Clemens Weiss

While looking into covering this use-case with tests, I discovered that there are ChangePoint-related tests implemented both in [tests/gpflow/kernels/test_kernels.py](../blob/develop/tests/gpflow/kernels/test_kernels.py#L481) as well as a single one in [tests/gpflow/kernels/test_changepoints.py](../blob/develop/tests/gpflow/kernels/test_changepoints.py). Is there any...

> I hope you'd still be interested to finish off this PR!? Yes, absolutely! Sorry, it took me a moment to get back to it. I've added a few commits...

[Just tagging this SO question here to remind me to update my response upon merge: [https://stackoverflow.com/questions/68209521](https://stackoverflow.com/questions/68209521)]

Hi @st--, I just thought I'd bump this to see if there's still interest in merging this? I'm happy to fix anything that needs fixing!

@nanounanue did you find a solution for this? I am experiencing very similar behavior. Weirdly, `anaconda-mode` seems to be working initially when I start up emacs, but stops working soon...

Unfortunately this problem is persisting for me, and I haven't been able to figure out what is causing it. Are there any ideas on how to debug this? Also, could...

Thanks for the discussion! I just wanted to say that putting the values into `Individual.z` works fine for my use case.

I fixed this behavior by including the following in my `systemd` unit file: ``` ExecStart=/usr/bin/emacs --fg-daemon=base ExecStop=/usr/bin/emacsclient --eval "(let (kill-emacs-hook)(kill-emacs))" -s base ``` This will set `kill-emacs-hook` to `nil` before...

hmm... so the `Q`, `Y` and `G` matrices go into the linear regression [here](https://github.com/pystatgen/sgkit/blob/main/sgkit/stats/association.py#L236), and it looks to me as though the only one not "dimension-safe" is the `G` matrix...

alright, that all makes sense! thanks for the replies! And yeah, I think including dimension order checks in the dataset validation would be great! @eric-czech no, no particular reason to...