The intended usage is to be able to add molecular vectorization directly into scikit-learn pipelines, so that the final model directly predict on RDKit molecules or SMILES strings As example with the ...

Now With Missing Data Support! The py-earth package now supports missingness in its predictors. Just set allow_missing=True when constructing an Earth object. The R package earth was most useful to me ...

Hidden Scikit Learn tools support cleaner workflows and reduce common errors in data preparation. Features like calibration and permutation importance improve trust and clarity in model results.