shapiq 1.3.0__tar.gz → 1.3.2__tar.gz

{shapiq-1.3.0 → shapiq-1.3.2}/CHANGELOG.md

@@ -1,13 +1,31 @@
-## Changelog
+# Changelog
 
-### v1.3.0 (2025-06-17)
+## v1.3.2 (2025-10-14)
 
-#### Highlights
+### Hotfix
+Removes `overrides` import in tabular explainer, which is not part of the package dependencies resulting in an ImportError when importing `shapiq`. [#436](https://github.com/mmschlk/shapiq/issues/436)
+
+## v1.3.1 (2025-07-11)
+
+### New Features
+- adds the `shapiq.plot.beesvarm_plot()` function to shapiq. The beeswarm plot was extended to also support interactions of features. Beeswarm plots are useful in visualizing dependencies between feature values. The beeswarm plot was adapted from the SHAP library by sub-dividing the y-axis for each interaction term. [#399](https://github.com/mmschlk/shapiq/issues/399)
+- adds JSON support to `InteractionValues` and `Game` objects, allowing for easy serialization and deserialization of interaction values and game objects [#412](https://github.com/mmschlk/shapiq/pull/412) usage of `pickle` is now deprecated. This change allows us to revamp the data structures in the future and offers more flexibility.
+
+### Testing, Code-Quality and Documentation
+- adds a testing suite for testing deprecations in `tests/tests_deprecations/` which allows for easier deprecation managment and tracking of deprecated features [#412](https://github.com/mmschlk/shapiq/pull/412)
+
+## Deprecated
+- The `Game(path_to_values=...)` constructor is now deprecated and will be removed in version 1.4.0. Use `Game.load(...)` or `Game().load_values(...)` instead.
+- Saving and loading `InteactionValues` via `InteractionValues.save(..., as_pickle=True)` and `InteractionValues.save(..., as_npz=True)` is now deprecated and will be removed in version 1.4.0. Use `InteractionValues.save(...)` to save as json.
+
+## v1.3.0 (2025-06-17)
+
+### Highlights
 - `shapiq.SPEX` (Sparse Exact) approximator for efficient computation of sparse interaction values for really large models and games. Paper: [SPEX: Scaling Feature Interaction Explanations for LLMs](https://arxiv.org/abs/2502.13870)
 - `shapiq.AgnosticExplainer` a generic explainer that works for any value function or `shapiq.Game` object, allowing for more flexibility in explainers.
 - prettier graph-based plots via `shapiq.si_graph_plot()` and `shapiq.network_plot()`, which now use the same backend for more flexibility and easier maintenance.
 
-#### New Features
+### New Features
 - adds the SPEX (Sparse Exact) module in `approximator.sparse` for efficient computation of sparse interaction values [#379](https://github.com/mmschlk/shapiq/pull/379)
 - adds `shapiq.AgnosticExplainer` which is a generic explainer that can be used for any value function or `shapiq.Game` object. This allows for more flexibility in the explainers. [#100](https://github.com/mmschlk/shapiq/issues/100), [#395](https://github.com/mmschlk/shapiq/pull/395)
 - changes `budget` to be a mandatory parameter given to the `TabularExplainer.explain()` method [#355](https://github.com/mmschlk/shapiq/pull/356)
@@ -19,7 +37,7 @@
 - adds `Game.compute()` method to the `shapiq.Game` class to compute game values without changing the state of the game object. The compute method also introduces a `shapiq.utils.sets.generate_interaction_lookup_from_coalitions()` utility method which creates an interaction lookup dict from an array of coalitions. [#397](https://github.com/mmschlk/shapiq/pull/397)
 - streamlines the creation of network plots and graph plots which now uses the same backend. The network plot via `shapiq.network_plot()` or `InteractionValues.plot_network()` is now a special case of the `shapiq.si_graph_plot()` and `InteractionValues.plot_si_graph()`. This allows to create more beautiful plots and easier maintenance in the future. [#349](https://github.com/mmschlk/shapiq/pull/349)
 
