Johannes Buchner

OK, but for that case, `min(maxvalue - 1, int(counts * maxvalue * 1. / c))` should be changed to `int(min(maxvalue - 1, counts * maxvalue * 1. / c))`

I suppose you can divide by c first, and then multiply by maxvalue, to avoid the overflow.

use `apt search` to find packages. In current python 3 they are probably starting with e.g. python3-scipy. It would be good to update the instructions, can you suggest changes once...

don't put a space after the comma.

ultranest can resume with changed settings, including with different parameter names or number of live points. As long as the transform and likelihood function behave the same, it can resume....

I think we need to 1. add to [HDF5PointStore](https://github.com/JohannesBuchner/UltraNest/blob/master/ultranest/store.py#L161) that it accepts some headers to be set, then write that to the HDF5 file after opening it. 2. should pass...

also you may be interested in https://github.com/JohannesBuchner/UltraNest/issues/160

I meant that that function may not be very common to be used or needed by users? In general, I always thought some more tutorials on various applications of UltraNest...

Most of the plots you mention require nested sampling weights, which are only computable through nested sampling once the run is finished. What you can do, however, is take the...

That is very strange! Is this in a python script or a notebook? Can you rerun it from scratch?