Skip to content

Commit

Permalink
Release 2.3.2 (#402)
Browse files Browse the repository at this point in the history
Release PR for 2.3.2

* changelog
* version bump
* removed mentions of specific maintainers from pyproject
  • Loading branch information
fkiraly authored Jun 23, 2024
1 parent ab7b21f commit fbe193c
Show file tree
Hide file tree
Showing 5 changed files with 98 additions and 6 deletions.
2 changes: 1 addition & 1 deletion README.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
<a href="https://skpro.readthedocs.io/en/latest"><img src="https://github.com/sktime/skpro/blob/main/docs/source/images/skpro-banner.png" width="500" align="right" /></a>

:rocket: **Version 2.3.1 out now!** [Read the release notes here.](https://skpro.readthedocs.io/en/latest/changelog.html).
:rocket: **Version 2.3.2 out now!** [Read the release notes here.](https://skpro.readthedocs.io/en/latest/changelog.html).

`skpro` is a library for supervised probabilistic prediction in python.
It provides `scikit-learn`-like, `scikit-base` compatible interfaces to:
Expand Down
7 changes: 6 additions & 1 deletion docs/source/_static/switcher.json
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,12 @@
"url": "https://skpro.readthedocs.io/en/latest/"
},
{
"name": "2.3.1 (stable)",
"name": "2.3.2 (stable)",
"version": "stable",
"url": "https://skpro.readthedocs.io/en/v2.3.2/"
},
{
"name": "2.3.1",
"version": "stable",
"url": "https://skpro.readthedocs.io/en/v2.3.1/"
},
Expand Down
89 changes: 89 additions & 0 deletions docs/source/changelog.rst
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,92 @@ You can also subscribe to ``skpro``'s
For planned changes and upcoming releases, see roadmap in the
`issue tracker <https://github.com/sktime/skpro/issues>`_.


[2.3.2] - 2024-06-22
====================

Highlights
----------

* ``GLM`` now supports multiple ``distributions`` and ``link`` function
(:pr:`384`) :user:`ShreeshaM07`
* new metrics: interval width, area under calibration curve (:pr:`391`) :user:`fkiraly`
* histogram distribution (:pr:`382`) :user:`ShreeshaM07`
* new distributions with non-negative support:
Half Normal, Half Cauchy, Half Logistic, Log Laplace, Pareto
(:pr:`363`, :pr:`371`, :pr:`373`, :pr:`374`, :pr:`396`)
:user:`SaiRevanth25`, :user:`sukjingitsit`
* mean-scale family of distributions, composable with any real distribution
(:pr:`282`) :user:`fkiraly`

Enhancements
~~~~~~~~~~~~

Probability distributions
~~~~~~~~~~~~~~~~~~~~~~~~~

* [ENH] mean-scale family of distributions, composite (:pr:`282`) :user:`fkiraly`
* [ENH] Half Normal Distribution (:pr:`363`) :user:`SaiRevanth25`
* [ENH] Half Cauchy Distribution (:pr:`371`) :user:`SaiRevanth25`
* [ENH] Half Logistic Distribution (:pr:`373`) :user:`SaiRevanth25`
* [ENH] Log Laplace Distribution (:pr:`374`) :user:`SaiRevanth25`
* [ENH] Histogram distribution (:pr:`382`) :user:`ShreeshaM07`
* [ENH] Pareto distribution (:pr:`396`) :user:`sukjingitsit`

Probabilistic regression
~~~~~~~~~~~~~~~~~~~~~~~~

* [ENH] ``GLM`` with multiple ``distributions`` and ``link`` function support (:pr:`384`) :user:`ShreeshaM07`
* [ENH] interval width and area under calibration curve metrics (:pr:`391`) :user:`fkiraly`

Test framework
~~~~~~~~~~~~~~

* [ENH] Tests for polars support for estimators (:pr:`370`) :user:`julian-fong`

Fixes
~~~~~

Probability distributions
~~~~~~~~~~~~~~~~~~~~~~~~~

* [BUG] fix ``test_methods_p`` logic when ``shuffle`` is ``True`` (:pr:`381`) :user:`ShreeshaM07`
* [BUG] ensure ``index`` and ``columns`` are taken into account in broadcasting if ``bc_params`` are set (:pr:`403`) :user:`fkiraly`

Probabilistic regression
~~~~~~~~~~~~~~~~~~~~~~~~

* [BUG] bugfix when ``None`` was specified for ``max_iter`` parameter in sklearn regressors (:pr:`386`) :user:`julian-fong`

Survival and time-to-event prediction
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

* [BUG] bugfix on #387 - changed paramset 3 to use ``ConditionUncensored`` instead of ``CoxPH`` (:pr:`388`) :user:`julian-fong`

Maintenance
~~~~~~~~~~~

* [MNT] Deprecation message for ``CyclicBoosting`` changes (:pr:`320`) :user:`setoguchi-naoki`
* [MNT] make ``BaseArrayDistribution`` private (:pr:`401`) :user:`fkiraly`

Documentation
~~~~~~~~~~~~~

* [DOC] fix typo in survival models API reference (:pr:`368`) :user:`fkiraly`
* [DOC] add ``scipy`` reference to interfaced distributions (:pr:`379`) :user:`fkiraly`
* [DOC] in API reference, order distributions by support (:pr:`400`) :user:`fkiraly`

Contributors
~~~~~~~~~~~~

:user:`fkiraly`,
:user:`julian-fong`,
:user:`SaiRevanth25`,
:user:`setoguchi-naoki`,
:user:`ShreeshaM07`,
:user:`sukjingitsit`


[2.3.1] - 2024-05-26
====================

Expand Down Expand Up @@ -89,6 +175,9 @@ Contributors
[2.3.0] - 2024-05-16
====================

Highlights
----------

* new tutorial notebooks for survival prediction and probability distributions (:pr:`303`, :pr:`305`) :user:`fkiraly`
* interface to ``ngboost`` probabilistic regressor and survival predictor (:pr:`215`, :pr:`301`, :pr:`309`, :pr:`332`) :user:`ShreeshaM07`
* interface to Poisson regressor from ``sklearn`` (:pr:`213`) :user:`nilesh05apr`
Expand Down
4 changes: 1 addition & 3 deletions pyproject.toml
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
[project]
name = "skpro"
version = "2.3.1"
version = "2.3.2"
description = "A unified framework for probability distributions and probabilistic supervised regression"
authors = [
{name = "skpro developers", email = "[email protected]"},
Expand All @@ -10,8 +10,6 @@ authors = [
]
maintainers = [
{name = "skpro developers", email = "[email protected]"},
{name = "Franz Király"},
{name = "Frithjof Gressmann"},
]
readme = "README.md"
keywords = [
Expand Down
2 changes: 1 addition & 1 deletion skpro/__init__.py
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
"""skpro."""

__version__ = "2.3.1"
__version__ = "2.3.2"

__all__ = ["show_versions"]

Expand Down

0 comments on commit fbe193c

Please sign in to comment.