-#### Testing, Code-Quality and Documentation
+### Testing, Code-Quality and Documentation
 - activates ``"ALL"`` rules in ``ruff-format`` configuration to enforce stricter code quality checks and addressed around 500 (not automatically solvable) issues in the code base. [#391](https://github.com/mmschlk/shapiq/pull/391)
 - improved the testing environment by adding a new fixture module containing mock `InteractionValues` objects to be used in the tests. This allows for more efficient and cleaner tests, as well as easier debugging of the tests  [#372](https://github.com/mmschlk/shapiq/pull/372)
 - removed check and error message if the ``index`` parameter is not in the list of available indices in the ``TabularExplainer`` since the type hints were replaced by Literals [#391](https://github.com/mmschlk/shapiq/pull/391)
@@ -29,12 +47,12 @@
 - refactors the tests into ``tests_unit/`` and ``tests_integration/`` to better separate unit tests from integration tests. [#395](https://github.com/mmschlk/shapiq/pull/395)
 - adds new integration tests in ``tests/tests_integration/test_explainer_california_housing`` which compares the different explainers against ground-truth interaction values computed by ``shapiq.ExactComputer`` and interaction values stored on [disk](https://github.com/mmschlk/shapiq/tree/main/tests/data/interaction_values/california_housing) as a form of regression test. This test should help finding bugs in the future when the approximators, explainers, or exact computation are changed. [#395](https://github.com/mmschlk/shapiq/pull/395)
 
-#### Bug Fixes
+### Bug Fixes
 - fixed a bug in the `shapiq.waterfall_plot` function that caused the plot to not display correctly resulting in cutoff y_ticks. Additionally, the file was renamed from `watefall.py` to `waterfall.py` to match the function name [#377](https://github.com/mmschlk/shapiq/pull/377)
 - fixes a bug with `TabPFNExplainer`, where the model was not able to be used for predictions after it was explained. This was due to the model being fitted on a subset of features, which caused inconsistencies in the model's predictions after explanation. The fix includes that after each call to the `TabPFNImputer.value_function`, the tabpfn model is fitted on the whole dataset (without omitting features). This means that the original model can be used for predictions after it has been explained. [#396](https://github.com/mmschlk/shapiq/issues/396).
 - fixed a bug in computing `BII` or `BV` indices with `shapiq.approximator.MonteCarlo` approximators (affecting `SHAP-IQ`, `SVARM` and `SVARM-IQ`). All orders of BII should now be computed correctly. [#395](https://github.com/mmschlk/shapiq/pull/395)
 
-### v1.2.3 (2025-03-24)
+## v1.2.3 (2025-03-24)
 - substantially improves the runtime of all `Regression` approximators by a) a faster pre-computation of the regression matrices and b) a faster computation of the weighted least squares regression [#340](https://github.com/mmschlk/shapiq/issues/340)
 - removes `sample_replacements` parameter from `MarginalImputer` and removes the DeprecationWarning for it
 - adds a trivial computation to `TreeSHAP-IQ` for trees that use only one feature in the tree (this works for decision stumps or trees splitting on only one feature multiple times). In such trees, the computation is trivial as the whole effect of $\nu(N) - \nu(\emptyset)$ is all on the main effect of the single feature and there is no interaction effect. This expands on the fix in v1.2.1 [#286](https://github.com/mmschlk/shapiq/issues/286).
@@ -45,18 +63,18 @@
 - adds the `RegressionFBII` approximator to estimate Faithful Banzhaf interactions via least squares regression [#333](https://github.com/mmschlk/shapiq/pull/333). Additionally, FBII support was introduced in TabularExplainer and MonteCarlo-Approximator.
 - adds a `RandomGame` class as part of `shapiq.games.benchmark` which always returns a random vector of integers between 0 and 100.
 
