shap

SKILL.md

SHAP is a unified approach to explain machine learning model outputs using Shapley values from cooperative game theory. This skill provides comprehensive guidance for:

SHAP works with all model types: tree-based models (XGBoost, LightGBM, CatBoost, Random Forest), deep learning models (TensorFlow, PyTorch, Keras), linear models, and black-box models.

See references/explainers.md for detailed information on all explainer types.

使用 SHAP（SHapley Additive exPlanations）建立模型的可解釋性和可解釋性。在解釋機器學習模型預測、計算特徵重要性、生成 SHAP 圖（瀑布圖、蜂群圖、條形圖、散點圖、力圖、熱圖）、調試模型、分析模型偏差或公平性、比較模型或實現可解釋的 AI 時，請使用此技能。適用於基於樹的模型（XGBoost、LightGBM、隨機森林）、深度學習（TensorFlow、PyTorch）、線性模型和任何黑盒模型。 來源：ovachiever/droid-tings。

查看原文