choshin84 / learning_memo

personal learning memo
0 stars 0 forks source link

Interpretability: SHAP #35

Open choshin84 opened 4 years ago

choshin84 commented 4 years ago

Tweet summary

Generalized framework to enable machine learning interpretability, including LIME/DeepLIFT, etc. it works with categorical features. (Catboost has issue as of today, https://github.com/slundberg/shap/issues/761)

Useful link

http://www.ie110704.net/2019/04/26/%E6%A9%9F%E6%A2%B0%E5%AD%A6%E7%BF%92%E3%83%A2%E3%83%87%E3%83%AB%E3%82%92%E8%A7%A3%E9%87%88%E3%81%99%E3%82%8B%E6%8C%87%E6%A8%99shap%E3%81%AB%E3%81%A4%E3%81%84%E3%81%A6/