-### v1.2.2 (2025-03-11)
+## v1.2.2 (2025-03-11)
 - changes python support to 3.10-3.13 [#318](https://github.com/mmschlk/shapiq/pull/318)
 - fixes a bug that prohibited importing shapiq in environments without write access [#326](https://github.com/mmschlk/shapiq/issues/326)
 - adds `ExtraTreeRegressors` to supported models [#309](https://github.com/mmschlk/shapiq/pull/309)
 
-### v1.2.1 (2025-02-17)
+## v1.2.1 (2025-02-17)
 - fixes bugs regarding plotting [#315](https://github.com/mmschlk/shapiq/issues/315) and [#316](https://github.com/mmschlk/shapiq/issues/316)
 - fixes a bug with TreeExplainer and Trees that consist of only one feature [#286](https://github.com/mmschlk/shapiq/issues/286)
 - fixes SV init with explainer for permutation, svarm, kernelshap, and unbiased kernelshap [#319](https://github.com/mmschlk/shapiq/issues/319)
 - adds a progress bar to `explain_X()` [#324](https://github.com/mmschlk/shapiq/issues/324)
 
-### v1.2.0 (2025-01-15)
+## v1.2.0 (2025-01-15)
 - adds ``shapiq.TabPFNExplainer`` as a specialized version of the ``shapiq.TabularExplainer`` which offers a streamlined variant of the explainer for the TabPFN model [#301](https://github.com/mmschlk/shapiq/issues/301)
 - handles ``explainer.explain()`` now through a common interface for all explainer classes which now need to implement a ``explain_function()`` method
 - adds the baseline_value into the InteractionValues object's value storage for the ``()`` interaction if ``min_order=0`` (default usually) for all indices that are not ``SII```(SII has another baseline value) such that the values are efficient (sum up to the model prediction) without the awkward handling of the baseline_value attribute
@@ -71,20 +89,20 @@
 - refactors game theory computations like `ExactComputer`, `MoebiusConverter`, `core`, among others to be more modular and flexible into the `game_theory` module [#258](https://github.com/mmschlk/shapiq/issues/258)
 - improves quality of the tests by adding many more semantic tests to the different interaction indices and computations [#285](https://github.com/mmschlk/shapiq/pull/285)
 
-### v1.1.1 (2024-11-13)
+## v1.1.1 (2024-11-13)
 
-#### Improvements and Ease of Use
+### Improvements and Ease of Use
 - adds a `class_index` parameter to `TabularExplainer` and `Explainer` to specify the class index to be explained for classification models [#271](https://github.com/mmschlk/shapiq/issues/271) (renames `class_label` parameter in TreeExplainer to `class_index`)
 - adds support for `PyTorch` models to `Explainer` [#272](https://github.com/mmschlk/shapiq/issues/272)
 - adds new tests comparing `shapiq` outputs for SVs with alues computed with `shap`
 - adds new tests for checking `shapiq` explainers with different types of models
 
-#### Bug Fixes
+### Bug Fixes
 - fixes a bug that `RandomForestClassifier` models were not working with the `TreeExplainer` [#273](https://github.com/mmschlk/shapiq/issues/273)
 
-### v1.1.0 (2024-11-07)
+## v1.1.0 (2024-11-07)
 
-#### New Features and Improvements
+### New Features and Improvements
 - adds computation of the Egalitarian Core (`EC`) and Egalitarian Least-Core (`ELC`) to the `ExactComputer` [#182](https://github.com/mmschlk/shapiq/issues/182)
 - adds `waterfall_plot` [#34](https://github.com/mmschlk/shapiq/issues/34) that visualizes the contributions of features to the model prediction
 - adds `BaselineImputer` [#107](https://github.com/mmschlk/shapiq/issues/107) which is now responsible for handling the `sample_replacements` parameter. Added a DeprecationWarning for the parameter in `MarginalImputer`, which will be removed in the next release.
@@ -97,7 +115,7 @@
 - a `shapiq.Game` can now be called more intuitively with coalitions data types (tuples of int or str) and also allows to add `player_names` to the game at initialization [#183](https://github.com/mmschlk/shapiq/issues/183)
 - improve tests across the package
 
