Soledad Galli

Hi @Morgan-Sell Thanks for the PR. I am thinking out loud below: This function would be used by: - MeanEncoder - OrdinalEncoder - PRatioEncoder - WoE For categorical targets: -...

More on this: we can use the type_of_target function from sklearn to check if the target is binary as we did here: https://github.com/feature-engine/feature_engine/blob/65fedf100bc85f364b26838866a264dbf7320841/feature_engine/discretisation/decision_tree.py#L166 We could add a parameter to this...

Hi @Morgan-Sell It's me again :p I did some performance comparison, and `type_of_target` is slower than `y.unique()`. We have the `unique()` implementation is WoE, so we should stick with that...

> Actually, PRatio will be deprecated, so the only transformer atm using binary classifcation exclusively is WoE. Not worth the effort.

Hi @datacubeR Thank you for raising the issue. Apologies for the delay. I was on holidays until yesterday. To check if I understand this correctly, the first pipeline should return...

Yes. The PolynomialFeatures from sklearn is designed to just return the polynomial features. It operates over the entire dataset. As such, the result will have the original features, which are...

Sounds good @Morgan-Sell Shouldn't be too difficult (she said, :p) Thank you!

Hi @datacubeR Thanks for the suggestion. You are certainly not the first one who'd like the encoders to support NaN. I think @david-cortes made a similar suggestion here #481, am...

Will pick up this on the week of Sept 7. At the moment I am without my computer. Thanks!

I've just read in the article, that they add the features discretised as additional features to the dataset instead of replacing the existing ones. So we can expand the decision...