Releases | Open Source Science

What's Changed

Added

Add CoalitionExplainer and add possibility of using Winter Values in Partition Explainer by @CousinThrockmorton in https://github.com/shap/shap/pull/3666
Support and test against Python 3.13 by @connortann in https://github.com/shap/shap/pull/3861 and @CloseChoice in https://github.com/shap/shap/pull/4104
Add Support for PyTorch Identity Layer by @RoyiAvital in https://github.com/shap/shap/pull/4028 ### Documentation
Update Explaining a model that uses standardized features by @randombenj in https://github.com/shap/shap/pull/3903

Other Changes
Changed alias by @Ja-Tink in https://github.com/shap/shap/pull/4049
update javascript packages by @CloseChoice in https://github.com/shap/shap/pull/4067
Fixed visual bug for small SHAP values by @Ja-Tink in https://github.com/shap/shap/pull/4053
Fix summary_plot displays only one feature 4081 by @CloseChoice in https://github.com/shap/shap/pull/4087
resolve threading warnings of regex library by @emmanuel-ferdman in https://github.com/shap/shap/pull/4084

New Contributors

@RoyiAvital made their first contribution in https://github.com/shap/shap/pull/4028
@Ja-Tink made their first contribution in https://github.com/shap/shap/pull/4049
@emmanuel-ferdman made their first contribution in https://github.com/shap/shap/pull/4084
@randombenj made their first contribution in https://github.com/shap/shap/pull/3903
@CousinThrockmorton made their first contribution in https://github.com/shap/shap/pull/3666

Full Changelog: https://github.com/shap/shap/compare/v0.47.2...v0.48.0

- Jupyter Notebook
Published by CloseChoice 12 months ago

shap - CausalML support and fix ForceVisualizer regression

What's Changed

Added

Add experimental causalml support by @alexander-pv in https://github.com/shap/shap/pull/3273

Other Changes

DOCS: clarity for partition tree explanation in Simple California Demo.ipynb by @ethanknights in https://github.com/shap/shap/pull/4027
FIX: unique value jitter by @fabianliebig in https://github.com/shap/shap/pull/4041
FIX: fix neutral language in SHAP value description by @Hrafz in https://github.com/shap/shap/pull/4058
FIX regression test for javascript plotting compontents and add tests by @CloseChoice in https://github.com/shap/shap/pull/4060

New Contributors

@ethanknights made their first contribution in https://github.com/shap/shap/pull/4027
@Hrafz made their first contribution in https://github.com/shap/shap/pull/4058

Full Changelog: https://github.com/shap/shap/compare/v0.47.1...v0.47.2

- Jupyter Notebook
Published by CloseChoice about 1 year ago

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

- Jupyter Notebook
Published by CloseChoice about 1 year ago

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

- Jupyter Notebook
Published by CloseChoice about 1 year ago

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

- Jupyter Notebook
Published by connortann almost 2 years ago

shap - v0.45.1

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

- Jupyter Notebook
Published by connortann about 2 years ago

shap - v0.45.0

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

- Jupyter Notebook
Published by connortann about 2 years ago

shap - v0.44.1

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

- Jupyter Notebook
Published by connortann over 2 years ago

shap - v0.44.0

This release contains a number enhancements and bug fixes.

What's Changed

Added

Faster and more stable linear solver in KernelShap by @lorentzenchr in https://github.com/shap/shap/pull/3271
Enabled passing of ax to group_difference() plot by @mtlulka in https://github.com/shap/shap/pull/3355
Added support for Explanation.display_data in bar plot by @fountaindive in https://github.com/shap/shap/pull/3386
Improved build messages when building from source by @connortann in https://github.com/shap/shap/pull/3403

