shap-model-explainability

Model interpretability using SHAP (SHapley Additive exPlanations) based on Shapley values from game theory. Covers explainer selection (Tree, Deep, Linear, Kernel, Gradient, Permutation), computing feature attributions, and visualization (waterfall, beeswarm, bar, scatter, force, heatmap). Use when explaining ML model predictions, computing feature importance, debugging model behavior, analyzing fairness/bias, or comparing models. Works with tree-based, deep learning, linear, and black-box models.