Will Handley
Will Handley
In contrast to #232 and #231, this is a slightly more complicated/controversial PR. The way priors are treated in nested sampling is quite subtle, in particular the way that it...
In the initial stages of nested sampling, when it is drawing samples deep in the tails of the posterior distribution one can occasionally get NaN values for the Cls. When...
In the current version of matplotlib (3.5.2) /ipython (8.4.0) the interactive plotting behaviour has changed. This means that once created, plots do not update (as they are seen to do...
# Description A set of scripts for generating perfect nested sampling runs which will prove useful in developing techniques such as importance sampling #132. Changes: 1. Implemented a spherical gaussian...
At the moment this code does not work correctly ```python samples = Samples(...) samples.plot.kde_1d(subplots=True) ``` This should produce a pandas-style array of kde_1d plots, but at the moment only produces...
At the moment anesthetic is hosted on my personal github. It would be more professional to transfer it to an organisation. I have an unpopulated organisation [handley-lab](https://github.com/orgs/handley-lab) which I plan...
As [pointed out](https://github.com/williamjameshandley/anesthetic/pull/217#discussion_r946868921) by @lukashergt in #217, currently only chain readers are capable of burn-in. This (repeated) code should be moved into MCMCSamples, where it would correctly handle the chain...
The plot gallery needs updating, and the README would benefit from including some figures that show anesthetic in action.
Since the title of #178 is centered around the iso_probability_contours functionality which is being implemented in #188 (it might be good to also have a KDE-based version alongside @Stefan-Heimersheim's kde-less...
In nested sampling, there is a concept called 'logzero' which is important, but neither well-defined, nor consistently implemented. In general, at runtime if a likelihood returns 'logzero' (which in MultiNest...