Fixed

Fixed CatboostClassifier explanations with feature interactions on Windows by @CloseChoice in https://github.com/shap/shap/pull/3325
Fixed passing of Xgboost model parameters to xgboost.DMatrix by @vancromy in https://github.com/shap/shap/pull/3314
Explicit specification of xgboost>=1.4 constraint by @mtlulka in https://github.com/shap/shap/pull/3352
Fixed conversion of DMatrix to CSR matrix by @thatlittleboy in https://github.com/shap/shap/pull/3359
Removed deprecated use_line_collection in dependence_plot by @CloseChoice in https://github.com/shap/shap/pull/3369
Fixed bug relating to array reshaping in scatter plots by @SomeUserName1 in https://github.com/shap/shap/pull/2799

Documentation

A large number of example notebooks fixed and updated by @connortann, @znacer , @thatlittleboy, @CloseChoice and @stompsjo

New Contributors

@vancromy made their first contribution in https://github.com/shap/shap/pull/3314
@lorentzenchr made their first contribution in https://github.com/shap/shap/pull/3271
@mtlulka made their first contribution in https://github.com/shap/shap/pull/3352
@fountaindive made their first contribution in https://github.com/shap/shap/pull/3386
@SomeUserName1 made their first contribution in https://github.com/shap/shap/pull/2799
@stompsjo made their first contribution in https://github.com/shap/shap/pull/3391

Full Changelog: https://github.com/shap/shap/compare/v0.43.0...V0.44.0

- Jupyter Notebook
Published by connortann over 2 years ago

shap - v0.43.0

What's Changed

This release contains a number of bug fixes and improvements.

Following the NEP 29 deprecation policy, this release drops support for python 3.7 and will be the last major release to support python 3.8.

Breaking changes

Removed the deprecated Boston dataset by @thatlittleboy in https://github.com/shap/shap/pull/3316
The shape of Explanation.base_values has been standardised between different TreeExplainer models to always be of shape (N,) and not (N,1). By @thatlittleboy in https://github.com/shap/shap/pull/3121

Added

Added additivity check to Pytorch DeepExplainer (activated by default) by @noxthot in https://github.com/shap/shap/pull/3265
Added flag to allow the printing of the mean SHAP value in the legend of a multi-output bar plot. By @101AlexMartin in https://github.com/shap/shap/pull/3062
Added heatmap and violin plot to top-level API by @connortann in https://github.com/shap/shap/pull/3157
Replaced all tqdm imports with tqdm.auto by @owenlamont in https://github.com/shap/shap/pull/3199

Fixed

Fixed segmentation faults on MacOS with lightgbm tests (with newer libomp versions) by @thatlittleboy in https://github.com/shap/shap/pull/3093
Support LightGBM ensemble containing single leaf trees (stump) by @thatlittleboy in https://github.com/shap/shap/pull/3094
Fixed conversion DataFrame to ndarray for Explanation.data by @danieleongari in https://github.com/shap/shap/pull/3131
Fixed waterfall plot on explanations of sklearn tree models by @connortann in https://github.com/shap/shap/pull/3138
Fixed pandas input for gradient explainer by @Koen-Git in https://github.com/shap/shap/pull/3153
Fixed slicing of feature_names in Explanation objects with square .values by @thatlittleboy in https://github.com/shap/shap/pull/3126
Correct xlim in force_matplotlib in cases where the signs of force are all the same by @zaburo-ch in https://github.com/shap/shap/pull/2839
Fixed ngboost explanations when col_sample < 1 by @CloseChoice in https://github.com/shap/shap/pull/3294
Fixed torch additivity check in PyTorch DeepExplainer by @noxthot in https://github.com/shap/shap/pull/3281
Replaced print statements with warnings in DeepExplainer by @znacer in https://github.com/shap/shap/pull/3264
Replace deprecated register_backward_hook() by @noxthot in https://github.com/shap/shap/pull/3259
Fixed deprecated use of xgboost earlystoppingrounds by @CloseChoice in https://github.com/shap/shap/pull/3306
Fixed 3rd party deprecation warnings: numba, xgboost, typing, distutils by @connortann in https://github.com/shap/shap/pull/3084
Updated the Javascript bundle to update deprecated dependencies by @connortann in https://github.com/shap/shap/pull/2974

