-
+ (빨간막대) 이면, 모델 예측값들을 높게끔 푸시한다는 뜻
샤프 발류는 한 피쳐의 모델 아웃풋 변화에 대한 기여도이다.
lightgbm shap example : https://mlflow.org/docs/latest/python_api/mlflow.lightgbm.html#mlflow.lightgbm.load_model
mlflow.lightgbm — MLflow 2.1.1 documentation
pip_requirements – Either an iterable of pip requirement strings (e.g. ["lightgbm", "-r requirements.txt", "-c constraints.txt"]) or the string path to a pip requirements file on the local filesystem (e.g. "requirements.txt"). If provided, this describes
mlflow.org
lundberg github : https://github.com/slundberg/shap
'ML > XAI' 카테고리의 다른 글
Causal Impact (0) 2023.04.18 causal impact (0) 2023.02.07 causal impact (0) 2023.01.25 SHAP for imbalanced data (0) 2023.01.03 SHAP with train vs. test data (0) 2023.01.02