Want to learn how to use pipelines effectively? I've got 9 more pipeline tips in my free ML course, "50 scikit-learn tips": courses.dataschool.io/scikit-learn-tips
Is it possible to apply StratifiedKFold on the data, then apply cross_val_score while for each validation only balancing (over/under sampling) the current train folds while leaving the test fold data as it is?
Want to learn how to use pipelines effectively? I've got 9 more pipeline tips in my free ML course, "50 scikit-learn tips": courses.dataschool.io/scikit-learn-tips
Is it possible to apply StratifiedKFold on the data, then apply cross_val_score while for each validation only balancing (over/under sampling) the current train folds while leaving the test fold data as it is?
Super👌
Thank you!