There have also been a large number of improvements to the tutorials and examples, by @connortann, @znacer, @arshiaar, @thatlittleboy, @dsgibbons, @owenlamont and @CloseChoice

New Contributors

@101AlexMartin made their first contribution in https://github.com/shap/shap/pull/3062
@znacer made their first contribution in https://github.com/shap/shap/pull/3112
@danieleongari made their first contribution in https://github.com/shap/shap/pull/3131
@Koen-Git made their first contribution in https://github.com/shap/shap/pull/3153
@pre-commit-ci made their first contribution in https://github.com/shap/shap/pull/3173
@owenlamont made their first contribution in https://github.com/shap/shap/pull/3199
@arshiaar made their first contribution in https://github.com/shap/shap/pull/3201
@dsgibbons made their first contribution in https://github.com/shap/shap/pull/3200
@noxthot made their first contribution in https://github.com/shap/shap/pull/3265
@zaburo-ch made their first contribution in https://github.com/shap/shap/pull/2839
@CloseChoice made their first contribution in https://github.com/shap/shap/pull/3282

Full Changelog: https://github.com/shap/shap/compare/v0.42.1...v0.43.0

- Jupyter Notebook
Published by connortann over 2 years ago

shap - v0.42.1

Patch release to provide wheels for a broader range of architectures.

Added

Added wheels for linux:aarch64 and macos:arm64 by @PrimozGodec in https://github.com/slundberg/shap/pull/3078 and @connortann in https://github.com/slundberg/shap/pull/3083.

Fixed

Fixed circular import issues with shap.benchmark by @thatlittleboy in https://github.com/slundberg/shap/pull/3076.
Fixed TestPyPI releases workflow by @connortann in https://github.com/slundberg/shap/pull/3068
Fix further flaky tests by @thatlittleboy in https://github.com/slundberg/shap/pull/3073
Fix shap.summary_plot to work with matplotlib 3.6.0 by @jklaise in https://github.com/slundberg/shap/pull/2697
Fix benchmark top-level import by @thatlittleboy in https://github.com/slundberg/shap/pull/3076
Fix ipython import warning from top-level shap import by @connortann in https://github.com/slundberg/shap/pull/3090

Full Changelog: https://github.com/slundberg/shap/compare/v0.42.0...v0.42.1

- Jupyter Notebook
Published by connortann almost 3 years ago

shap - v0.42.0

This release incorporates many changes that were originally contributed by the SHAP community via @dsgibbons's Community Fork, which has now been merged into the main shap repository. PRs from this origin are labelled here as fork#123.

This will be the last release that supports python 3.7.

Added

Added support for python 3.11 (fork#72 by @connortann).
Added n_points parameter to all functions in shap.datasets (fork#39 by @thatlittleboy).
Added __call__ to KernelExplainer (#2966 by @dwolfeu).
Added contributing guidelines (#2996 by @connortann).

Fixed

Fixed plot.waterfall to support yticklabels with boolean features (fork#58 by @dwolfeu).
Prevent TreeExplainer.__call__ from throwing ValueError when passed a pandas DataFrame containing Categorical columns (fork#88 by @thatlittleboy).
Fixed sampling in shap.datasets to sample without replacement (fork#36 by @thatlittleboy).
Fixed an UnboundLocalError problem arising from passing a dictionary input to shap.plots.bar (#3001 by @thatlittleboy).
Fixed tensorflow import issue with Pyspark when using Gradient (#2983 by @skamdar).
Fixed the aspect ratio of the colorbar in shap.plots.heatmap, and use the ax matplotlib API internally for plotting (#3040 by @thatlittleboy).
Fixed deprecation warnings for numba>=0.44 (fork#9 and fork#68 by @connortann).
Fixed deprecation warnings for numpy>=1.24 from numpy types (fork#7 by @dsgibbons).
Fixed deprecation warnings for Ipython>=8 from Ipython.core.display (fork#13 by @thatlittleboy).
Fixed deprecation warnings for tensorflow>=2.11 from tf.optimisers (fork#16 by @simonangerbauer).
Fixed deprecation warnings for sklearn>=1.2 from sklearn.linear_model (fork#22 by @dsgibbons).
Fixed deprecation warnings for xgboost>=1.4 from ntree_limit in tree explainer (#2987 by @adnene-guessoum).
Fixed build on Windows and MacOS (#3015 by @PrimozGodec; #3028, #3029 and #3031 by @connortann).
Fixed creation of ragged arrays in shap.explainers.Exact (#3064 by @connortann).

Changed

Updates to docstrings of several shap.plots functions (#3003, #3005 by @thatlittleboy).

Removed

Deprecated the Boston house price dataset (fork#38 by @thatlittleboy).
Removed the unused mimic.py file and MimicExplainer code (fork#53 by @thatlittleboy).

Maintenance

Fixed failing unit tests (fork#29 by @dsgibbons, fork#20 by @simonangerbauer, #3044 and fork#24 by @connortann).
Include CUDA GPU C extension files in the source distribution (#3009 by @jklaise).
Fixed installation of package via setuptools (fork#51 by @thatlittleboy).
Introduced a minimal set of ruff linting (fork#25, fork#26, fork#27, #2973, #2972 and #2976 by @connortann; #2968, #2986 by @thatlittleboy).
Updated project metadata to PEP 517 (#3022 by @connortann).
Introduced more thorough testing on CI against newer dependencies (fork#61 and #3017 by @connortann)
Reduced unit test time by ~5 mins (#3046 by @connortann).
Introduced fixtures for reproducible fuzz testing (#3048 by @connortann).

- Jupyter Notebook
Published by connortann almost 3 years ago

shap - v0.41.0

Lots of bugs fixes and API improvements.

Fixed rare bug with XGBoost model loading by @TheZL @lrjball
Fixed the beeswarm plot so it does not modify the passed explanation object, @ravwojdyla
Automatic wheel building using GH actions by @quantumtec
GC collection for memory in KernelExplainer by @Qingtian-Zou
Fixed max_evals params for PartitionExplainer
JIT optimize the PartitionExplainer
Fix colorbar formatting issues @SleepyPepperHead
New benchmark notebooks
Use display_data for plotting when possible @yuuuxt
Improved GPUTreeShap compilation and params @RAMitchell
Fix TF API change in DeepExplainer @filusn
Add torch tensor support for plots @alexander-pv
Switch to Github actions for testing instead of Travis
New California demo dataset @swalsh1123
Fix waterfall plot bug @RichardScottOZ
Handle missing matplotlib installation @klieret
Add linearize link support for Additive explainer (Nandish Gupta)
Fix exceptions to be more specific @alexisdrakopoulos @collinb9
Add color map option for plotting @tlabarta
Release fixed numpy version requirement @rmehyde
And many other contributions kindly made by @WeichenXu123 @imatiach-msft @zeshengli @nkthiebaut @songololo @GiovannaNicora @joshzwiebel @Ashishbodla @navdeep-G @smathewmanuel @ycouble @anubhavmaity @adityasaini70 @ngupta20 @jckkvs @abs428 @JulesCollenne @Tiagosf00 @javirandor and @Thuener

- Jupyter Notebook
Published by slundberg almost 4 years ago

shap - v0.40.0

This release contains many bugs fixes and lots of new functionality, specifically for transformer based NLP models. Some highlights include: - New plots, bug fixes, docs, and features for NLP model explanations (see docs for details). - important permutation explainer performance fix by @sander-sn - New joint scatter plots to plot many at once on the same y-scale - better tree model memory usage by @morriskurz - new docs by @coryroyce - new wheel building by @PrimozGodec - dark mode improvements for the docs by @gialmisi - api tweaks by @c56pony @nsorros @jebarb

- Jupyter Notebook
Published by slundberg over 4 years ago

shap - v0.39.0

Lots of new text explainer work courtesy of @ryserrao and serialization courtesy of @vivekchettiar! (will note all the other changes later)

- Jupyter Notebook
Published by slundberg about 5 years ago

shap - v0.38.1

Fixes a version mismatch with the v0.38.0 release and serialization updates.

