Skip to content

Releases: pymc-devs/pymc

v5.9.0

04 Oct 10:21
Compare
Choose a tag to compare

What's Changed

Major Changes 🛠

  • Update Gamma Distribution to support new pytensor GammaRV reparameterization by @tvwenger in #6934

Bugfixes 🪲

  • Fix fgraph_from_model with multivariate transformed variables by @ferrine in #6924

Documentation 📖

Maintenance 🔧

New Contributors

Full Changelog: v5.8.2...v5.9.0

v5.8.2

21 Sep 12:47
Compare
Choose a tag to compare

What's Changed

Bugfixes 🪲

  • Fix bug in compute_log_likelihood when variable has dims without coords by @jaharvey8 in #6882

Full Changelog: v5.8.1...v5.8.2

v5.8.1

14 Sep 07:30
Compare
Choose a tag to compare

What's Changed

New Features 🎉

  • Logprob derivation for Min of continuous IID variables by @Dhruvanshu-Joshi in #6846
  • Derive logprob for exp2, log2, log10, log1p, expm1, log1mexp, log1pexp (softplus), and sigmoid transformations by @LukeLB in #6826

Bugfixes 🪲

Documentation 📖

Maintenance 🔧

Full Changelog: v5.8.0...v5.8.1

v5.8.0

04 Sep 09:43
Compare
Choose a tag to compare

What's Changed

New Features 🎉

Bugfixes 🪲

  • Fix logcdf and icdf derivations for non-monotonically increasing transformations by @ricardoV94 in #6850

Documentation 📖

Maintenance 🔧

Full Changelog: v5.7.2...v5.8.0

v5.7.2

09 Aug 08:31
Compare
Choose a tag to compare

What's Changed

Bugfixes 🪲

  • Do not use seeded_test fixture in exported BaseTestDistributionRandom by @ricardoV94 in #6848

Documentation 📖

  • Use ordered_univariate in documentation example of NormalMixture by @mrpg in #6842

New Contributors

Full Changelog: v5.7.1...v5.7.2

v5.7.1

04 Aug 07:14
Compare
Choose a tag to compare

What's Changed

Bugfixes 🪲

Maintenance 🔧

Full Changelog: v5.7.0...v5.7.1

v5.7.0

31 Jul 08:56
Compare
Choose a tag to compare

What's Changed

Major Changes 🛠

  • Drop support for Python 3.8 by @ricardoV94 in #6832
  • Bump PyTensor dependency by @ricardoV94 in #6830
    • PyTensor no longer allows runtime broadcasting. If you want a MutableData tensor to broadcast along an existing dimension, specify its static shape as (1,) along the relevant axis. Example: pm.MutableData("x", np.ones((1, 10)), shape=(1, None)).

New Features 🎉

Bugfixes 🪲

Documentation 📖

  • Don't use size and simplify dims example in dimensionality notebook by @ricardoV94 in #6829

Maintenance 🔧

Full Changelog: v5.6.1...v5.7.0

v5.6.1

14 Jul 07:22
Compare
Choose a tag to compare

What's Changed

Bugfixes 🪲

Documentation 📖

  • Fix mathematical notation in conditional_logprob docstrings by @amyoshino in #6821

Maintenance 🔧

Full Changelog: v5.6.0...v5.6.1

v5.6.0

04 Jul 12:10
Compare
Choose a tag to compare

What's Changed

Major Changes 🛠

  • Rewrite logp graph before taking the gradient by @dehorsley in #6736
  • Support automatic imputation for multivariate and symbolic distributions by @ricardoV94 in #6797

New Features 🎉

  • Probabilty inference for arc transformations by @LukeLB in #6775
  • Add icdf function for Cauchy and Logistic distributions by @amyoshino in #6747
  • Add icdf functions for Lognormal, Half Cauchy and Half Normal distributions by @amyoshino in #6766
  • Add icdf functions for Moyal, Gumbel, Triangular and Weibull distributions by @amyoshino in #6802
  • Allow non-scalar measurable switch mixtures by @ricardoV94 in #6796

Bugfixes 🪲

Documentation 📖

Maintenance 🔧

New Contributors

Full Changelog: v5.5.0...v5.6.0

v5.5.0

09 Jun 14:56
Compare
Choose a tag to compare

What's Changed

Major Changes 🛠

  • Rename basic "joint_logprob" functions to "conditional_logp" by @ricardoV94 in #6760

New Features 🎉

Bugfixes 🪲

Maintenance 🔧

New Contributors

Full Changelog: v5.4.1...v5.5.0