CatBoost Target Encoding

この記事の翻訳、内容のまとめ

https://catboost.ai/docs/concepts/algorithm-main-stages_cat-to-numberic.html

CatBoostは内部でTargetEncodingしているらしい？がどうやっているのか

ほげ

Before each split is selected in the tree (see Choosing the tree structure), categorical features are transformed to numerical. This is done using various statistics on combinations of categorical features and combinations of categorical and numerical features.

カテゴリ×カテゴリ、カテゴリ×数値それぞれの組み合わせを新しい特徴量として生成する？

various statisticsってなんだよ

Reference

catboost

https://catboost.ai/docs/concepts/algorithm-main-stages_cat-to-numberic.html

https://catboost.ai/docs/concepts/python-reference_catboost_fit.html

https://catboost.ai/docs/concepts/algorithm-main-stages_choose-tree-structure.html#algorithm-main-stages_choose-tree-structure

category_encoders

https://contrib.scikit-learn.org/categorical-encoding/catboost.html

https://contrib.scikit-learn.org/categorical-encoding/_modules/category_encoders/cat_boost.html#CatBoostEncoder.fit

blog

https://copypaste-ds.hatenablog.com/entry/2019/09/05/184947