home/categories/data-analysis/jaechang-hits-sciagent-skills-skills-biostatistics-shap-model-explainability-skill-md
data-analysisdata-ai

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.

jaechang-hits
maintainer
jaechang-hits
Updated 2/18/2026
Stars
93
Forks
12
quick start

Installation and usage

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.

Installation
$ install --globalskills.sh
Usage

Once installed, you can use this skill by running the following command in your terminal:

skills use shap-model-explainability