Tom Augspurger

Right I think I'm stalled on deserializing the TensorFlow graph in a new process https://gist.github.com/33efb49efe611701ef122f577d0e0430

Probably putting this on the backburner for now, if others want to take a look.

I'm curious: why are you using `Incremental` and `IncrementalPCA` together? I think that `decomposition.IncrementalPCA` expects a Dask Array. But `Incremental` feeds through chunks of Dask Arrays to the underlying estimator.

Thanks @VibhuJawa. When looking at the traceback in #911, I see that skearn's `check_array` takes an `ensure_min_samples` parameter. If we pass `ensure_min_samples=False` there, does stuff go through properly?

Thanks for continuing to work on this. > I experienced very poor running time performances with small chunks=(100, 2) when building dask.array Depending on the scheduler there's a roughly 10-200...

It'll be a week or so before I can take a look. Thanks for your patience! In the meantime, perhaps @jameslamb has a chance to glance through this (no worries...

Probably not. All development happens on GitHub. On Tue, Aug 25, 2020 at 3:04 PM Unex wrote: > Any updates here ? > > — > You are receiving this...

I don't believe anyone is working on it at the moment, though @stsievert might have a better idea. On Tue, Aug 25, 2020 at 3:14 PM Unex wrote: > Sorry,...

Still thinking through this... I don't particularly like the though of `.astype`ing without the user asking us to. I see that's what scikit-learn does, but that's likely due to their...

Thanks. I think the main issue here is likely around inferring whether a problem is binary or multi-class. I'd prefer to avoid inference at `fit` time. Users would be explicit...