Seth Axen

> Only thing which is a bit uneasy is the output type... I am not sure there is a strong guarantee that the first evaluated type would correspond to the...

> It would be worth pointing out that the default should all be fine (I think they all assume Euclidean space). Which default? Whether or not the kernel is PD...

Okay, so the simplest change right now is to simply document in `SEKernel` and the section on `SimpleKernel` the warning that most metrics will in general not produce a PD...

Yes, it's absolutely possible. The simplex transform we use (and Stan as well) is just the classic stick-breaking transform (called the inverse multiplicative log-ratio transform in the compositional data analysis...

@yebai I don't think anything I did fixing the correlation bijectors would have fixed this. I'm not at a computer right now, but I imagine the problem is similar; the...

Nice catch, the relevant line is https://github.com/keiserlab/e3fp/blob/fdf1417107803eb1453181dda56d8e7888affaa1/e3fp/conformer/generator.py#L217. In `e3fp.conformer.generate`, `pool_multiplier` is documented to be an integer, but we don't enforce this. Probably the better approach is to throw an error...

This looks like the same `MultiplePlot ` issue that showed up in #106 .

The graphic was taken from the tidybayes package, I'm not certain how it specifically was generated: http://mjskay.github.io/tidybayes/index.html

I'm happy to provide examples of plots in other packages that I think are useful and the syntax from that package for generating them. Is that what you mean?

Thanks to you both for the explanations and links to previous discussions. These are very helpful. I think the priorities I have are that it would ideally be straightforward for...