Shap

<!-- Release notes generated using configuration in .github/release.yml at master -->

Fixes
* Fix regression in summary violin plot by CloseChoice in https://github.com/shap/shap/pull/4033
* Fix incorrect SHAP Values for Missing Data in new scikit versions for Tree Models by sunruslan in https://github.com/shap/shap/pull/3998
* Fix issue with tight tolerances when calling check_additivity by adamwitmer in https://github.com/shap/shap/pull/3993
* Fix AttributeError when extracting colors by fabianliebig in https://github.com/shap/shap/pull/4017
* Fix additivity check failure uint32 overflow by arhall0 in https://github.com/shap/shap/pull/4006

New Contributors
* adamwitmer made their first contribution in https://github.com/shap/shap/pull/3993
* fabianliebig made their first contribution in https://github.com/shap/shap/pull/4017
* sunruslan made their first contribution in https://github.com/shap/shap/pull/3998
* arhall0 made their first contribution in https://github.com/shap/shap/pull/4006

**Full Changelog**: https://github.com/shap/shap/compare/v0.47.0...v0.47.1

<!-- Release notes generated using configuration in .github/release.yml at master -->

What's Changed
Breaking changes
* Add deprecation warning to legacy bar plot, add migration guide to new Explainer API by connortann in https://github.com/shap/shap/pull/3739
Added
* Added categorical support for shap.plots.scatter by hypostulate in https://github.com/shap/shap/pull/3706
* Introduce vmax parameter in image plot by sd3ntato in https://github.com/shap/shap/pull/2848
* New plotting API for beeswarm to accept and return axes by chriscave in https://github.com/shap/shap/pull/3561
* Enabeling to create a beeswarm figure without sum of other features by kalkairis in https://github.com/shap/shap/pull/2225
* New interface to customise visualisations by connortann in https://github.com/shap/shap/pull/3788
* Allow custom styles for bar plot by connortann in https://github.com/shap/shap/pull/3849
* TreeExplainer numerical sensitivity by tylerjereddy in https://github.com/shap/shap/pull/3990
* Faster non-tree KernelExplainer by tylerjereddy in https://github.com/shap/shap/pull/3944
Fixed
* Fix logit errors in KernelExplainer by CloseChoice in https://github.com/shap/shap/pull/3917
* Fix TypeError in summary_plot by bedapisl in https://github.com/shap/shap/pull/3738
* Re-vendor colorconv from skimage 0.24.0 by connortann in https://github.com/shap/shap/pull/3785
* Fix label option for multiple rows in shap.plots.image by SFatemehM in https://github.com/shap/shap/pull/3636
* Fix transformers by costrau in https://github.com/shap/shap/pull/3578
* Fix OpChain repr for kwargs-only operations by thatlittleboy in https://github.com/shap/shap/pull/3838
* Fix the wrong figure for multiclass in summary plot by 46319943 in https://github.com/shap/shap/pull/3836
* Fix summary plot issue for multiclass case by CloseChoice in https://github.com/shap/shap/pull/3925
* Fix colormaps by CloseChoice in https://github.com/shap/shap/pull/3909
Documentation
* Fixed error in documentation of shap.datasets.communitiesandcrime by TommyGiak in https://github.com/shap/shap/pull/3846
* Fix column indices in Understanding Tree SHAP notebook by operte in https://github.com/shap/shap/pull/3749
* Reformat the scatter notebook in API example by Xovee in https://github.com/shap/shap/pull/3752
* Improved typing and docs for scatter plot by connortann in https://github.com/shap/shap/pull/3811
* Use intersphinx for some external links by thatlittleboy in https://github.com/shap/shap/pull/3851
* Pin docs dependencies for reproducibility by connortann in https://github.com/shap/shap/pull/3885
* Fix typo in force plot with LightGBM and description by davidefiocco in https://github.com/shap/shap/pull/3962
* Fix: fixed markdown issue with some sections title in the introductio… by CSantos01 in https://github.com/shap/shap/pull/3957
* Fix comment for beeswarm plot in intro notebook by davidefiocco in https://github.com/shap/shap/pull/3960
Maintenance
* Fix: explicitly set matplotlib interpolation rcParams in tests by connortann in https://github.com/shap/shap/pull/3953
Other Changes
* Skip sentiment analysis test on MacOS runners by connortann in https://github.com/shap/shap/pull/3955
* Remove deprecated unused code `_build_delta_masked_inputs` and `Explainer._compute_main_effects` by connortann in https://github.com/shap/shap/pull/3856
* Improve handling of the `approximate` parameter to TreeExplainer for consistency, and deprecate the argument in the explainer's init method by CloseChoice in https://github.com/shap/shap/pull/3834
* Refactor feature_perturbation in Tree explainers by glemaitre in https://github.com/shap/shap/pull/2624
* Test decision plot by CloseChoice in https://github.com/shap/shap/pull/3720
* Bump ruff, fix rule E721 by connortann in https://github.com/shap/shap/pull/3751
* Refactor plot utils and colors by thatlittleboy in https://github.com/shap/shap/pull/3833
* Refactor and optimize explanation ops by thatlittleboy in https://github.com/shap/shap/pull/3850
* Fix CI feedstock build by CloseChoice in https://github.com/shap/shap/pull/3862
* Add error to multi output cohort call by CloseChoice in https://github.com/shap/shap/pull/3870
* Fix typo in beeswarm.ipynb by kamurani in https://github.com/shap/shap/pull/3900
* DeepExplainer docstring improvements by anitagraser in https://github.com/shap/shap/pull/3892
* Clear plot before generating new summary plots to avoid overlapping color bars by chun61205 in https://github.com/shap/shap/pull/3921
* Support rng for summary_plot by tylerjereddy in https://github.com/shap/shap/pull/3945
* Minor speedups in non-tree KernelExplainer by tylerjereddy in https://github.com/shap/shap/pull/3983

