Exploratory analysis of Bayesian models
http://github.com/arviz-devs/arviz
ArviZ is a Python package for exploratory analysis of Bayesian models. Includes
functions for posterior analysis, data storage, model checking, comparison and
diagnostics.
- Developed at devel:languages:python:numeric
-
2
derived packages
- Download package
-
Checkout Package
osc -A https://api.opensuse.org checkout openSUSE:Factory/python-arviz && cd $_ - Create Badge
Refresh
Refresh
Source Files
| Filename | Size | Changed |
|---|---|---|
| arviz-0.17.0.tar.gz | 0009271807 8.84 MB | |
| python-arviz.changes | 0000007995 7.81 KB | |
| python-arviz.spec | 0000003225 3.15 KB |
Revision 7 (latest revision is 11)
Ana Guerrero (anag+factory)
accepted
request 1140110
from
Dirk Mueller (dirkmueller)
(revision 7)
- update to 0.17.0:
* Add prior sensitivity diagnostic `psens`
* Add filter_vars functionality to
`InfereceData.to_dataframe`method
* Update requirements: matplotlib>=3.5, pandas>=1.4.0,
numpy>=1.22.0
* Fix behaviour of `plot_ppc` when dimension order isn't
`chain, draw, ...`
* Avoid repeating the variable name in `plot_ppc`,
`plot_bpv`, `plot_loo_pit`... when repeated.
* Add support for the latest CmdStanPy.
* Fix import error on windows due to missing encoding
argument
* Add ``__delitem__`` method to InferenceData
* Improve the docstring of `psislw`
* Rerun the quickstart and working with InferenceData notebooks
* Several fixes in `plot_ppc` docstring
- No longer skip Python 3.8 and 3.11.
Comments 0