- Jupyter Notebook
Published by slundberg over 5 years ago

shap - v0.38.0

This release contains improved support for explanations of transformer text models and support for the new Explanation object based API. Specific improvements include:

Transformer model support in the Text explainer courtesy of @ryserrao
Interventional Tree explainer GPU support courtesy of @RAMitchell
Image captioning model support courtesy of @anusham1990
Benchmarking improvements courtesy of @maggiewu19
New text and image visualizations courtesy of @vivekchettiar
New explainer serialization support courtesy of @vivekchettiar
Bug fixes for Linear explainer and the new API courtesy of @heimengqi
Fix for categorical plots courtesy of @jeffreyftang
CUDA support improvements courtesy of @JohnZed
Support for econML model courtesy of @vasilismsr
Many other bug fixes and API improvements.

- Jupyter Notebook
Published by slundberg over 5 years ago

shap - v0.37.0

This release contains more support for the new API, many bug fixes, and preliminary model agnostic text/image explainer support (still beta). Specific contributions include:

Fix Sampling explainer sample counting issue courtesy of @tcbegley
Add multi-bar plotting support.
Preliminary support for cohorts.
Fixed an import error courtesy of @suragnair
Fix Tree explainer issues with isolation forests with max_features < 1 courtesy of @zhanjiezhu
Huge documentation cleanup and update courtesy of @lrjball
Typo fix courtesy of @anusham1990
Added a documentation notebook for the Exact explainer.
Text and Image explainers courtesy of @anusham1990 and Ryan Serrao
Bug fix for shap.utils.hclust
Initial support for InterpretML EBM models.
Added column grouping functionality to Explainer objects.
Fix for loop index bug in Deep explainer for PyTorch courtesy of @quentinRaq
Initial text to text visualization concepts courtesy of @vivekchettiar
Color conversion warning fix courtesy of @wangjoshuah
Fix invertibility issues in Kernel explainer with the pseudoinverse courtesy of @PrimozGodec
New benchmark code courtesy of @maggiewu19 and @vivekchettiar
Other small bug fixes and enhancements.

- Jupyter Notebook
Published by slundberg over 5 years ago

shap - v0.36.0

This version contains a significant refactoring of the SHAP code base into a new (cleaner) API. Full backwards compatibility should be retained, but most things are now available in locations with the new API. Note that this API is still in a beta form, so refrain from depending on it for production code until the next release. Highlights include: - A new shap.Explainer object that auto-chooses the explainer based on the given model and masking dataset. - A new shap.Explanation object that allows for parallel slicing of data, SHAP values, base values (expected values), and other explanation-specific elements. - A new shap.maskers.* module that separates the various ways to mask (i.e. perturb/hide) features from the algorithms themselves. - A new shap.explainers.Partition explainer that can explain any text or image models very quickly. - A new shap.maskers.Partition masker that ensures tightly grouped features are perturbed in unison, so preventing "unrealistic" model inputs from inappropriately influencing the model prediction. It also allows for the exact quadratic time computation of SHAP values for the 'structured games' (with coalitions structured according to a hierarchical clustering). - A new shap.plots.* module with revamped plot types that all support the new API. Plots are now named more directly, so summary_plot (default) becomes beeswarm, and dependent_plot becomes scatter. Not all the plots have been ported over to the new API, but most have. - A new notebooks/plots/* directory given examples of how to use the new plotting functions. - A new shap.plots.bar function to directly create bar plots and also display hierarchical clustering structures to group redundant features together, and show the structure used by a Partition explainer (that relied on Owen values, which are an extension of Shapley values). - Equally check fixes courtesy of @jameslamb - Sparse kmeans support courtesy of @PrimozGodec - Pytorch bug fixes courtesy of @rightx2 - NPM JS code clean up courtesy of @SachinVarghese - Fix logit force plot bug courtesy of @ehuijzer - Decision plot documentation updates courtesy of @floidgilbert - sklearn GBM fix courtesy of @ChemEngDataSci - XGBoost 1.1 fix courtesy of @lrjball - Make SHAP spark serializable courtesy of @QuentinAmbard - Custom summary plot color maps courtesy of @nasir-bhanpuri - Support string inputs for KernelSHAP courtesy of @YotamElor - Doc fixes courtesy of @imatiach-msft - Support for GPBoost courtesy of @fabsig - Import bug fix courtesy of @gracecarrillo and @aokeson

- Jupyter Notebook
Published by slundberg almost 6 years ago

shap - 0.35.0

This release includes:

Better support for TensorFlow 2 (thanks @imatiach-msft)
Support for NGBoost models in TreeExplainer (thanks @zhiruiwang)
TreeExplainer support for the new sklearn.ensemble.HistGradientBoosting model.
New improved versions of PartitionExplainer for images and text.
IBM zOS compatibility courtesy of @DorianCzichotzki.
Support for XGBoost 1.0
Many bug fixes courtesy of Ivan, Christian Paul, @RandallJEllis, and @ibuda.

- Jupyter Notebook
Published by slundberg over 6 years ago

shap - 0.34.0

This release includes: - Many small bug fixes. - Better matplotlib text alignment during rotation courtesy of @koomie - Cleaned up the C++ transformer code to allow easier PRs. - Fixed a too tight checkadditivity tolerance in TreeExplainer #950 - Updated the LinearExplainer API to match TreeExplainer - Allow custom class ordering in a summaryplot courtesy of @SimonStreicher

- Jupyter Notebook
Published by slundberg over 6 years ago

shap - 0.33.0

This release contains various bug fixes and new features including:

Added PySpark support for TreeExplainer courtesy of @QuentinAmbard
A new type of plot that is an alternative to the forceplot, a `waterfallplot`
A new PermutationExplainer that is an alternative to KernelExplainer and SamplingExplainer.
Added return_variances to GradientExplainer for PyTorch courtesy of @s6juncheng
Now we use exceptions rather than assertions in TreeExplainer courtesy of @ssaamm
Fixed image_plot transpose issue courtesy of @Jimbotsai
Fix color bar axis attachment issue courtesy of Lasse Valentini Jensen
Fix tensor attachment issue in PyTorch courtesy of @gabrieltseng
Fix color clipping ranges in summary_pot courtesy of @joelostblom
Address sklearn 0.22 API changes courtesy of @lemon-yellow
Ensure matplotlib is optional courtesy of @imatiach-msft

- Jupyter Notebook
Published by slundberg over 6 years ago

shap - 0.32.1

This release is just intended to push better auto-deploy bundles out of travis and appveyor.

- Jupyter Notebook
Published by slundberg over 6 years ago

shap - 0.32.0

This release includes: - Support for sklearn isolation forest courtesy of @JiechengZhao - New check_additivity tests to ensure no errors in DeepExplainer and TreeExplainer - Fix #861, #860 - Fix missing readme example html file - Support for spark decision tree regressor courtesy of @QuentinAmbard - Better safe isinstance checking courtesy of @parsatorb - Fix eager execution in TF < 2 courtesy of @bottydim

- Jupyter Notebook
Published by slundberg over 6 years ago

shap - 0.31.0

This release contains several new features and bug fixes: - GradientExplainer now supports TensorFlow 2.0. - We now do a lazy load of the plotting dependencies, which means a pip install no longer needs to also pull in matplotlib, skimage, and ipython. This should make installs much lighter, especially those that don't need plotting :) - Added a new BruteForceExplainer for easy testing and comparison on small problems. - Added a new partialdependenceplot function. This function will be used to illustrate the close connections between partial dependence plots and SHAP values in future example notebooks. - Handle the multiclass case with no intercept in LinearExplainer courtesy of @gabrieltseng - Some extras_require options during the pip install courtesy of @AbdealiJK - Other small bug fixes and updates

