Gavin Mischler

Could you post a code snippet so we can reproduce your issue? This is about CTClassifier, right? In the CTClassifier code, it does make use of the unlabeled_pool_size input, but...

It's a little hard to debug without your actual data, but a couple things: - Input data to ct.fit() should be a list of length 2 where each item is...

We could also just change it to indicate that it is for the "dev" version, since the docs update before we push new releases

In a local conda env with python 3.8, I ran this test 100 times and it never failed, so I'm not really sure what the issue is now...

If you look at the build artifact, the functionality is basically there, but the current default version is listed as v:pull/287, which I think should change to main when it's...

I was trying to follow the example from this repo and associated docs: https://github.com/maltfield/rtd-github-pages https://maltfield.github.io/rtd-github-pages/en/dev/# Some other repos used that as a template and seemed to work. For example, here's...

Can you update to graspologic within conda-forge? Or maybe just create a new feedstock? Currently causing an [issue](https://github.com/mvlearn/mvlearn/issues/294) with using mvlearn from conda-forge since only an old version of graspy...

It should be this paper, but yeah it looks like that needs to be added more clearly: ``` Choi, Yunjin, Jonathan Taylor, and Robert Tibshirani. "Selecting the number of principal...

Can you give the details of your environment? I just tried running in a fresh environment with python 3.9 and mvlearn 0.5.0 installed from conda-forge and I was able to...

Right, the estimator1 can be accessed as ``ctc.estimator1_``, but that is the same estimator object that the class was initialized with so you should be able to tune the hyper...