-#### Documentation
+### Documentation
 - adds a notebook showing how to use custom tree models with the `TreeExplainer` [#66](https://github.com/mmschlk/shapiq/issues/66)
 - adds a notebook show how to use the `shapiq.Game` API to create custom games [#184](https://github.com/mmschlk/shapiq/issues/184)
 - adds a notebook showing hot to visualize interactions [#252](https://github.com/mmschlk/shapiq/issues/252)
@@ -105,17 +123,17 @@
 - adds a notebook for conducting data valuation [#190](https://github.com/mmschlk/shapiq/issues/190)
 - adds a notebook showcasing introducing the Core and how to compute it with `shapiq` [#191](https://github.com/mmschlk/shapiq/issues/191)
 
-#### Bug Fixes
+### Bug Fixes
 - fixes a bug with SIs not adding up to the model prediction because of wrong values in the empty set [#264](https://github.com/mmschlk/shapiq/issues/264)
 - fixes a bug that `TreeExplainer` did not have the correct baseline_value when using XGBoost models [#250](https://github.com/mmschlk/shapiq/issues/250)
 - fixes the force plot not showing and its baseline value
 
-### v1.0.1 (2024-06-05)
+## v1.0.1 (2024-06-05)
 
 - add `max_order=1` to `TabularExplainer` and `TreeExplainer`
 - fix `TreeExplainer.explain_X(..., n_jobs=2, random_state=0)`
 
-### v1.0.0 (2024-06-04)
+## v1.0.0 (2024-06-04)
 
 Major release of the `shapiq` Python package including (among others):
 

{shapiq-1.3.0/shapiq.egg-info → shapiq-1.3.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: shapiq
-Version: 1.3.0
+Version: 1.3.2
 Summary: Shapley Interactions for Machine Learning
 Author: Hubert Baniecki, Fabian Fumagalli
 Author-email: Maximilian Muschalik <Maximilian.Muschalik@lmu.de>
@@ -48,8 +48,8 @@ Requires-Dist: lightgbm; extra == "ml"
 Requires-Dist: transformers; extra == "ml"
 Requires-Dist: scikit-image; extra == "ml"
 Requires-Dist: joblib; extra == "ml"
-Requires-Dist: tensorflow; python_version < "3.13" and extra == "ml"
-Requires-Dist: tf-keras; python_version < "3.13" and extra == "ml"
+Requires-Dist: tensorflow; (python_version < "3.13" and platform_system != "Windows") and extra == "ml"
+Requires-Dist: tf-keras; (python_version < "3.13" and platform_system != "Windows") and extra == "ml"
 Dynamic: license-file
 
 # shapiq: Shapley Interactions for Machine Learning <img src="https://raw.githubusercontent.com/mmschlk/shapiq/main/docs/source/_static/logo/logo_shapiq_light.svg" alt="shapiq_logo" align="right" height="250px"/>
@@ -273,16 +273,34 @@ Some authors acknowledge the financial support by the German Research Foundation
 ---
 Built with ❤️ by the shapiq team.
 
-## Changelog
+# Changelog
 
-### v1.3.0 (2025-06-17)
+## v1.3.2 (2025-10-14)
 
-#### Highlights
+### Hotfix
+Removes `overrides` import in tabular explainer, which is not part of the package dependencies resulting in an ImportError when importing `shapiq`. [#436](https://github.com/mmschlk/shapiq/issues/436)
+
+## v1.3.1 (2025-07-11)
+
+### New Features
+- adds the `shapiq.plot.beesvarm_plot()` function to shapiq. The beeswarm plot was extended to also support interactions of features. Beeswarm plots are useful in visualizing dependencies between feature values. The beeswarm plot was adapted from the SHAP library by sub-dividing the y-axis for each interaction term. [#399](https://github.com/mmschlk/shapiq/issues/399)
+- adds JSON support to `InteractionValues` and `Game` objects, allowing for easy serialization and deserialization of interaction values and game objects [#412](https://github.com/mmschlk/shapiq/pull/412) usage of `pickle` is now deprecated. This change allows us to revamp the data structures in the future and offers more flexibility.
+
+### Testing, Code-Quality and Documentation
+- adds a testing suite for testing deprecations in `tests/tests_deprecations/` which allows for easier deprecation managment and tracking of deprecated features [#412](https://github.com/mmschlk/shapiq/pull/412)
+
+## Deprecated
+- The `Game(path_to_values=...)` constructor is now deprecated and will be removed in version 1.4.0. Use `Game.load(...)` or `Game().load_values(...)` instead.
+- Saving and loading `InteactionValues` via `InteractionValues.save(..., as_pickle=True)` and `InteractionValues.save(..., as_npz=True)` is now deprecated and will be removed in version 1.4.0. Use `InteractionValues.save(...)` to save as json.
+
+## v1.3.0 (2025-06-17)
+
+### Highlights
 - `shapiq.SPEX` (Sparse Exact) approximator for efficient computation of sparse interaction values for really large models and games. Paper: [SPEX: Scaling Feature Interaction Explanations for LLMs](https://arxiv.org/abs/2502.13870)
 - `shapiq.AgnosticExplainer` a generic explainer that works for any value function or `shapiq.Game` object, allowing for more flexibility in explainers.
 - prettier graph-based plots via `shapiq.si_graph_plot()` and `shapiq.network_plot()`, which now use the same backend for more flexibility and easier maintenance.
 