New Contributors
* bedapisl made their first contribution in https://github.com/shap/shap/pull/3738
* operte made their first contribution in https://github.com/shap/shap/pull/3749
* Xovee made their first contribution in https://github.com/shap/shap/pull/3752
* hypostulate made their first contribution in https://github.com/shap/shap/pull/3706
* SFatemehM made their first contribution in https://github.com/shap/shap/pull/3636
* sd3ntato made their first contribution in https://github.com/shap/shap/pull/2848
* chriscave made their first contribution in https://github.com/shap/shap/pull/3561
* kalkairis made their first contribution in https://github.com/shap/shap/pull/2225
* TommyGiak made their first contribution in https://github.com/shap/shap/pull/3846
* 46319943 made their first contribution in https://github.com/shap/shap/pull/3836
* kamurani made their first contribution in https://github.com/shap/shap/pull/3900
* anitagraser made their first contribution in https://github.com/shap/shap/pull/3892
* chun61205 made their first contribution in https://github.com/shap/shap/pull/3921
* davidefiocco made their first contribution in https://github.com/shap/shap/pull/3962
* CSantos01 made their first contribution in https://github.com/shap/shap/pull/3957
* Fredheda made their first contribution in https://github.com/shap/shap/pull/3984
* tylerjereddy made their first contribution in https://github.com/shap/shap/pull/3945

**Full Changelog**: https://github.com/shap/shap/compare/v0.46.0...v0.47.0

What's Changed
This release adds compatibility with recent version of numpy and tensorflow, and includes several bug fixes.

Added
* Added support for numpy 2, by connortann in https://github.com/shap/shap/pull/3717 and paulbkoch in https://github.com/shap/shap/pull/3704
* Added support for keras 3 and tensorflow 2.16 by CloseChoice in https://github.com/shap/shap/pull/3677

Changed
* Removed the deprecated `auto_size_plot` parameter to `shap.summary_plot()`.

Fixed
* Fixed issue explaining models trained with `float16` mixed precision by CloseChoice in https://github.com/shap/shap/pull/3652
* Fixed deserialization bug with `XGBRegressor` models by CloseChoice in https://github.com/shap/shap/pull/3669

Plus several further documentation and code quality improvements.

New Contributors
* LetiP made their first contribution in https://github.com/shap/shap/pull/3685
* paulbkoch made their first contribution in https://github.com/shap/shap/pull/3704

**Full Changelog**: https://github.com/shap/shap/compare/v0.45.1...v0.46.0

This is a patch release with a couple of bug fixes. In particular, fixes a bug relating to loading of XGBoost models with exponential losses.

