You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
We need to address the following API issues raised by @jnothman:
fit_sample is not a great name, as I have argued elsewhere ;)
The fact that imblearn.pipeline.Pipeline has a method called sample that fits its constituents (using fit_sample) rings loud alarm bells. IMO, the sample method should not exist.
fit_sample needs, eventually, to be able to update things other than X and y (e.g. weights).
The text was updated successfully, but these errors were encountered:
fit_sample is not a great name, as I have argued elsewhere ;)
This is debatable. fit_resample I suppose that could have been better choice. We could change the name of the method and keep an alias for backwards compatibility.
The fact that imblearn.pipeline.Pipeline has a method called sample that fits its constituents (using fit_sample) rings loud alarm bells. IMO, the sample method should not exist.
True. I have thought about that many times.
fit_sample needs, eventually, to be able to update things other than X and y (e.g. weights).
closes#460
This PR implements:
- [x] Removing `sample`.
- [x] Having a single `fit_resample`. In addition, we kept an alias `fit_sample` for backcompatibility.
We need to address the following API issues raised by @jnothman:
fit_sample
is not a great name, as I have argued elsewhere ;)imblearn.pipeline.Pipeline
has a method calledsample
that fits its constituents (usingfit_sample
) rings loud alarm bells. IMO, thesample
method should not exist.fit_sample
needs, eventually, to be able to update things other than X and y (e.g. weights).The text was updated successfully, but these errors were encountered: