Add novel-value handing method to step_woe

[kylegilde]

Hi

I noticed that all the glm based steps have a method for handling novel values: "For novel levels, a slightly timmed average of the coefficients is returned."

Would it make sense to add the same handling method to step_woe?

[topepo]

They are very different models. We can do that in the likelihood encoding and embedding steps because of their probabilistic models. WoE doesn't have the same properties.

[kylegilde]

Hi Max,

I really want to use WoE transformation in my project, but I need it to be able to handle novel values or else my script will fail.

What if the user could specify novel values to be set to 0 like this other WoE encoder does?

http://contrib.scikit-learn.org/category_encoders/woe.html

Is there another way to handle novel values in a WoE transformation that I am overlooking?

Thanks

[topepo]

You can use step_novel() beforehand.

[github-actions]

This issue has been automatically locked. If you believe you have found a related problem, please file a new issue (with a reprex: https://reprex.tidyverse.org) and link to this issue.