- Jupyter Notebook
Published by slundberg over 6 years ago

shap - 0.30.2

This release is primarily to remove a dependency on dill that was not in setup.py. It also includes:

A typo fix in force.py courtesy of @jonlwowski012
Test code cleanup courtesy of @jorgecarleitao

- Jupyter Notebook
Published by slundberg over 6 years ago

shap - 0.30.1

Fix floating point rounding mismatches in recent sklearn versions of tree models
An update to allow easier loading of custom tree ensemble models by TreeExplainer.
decision_plot documentation updates courtesy of @floidgilbert

- Jupyter Notebook
Published by slundberg over 6 years ago

shap - 0.30.0

New decision_plot function courtesy of @floidgilbert
Add alpha version of the new model agnostic PartitionExplainer
ensure data is all on the same device for pytorch in DeepExplainer courtesy of @gabrieltseng
fix lightgbm edge case issue courtesy of @imatiach-msft
create binder setup for shap courtesy of @jamesmyatt
Allow for multiple inputs in the gradient explainer courtesy of @gabrieltseng
New KernelExplainer unit tests courtesy of @jorgecarleitao
Add python 2/3 trove classifiers courtesy of @proinsias
support for pyspark trees courtesy of @QuentinAmbard
many other bug fixes courtesy of @Rygu, @Kylecrif, @trams, @imatiach-msft, @yunchuankong, @invokermain, @lupusomniator, @satyarta, @jotsif, @parkerzf, @jaller94, @gabrieltseng, and others

- Jupyter Notebook
Published by slundberg almost 7 years ago

shap - 0.29.3

Fixes an issue in DeepExplainer caused by a change in TensorFlow 1.14.

- Jupyter Notebook
Published by slundberg almost 7 years ago

shap - 0.29.2

Various bug fixes and improvements including:

adding SHAP values for binary classification to CatBoost courtesy of @dvpolyakov
Integer division fix for plots courtesy of @pmeier-tiplu
Support passing in an Axes object to dependence_plot courtesy of @mqk
Add adaptive average pooling and conv transpose layers courtesy of of @gabrieltseng
fix import errors on a missing matplotlib backend courtesy of @hchandola
fix TreeExplainer GradientBoostingClassifier bug courtesy of @prempiyush
make tqdm play nicer with notebooks courtesy of @KOLANICH
Allow deep_pytorch to use cuda models courtesy of @juliusbierk
Fix sklearn GradientBoostingRegressor bug courtesy of @nasir-bhanpuri
adding sparse support to shap linear explainer courtesy of @imatiach-msft

- Jupyter Notebook
Published by slundberg almost 7 years ago

shap - 0.29.1

Fixes to support changes in the most recent version of sklearn

- Jupyter Notebook
Published by slundberg about 7 years ago

shap - 0.29.0

A few contribution highlights of this release (in chronological order) - Better testing courtesy of @jorgecarleitao - Image plot customizations courtesy of @verdimrc - Batch norm support for PyTorch in DeepExplainer courtesy of @JiechengZhao - Leaky ReLU and other conv layer support for pytorch deep explainer courtesy of @gabrieltseng - Fixed keras multi input in gradient explainer and improved random seeds courtesy of @moritzaugustin - Support for catBoost ranker courtesy of @doramir - Added XGBRanker and LGBMRanker to TreeExplainer courtesy of @imatiach-msft - Fix embedding lookup with tf.keras in DeepExplainer courtesy of @andriy-nikolov - Custom dependence_plot colors maps courtesy of @rcarneva - Fix divide by zero issues possible with CatBoost models courtesy of @dvpolyakov - Lots of other bug fixes/improvements!

