Dmitry Kobak

Cool! Did you have a chance to compare these embeddings: ``` sc.pp.neighbors() sc.tl.tsne(binarize=True) sc.tl.tsne(binarize=False) sc.pp.neighbors_tsne() sc.tl.tsne(binarize=False) ``` on one of the standard scanpy datasets, like e.g. scanpy.datasets.pbmc3k_processed (used in scanpy...

For some reason I don't see the figures here on the Github page (and get an error message when I click on the link), but they showed fine in the...

The problem is not the collapsible thing. I still don't see the images here but only links instead, and when I click on a link e.g. https://user-images.githubusercontent.com/5758119/115158730-f0768a00-a08f-11eb-939a-1b9c35373fae.png I get an...

Right. Thanks. You can get it here: https://raw.githubusercontent.com/berenslab/mini-atlas/master/data/raw/allen/tasic2018/sample_heatmap_plot_data.csv

> There are two more to do with 'reflective list' being deprecated, but those can't be easily fixed until the replacement appears in Numba 0.45. @tomwhite I haven't seen those...

@pavlin-policar Based on the discussion above, this is not a bug. Rather, it's a feature request to add Pandas support to openTSNE. I guess this could be done along the...

I agree -- I am fine with closing this issue.

Getting back to this issue: I assume NSO never replied. Anyway - is there any reason not to scale 2015 monthly values to make them add up to the 2015...

Related to this, I am wondering if your implementation uses the factor of 4 in the gradient? See Eq. 5 in https://github.com/fcdimitr/sgtsnepi#approximation-of-the-gradient. Many implementations, following the original van der Maaten's...

Also, why is whiten=TRUE the default value? This is IMHO super confusing, all other tsne libraries usually do not whiten by default, see e.g. Rtsne. When the data have some...