rather than class Q? Standard attribution methods answer "why did the model predict P?".
DiceCounterfactual	Diverse counterfactual explanations via the DiCE library.
GradCam	Gradient-based class activation maps for image classifiers.
KernelShap	Model agnostic local explainer that estimates SHAP values via a weighted linear model.
LimeText	LIME explanations for text classification models.
NearestCounterfactual	Case-based counterfactual explainer for tabular classification.
OcclusionSaliency	Perturbation-based saliency maps for image classifiers.
RegressionKernelShap	Model agnostic local explainer for regression via Kernel SHAP.
TokenAblation	Occlusion-based local explainer for text classification.