SHAP-Tutorial

Model Agnostic Explanations: SHAP

Python implementation of the SHAP(SHapley Additive exPlanations) that is a unified approach to explain the output of any machine learning model.

Dataset

Wine Quality Dataset UCI Machine Learning Repository

Reference Code

Based on code by Scott Lundberg

Based on code by Christophe Rigon

Reference Paper

"A Unified Approach to Interpreting Model Predictions". Scott Lundberg, Su-In Lee (https://arxiv.org/abs/1705.07874)

Requirements

• numpy (1.16.4)
• scipy (1.3.0)
• scikit-learn (0.21.3)
• matplotlib (3.0.3)
• pandas (0.24.2)
• seaborn (0.9.0)
• Keras (2.2.4)
• xgboost (0.90)
• shap (0.29.3)

License

Apache License 2.0

Contacts

If you have any question, please contact Seongman Heo ([email protected]).

XAI Project

This work was supported by Institute for Information & Communications Technology Promotion (IITP) grant funded by the Korea government (MSIT) (No.2017-0-01779, A machine learning and statistical inference framework for explainable artificial intelligence)

• Project Name : A machine learning and statistical inference framework for explainable artificial intelligence (의사결정 이유를 설명할 수 있는 인간 수준의 학습·추론 프레임워크 개발)

• Managed by Ministry of Science and ICT/XAIC

• Participated Affiliation : UNIST, Korea Univ., Yonsei Univ., KAIST, AItrics

• Web Site : http://openXai.org