- Jupyter Notebook
Published by slundberg about 7 years ago

shap - 0.28.5

This release is just to refresh the Windows builds on AppVeyor that didn't complete for 0.28.4

- Jupyter Notebook
Published by slundberg over 7 years ago

shap - 0.28.4

Fixes memory corruption error from TreeExplainer (courtesy of @imatiach-msft)
Adds support for skopt Random Forest and ExtraTrees Regressors (courtesy of @Bacoknight)
Adds support for matplotlib forceplot with text rotation (courtesy of @vatsan)
Adds a save_html function

- Jupyter Notebook
Published by slundberg over 7 years ago

shap - 0.28.3

Fix some plot coloring issues introduced by 0.28 (such as #406)

- Jupyter Notebook
Published by slundberg over 7 years ago

shap - 0.28.2

Downgrade numpy API usage to support older versions.

- Jupyter Notebook
Published by slundberg over 7 years ago

shap - 0.28.1

Fixes a byte-alignment issue on Windows when loading XGBoost models.
Now matches tree_limit use in XGBoost models courtesy of @HughChen
Fix an issue with the expected_value of transformed model outputs in TreeExplainer

- Jupyter Notebook
Published by slundberg over 7 years ago

shap - 0.28.0

Add support for rank-based feature selection in KernelExplainer.
Depreciate l1_reg="auto" in KernelExplainer in favor of eventually defaulting to l1_reg="num_features(10)"
New color scales based on the Lch color space.
Better auto-color choices for multi-class summary plots.
Better plotting of NaN values in dependence_plots
Updates for Pytorch 1.0 courtesy of @gabrieltseng
Fix the sklearn DecisionTreeClassifier handling to correctly normalize to a probability output
Enable multi-output model support for TreeExplainer when feature_dependence="independent"
Correctly load the objective of LightGBM models for use in explaining the model loss.
Fix numerical precision mismatch with sklearn models.
Fix numerical precision mismatch with XGBoost models by now directly loading from memory instead of JSON.

- Jupyter Notebook
Published by slundberg over 7 years ago

shap - 0.27.0

Better hierarchal clustering orderings that now rotate subtrees to give more continuity.
Work around XGBoost JSON issue.
Account for NaNs when doing auto interaction detection.
PyTorch fixes.
Updated LinearExplainer.

- Jupyter Notebook
Published by slundberg over 7 years ago

shap - 0.26.0

Complete refactor of TreeExplainer to support deeper C++ integration
The ability to explain transformed outputs of tree models in TreeExplainer, including the loss. In collaboration with @HughChen
Allow for a dynamic reference value in DeepExplainer courtesy of @AvantiShri
Add x_jitter option for categorical dependence plots courtesy of @ihopethiswillfi
Added support for GradientBoostingRegressor with quantile loss courtesy of @dmilad
Better plotting support for NaN values
Fixes several bugs.

- Jupyter Notebook
Published by slundberg over 7 years ago

shap - 0.25.2

Allows orderingkeys to be given to forceplot courtesy of @JasonTam
Fixes sparse nonzero background issue with KernelExplainer courtesy of @imatiach-msft
Fix to support tf.concat in DeepExplainer.

- Jupyter Notebook
Published by slundberg over 7 years ago

shap - 0.25.1

Fixes a problem where tree_shap.h was not included in the pip bundle.

- Jupyter Notebook
Published by slundberg over 7 years ago

shap - 0.25.0

Support for PyTorch in GradientExplainer and preliminary support for PyTorch in DeepExplainer courtesy of @gabrieltseng.
A matplotlib version of the single sample force_plot courtesy of @jverre.
Support functional Keras models in GradientExplainer.
KernelExplainer speed improvements.
Various performance improvements and bug fixes.

- Jupyter Notebook
Published by slundberg over 7 years ago

shap - 0.24.0

New improvements include: Faster KernelExplainer execution for sparse inputs. Support for sklearn gradient boosting classifiers. DeepExplainer extended to support very deep models.