Dynesty

Added
- Warning is emitted if bootstrap expansion factor is too large ( segasai )
- Warning is emitted if maxcall/maxiter stop the iterations too early ( segasai )
Changed
- The clustering/K-means for ellipsoid decomposition is now done in scaled space of points divided by stddev along each dimension ( segasai)
- Update the initialisation of points in the case where some fraction of prior volume has log(L)=-inf this should increase the accuracy of log(Z) estimates in some cases
Fixed
- Fix a rare possible bug where due to numerical instability in uniform sampling a q==0 error could have occured ( segasai)
- Fix a FileExistsError when using check-points on Windows ( 450, reported by rodleiva, fixed by segasai )

Fixed
- Fix the restoration of the dynamic sampler from the checkpoint with the pool. Previously after restoring the sampler, the pool was not used. (438 ; by segasai)
- Fix the issue with checkpointing from the dynamic sampler. Previously if one batch took shorter than the checkpoint_every seconds then the checkpoints were not created (by segasai)
- Fix the restoration from checkpoint that could have occassiounaly lead to one skipped point from nested run (by segasai)

Changed
- Change the way initialization of live-points happens. Now if after 1000 iterations we managed to get at least a single point, the code will continue sampling after putting a warning. Previously the error was raised. (by segasai )
- Refactor the bound update code which will lead to more consistent boundary updates (428 by segasai )
- If incorrect keys to first_update are provided an exception will be raised
Fixed
- Fix some pathological cases when uniform distribution is sampled with a very low logl.
- Fix a problem when a very small nlive is used leading to the error (424 , reported by frgsimpson)
- Fix the incorrect update_interval calculation leading to too unfrequent updates of bounds when using dynamic sampler (report by ajw278, analysis and fix by segasai)
- If you try to resume a previously finished dynamic run, the warning will be raised and the sampler will exit (previously an error could have occured in this case)

Added
- Dynesty is now able to correctly sample posteriors that have plateaus (i.e. areas of constant likelihood)
Changed
Fixed
- Previously when sampling posteriors that have areas with log(L)=minus infinity the computed evidence values were biased by roughly the fraction of the prior volume that has infinite log(L).

A release with major performance bug fix for the dynamical sampler
Added
Changed
Fixed
- A major performance regression has been discovered that lead to dynamic nested sampling batches becoming slower and slower. The regression was introduced in 1.2 and can easily lead to a factor of several slower performance if a large number of batches is used. (415 ; discovery and fix by segasai)
- Some small fixes related to resuming of runs

Added
Changed
- When checkpointing is on the dynamic sampler will always checkpoint in the end of the run_nested() irrespective of checkpoint_time
- Equally weighted samples are now randomly shuffled ( 408 )
Fixed
- The live_points option was somewhat broken when blob option was introduced requiring a tuple of 4 elements irrespective of whether your likelihood returns blobs or not. Now if you use blob=True and want to provide live_points you need to provide 4 elements (u,v,logl,blobs). If you use blob=False you will need to provide just 3 elements as before (u,v,logl)