./math/py-pymc3, Bayesian modeling and probabilistic machine learning

[ CVSweb ] [ Homepage ] [ RSS ] [ Required by ] [ Add to tracker ]

Branch: CURRENT, Version: 3.11.6, Package name: py312-pymc3-3.11.6, Maintainer: minskim

PyMC3 is a Python package for Bayesian statistical modeling and
Probabilistic Machine Learning focusing on advanced Markov chain Monte
Carlo (MCMC) and variational inference (VI) algorithms. Its
flexibility and extensibility make it applicable to a large suite of
problems.


Required to run:
[graphics/py-matplotlib] [devel/py-setuptools] [math/py-scipy] [math/py-numpy] [math/py-pandas] [devel/py-h5py] [math/py-patsy] [misc/py-tqdm] [lang/python37] [math/py-Theano]

Required to build:
[pkgtools/cwrappers]

Master sites:

Filesize: 785.615 KB

Version history: (Expand)

CVS history: (Expand)


   2024-11-11 08:29:31 by Thomas Klausner | Files touched by this commit (862) 
Log message:
py-*: remove unused tool dependency

py-setuptools includes the py-wheel functionality nowadays
   2024-10-14 08:46:10 by Thomas Klausner | Files touched by this commit (325) 
Log message:
*: clean-up after python38 removal
   2024-08-05 21:36:24 by Adam Ciarcinski | Files touched by this commit (3) | Package updated
Log message:
py-pymc3: updated to 3.11.6

PyMC 3.11.5 (14 March 2022)
Backports
+ The `pm.logp(rv, x)` syntax is now available and recommended to make your \ 
model code `v4`-ready. Note that this backport is just an alias and much less \ 
capable than what's available with `pymc >=4`
+ The `pm.Distribution(testval=...)` kwarg was deprecated and will be replaced \ 
by `pm.Distribution(initval=...)`in `pymc >=4`
+ The `pm.sample(start=...)` kwarg was deprecated and will be replaced by \ 
`pm.sample(initvals=...)`in `pymc >=4`
+ `pm.Lognormal` is now available as an alias for `pm.Lognormal`

Bugfixes
+ The upper limit for the SciPy version is `<1.8.0` and will most probably \ 
remain for all future `3.x.x` releases. For compatibility with newer SciPy \ 
versions please update to `pymc>=4.0.0`.
+ A hotfix is applied on import to remain compatible with NumPy 1.22

PyMC3 3.11.4 (20 August 2021)

New Features
+ Generalized BART, bounded distributions like Binomial and Poisson can now be \ 
used as likelihoods
+ `plot_gp_dist` is now available at the package level: `pm.plot_gp_dist`
+ The experimental JAX sampling was removed. It will be included in the upcoming \ 
`v4` release
+ `pm.intX` no longer downcasts integers unnecessarily

Maintenance
+ A deprecation warning from the `semver` package we use for checking backend \ 
compatibility was dealt with
+ `theano.printing.pydotprint` is now hotfixed upon import
+ Fix bug in the computation of the log pseudolikelihood values (SMC-ABC).
+ Fix `LKJCorr.random` method to work with `pm.sample_prior_predictive`.
+ Enable documentation generation via ReadTheDocs for upcoming v3 releases.
+ Remove `float128` dtype support
+ Use `to_tuple` function in `pm.fast_sample_posterior_predictive` to pass shape \ 
assertions
   2023-08-02 01:20:57 by Thomas Klausner | Files touched by this commit (158) 
Log message:
*: remove more references to Python 3.7
   2023-07-01 10:37:47 by Thomas Klausner | Files touched by this commit (105) | Package updated
Log message:
*: restrict py-numpy users to 3.9+ in preparation for update
   2022-04-10 02:57:15 by David H. Gutteridge | Files touched by this commit (18) 
Log message:
Fix build breakage from py-scipy now being Python >= 3.8
   2022-01-04 21:55:40 by Thomas Klausner | Files touched by this commit (1595) 
Log message:
*: bump PKGREVISION for egg.mk users

They now have a tool dependency on py-setuptools instead of a DEPENDS
   2021-12-30 14:05:42 by Adam Ciarcinski | Files touched by this commit (125) 
Log message:
Forget about Python 3.6