Nitin Madnani

Results 127 comments of Nitin Madnani

Even though this is an experimental implementation for now, it's still fine to have this done in a branch that we can just merge later when the implementation is stable....

I think we have enough to do in v2.5 so I am going to move this out for a later release.

Just FYI: scikit-learn will have [StackingClassifier](https://scikit-learn.org/dev/modules/generated/sklearn.ensemble.StackingClassifier.html#sklearn.ensemble.StackingClassifier) and [StackingRegressor](https://scikit-learn.org/dev/modules/generated/sklearn.ensemble.StackingRegressor.html#sklearn.ensemble.StackingRegressor) available starting with 0.22. So, our work should now be much simpler. Basically we need to figure out how to pass in...

At the very least, we should point the user to the documentation for the various solvers so that they can make their own decisions and implement either via `fixed_parameters` or...

Yeah it would be nice to do some sort of standardization that can be automated. I am not sure I like black but it's one option :-p

We can go with black :)