Leland McInnes
Leland McInnes
That sounds troubling, but I can't say too much without a little more information. Presumably the whole thing is segfaulting somewhere inside numba's workload. Are you using any different metrics,...
Any chance you could try installing pynndescent and see if that makes any difference?
I'm afraid this may have to suffice as a workaround for now -- I'll try to figure out what the issue might be, but it will likely be hard to...
I'm glad it is working. The crash is very puzzling. I am seeing some crash issues with a new metric I am implementing in pynndescent (it won't be the cause...
Not at present unfortunately. It is possible, but it would need a separate code path to do so, which doesn't exist at this time. Sorry.
If you have specific labels to measure against you could cluster the embedding (with, say, hdbscan) and look at the adjusted Rand score (``adjusted_rand_score`` in ``sklearn.metrics``). of the clustering against...
If there are no labels then there is not "truth", so no, there isn't a general method that works without labels.
The ``n_neighbors`` parameter in UMAP and the ``n_samples`` parameter in DBSCAN/HDBSCAN mean different things. They are, at least, measured in the same units. There is some reason to believe one...
Yes, it looks like they've refactored how all of that works quite a bit. There's no easy way to handle that anymore looking at the current setup. I think the...
This should be fixed in master now. I'll see if I can get a release out soon.