What's Changed
Added
* Added selu activation for pytorch deep explainer by CloseChoice in https://github.com/shap/shap/pull/3617
* Added "ax" option to heatmap plotting function by sroener in https://github.com/shap/shap/pull/3571
Changed
* Removed unused "display" parameters from dataset functions by LakshmanKishore in https://github.com/shap/shap/pull/3543
Fixed
* Fixed loading of XGBoost models with expeonential lossesby CloseChoice in https://github.com/shap/shap/pull/3616
* Fixed call interface for the deep explainer by CloseChoice in https://github.com/shap/shap/pull/3558
* Fixed use of Falcon language model for text generation by CloseChoice in https://github.com/shap/shap/pull/3592
* Fixed lightgbm compilation (macOS Workflow) by bewygs in https://github.com/shap/shap/pull/3632
* Fixed loading of XGBoost models with exponential losses by CloseChoice in https://github.com/shap/shap/pull/3616

Plus several documentation and maintenance updates by bewygs , CloseChoice , Hugh-OBrien

New Contributors
* sroener made their first contribution in https://github.com/shap/shap/pull/3571
* Hugh-OBrien made their first contribution in https://github.com/shap/shap/pull/3604
* bewygs made their first contribution in https://github.com/shap/shap/pull/3632

**Full Changelog**: https://github.com/shap/shap/compare/v0.45.0...v0.45.1

This is a fairly significant release containing a number of breaking changes.

Thank you to a number of new contributors for their contributions to this release! We are eager to grow the pool of maintainers, so please do get in touch on 3559 if you are interested in being part of the team.

What's Changed

Breaking changes
* Dropped support for 3.8 in https://github.com/shap/shap/pull/3414
* Changed type and shape of returned SHAP values in some cases, to be consistent with model outputs. SHAP values for models with multiple outputs are now np.ndarray rather than list, by CloseChoice in https://github.com/shap/shap/pull/3318
* Removed deprecated `feature_dependence` parameters in TreeExplainer and LinearExplainer by thatlittleboy in https://github.com/shap/shap/pull/3340
* Removed deprecated alias for Coefficient by connortann in https://github.com/shap/shap/pull/3511

Added
* Added support for python 3.12 by connortann in https://github.com/shap/shap/pull/3414
* Added support for GPU build on recent CUDA versions by trivialfis in https://github.com/shap/shap/pull/3462
* 2x import time speedup via lazy importing of pytorch by connortann in https://github.com/shap/shap/pull/3533
* Added support returning the matplotlib figure in bar plots by richarddli in https://github.com/shap/shap/pull/3494
* Added selu activation for tensorflow deep explainer by CloseChoice in https://github.com/shap/shap/pull/3504
* Added support for special characters in catboost models by CloseChoice in https://github.com/shap/shap/pull/3506
* Added ability to control marker size in `beeswarm` plots by MonoHue in https://github.com/shap/shap/pull/3530

Fixed
* Fixed XGBoost model load by trivialfis in https://github.com/shap/shap/pull/3462
* Fixed text masking with certain tokenizers by costrau in https://github.com/shap/shap/pull/3536
* Fixed issue with KernelExplainer when explaining tensorflow models by connortann in https://github.com/shap/shap/pull/3542
* Fixed force_plot contribution threshold for negative contributions by connortann in https://github.com/shap/shap/pull/3547
* Removed overwrite of default warning filter or formatter by connortann in https://github.com/shap/shap/pull/3514

.. plus a large number of documentation, testing and other maintenance updates by CloseChoice , yuanx749 , LakshmanKishore and others.

New Contributors

* richarddli made their first contribution in https://github.com/shap/shap/pull/3494
* yuanx749 made their first contribution in https://github.com/shap/shap/pull/3458
* LakshmanKishore made their first contribution in https://github.com/shap/shap/pull/3393
* trivialfis made their first contribution in https://github.com/shap/shap/pull/3462
* DanGolding made their first contribution in https://github.com/shap/shap/pull/3526
* MonoHue made their first contribution in https://github.com/shap/shap/pull/3530
* costrau made their first contribution in https://github.com/shap/shap/pull/3536

**Full Changelog**: https://github.com/shap/shap/compare/v0.44.1...v0.45.0

<!-- Release notes generated using configuration in .github/release.yml at master -->

Patch release to fix an issue with the display of force plots.

Fixed
* Fixed HTML issue affecting display of force plots by CloseChoice in https://github.com/shap/shap/pull/3464
* Fixed calculation of interactions values for catboost regressors by CloseChoice in https://github.com/shap/shap/pull/3459
* Update XGBoost parsing to use ubjson format, replacing deprecated binary format by CloseChoice in https://github.com/shap/shap/pull/3345
Other
* Further improvements to documentation

**Full Changelog**: https://github.com/shap/shap/compare/v0.44.0...v0.44.1