non-mean target encoding #245
Description
This would naturally cover quantile encoding. Maybe be included in the upcoming analytical version.
I have seen people use a lot of interesting things like min, max, nunique. https://www.kaggle.com/competitions/playground-series-s4e12/discussion/554328
another example: https://www.kaggle.com/code/cdeotte/first-place-single-model-lb-38-81#Feature-Engineer-Columns
this would be easy to do without shrinkage, but I haven't spend enough time thinking about how it would work in that scenario