search

predict-idlab / powershap

A power-full Shapley feature selection method.
Other
200 stars 19 forks source link

The cv argument in `fit` is ignored #9

Closed jvdd closed 2 years ago

jvdd commented 2 years ago

I would like to perform group based train-test split (to avoid data leakage in the powershap feature selection).

To do so I would;

  1. remove the cv argument in fit
  2. add an optional groups argument to fit and use GroupShuffleSplit in the powershap explain method
jvdd commented 2 years ago

11 solves this