-#### New Features
+### New Features
 - adds the SPEX (Sparse Exact) module in `approximator.sparse` for efficient computation of sparse interaction values [#379](https://github.com/mmschlk/shapiq/pull/379)
 - adds `shapiq.AgnosticExplainer` which is a generic explainer that can be used for any value function or `shapiq.Game` object. This allows for more flexibility in the explainers. [#100](https://github.com/mmschlk/shapiq/issues/100), [#395](https://github.com/mmschlk/shapiq/pull/395)
 - changes `budget` to be a mandatory parameter given to the `TabularExplainer.explain()` method [#355](https://github.com/mmschlk/shapiq/pull/356)
@@ -294,7 +312,7 @@ Built with ❤️ by the shapiq team.
 - adds `Game.compute()` method to the `shapiq.Game` class to compute game values without changing the state of the game object. The compute method also introduces a `shapiq.utils.sets.generate_interaction_lookup_from_coalitions()` utility method which creates an interaction lookup dict from an array of coalitions. [#397](https://github.com/mmschlk/shapiq/pull/397)
 - streamlines the creation of network plots and graph plots which now uses the same backend. The network plot via `shapiq.network_plot()` or `InteractionValues.plot_network()` is now a special case of the `shapiq.si_graph_plot()` and `InteractionValues.plot_si_graph()`. This allows to create more beautiful plots and easier maintenance in the future. [#349](https://github.com/mmschlk/shapiq/pull/349)
 
-#### Testing, Code-Quality and Documentation
+### Testing, Code-Quality and Documentation
 - activates ``"ALL"`` rules in ``ruff-format`` configuration to enforce stricter code quality checks and addressed around 500 (not automatically solvable) issues in the code base. [#391](https://github.com/mmschlk/shapiq/pull/391)
 - improved the testing environment by adding a new fixture module containing mock `InteractionValues` objects to be used in the tests. This allows for more efficient and cleaner tests, as well as easier debugging of the tests  [#372](https://github.com/mmschlk/shapiq/pull/372)
 - removed check and error message if the ``index`` parameter is not in the list of available indices in the ``TabularExplainer`` since the type hints were replaced by Literals [#391](https://github.com/mmschlk/shapiq/pull/391)
@@ -304,12 +322,12 @@ Built with ❤️ by the shapiq team.
 - refactors the tests into ``tests_unit/`` and ``tests_integration/`` to better separate unit tests from integration tests. [#395](https://github.com/mmschlk/shapiq/pull/395)
 - adds new integration tests in ``tests/tests_integration/test_explainer_california_housing`` which compares the different explainers against ground-truth interaction values computed by ``shapiq.ExactComputer`` and interaction values stored on [disk](https://github.com/mmschlk/shapiq/tree/main/tests/data/interaction_values/california_housing) as a form of regression test. This test should help finding bugs in the future when the approximators, explainers, or exact computation are changed. [#395](https://github.com/mmschlk/shapiq/pull/395)
 
-#### Bug Fixes
+### Bug Fixes
 - fixed a bug in the `shapiq.waterfall_plot` function that caused the plot to not display correctly resulting in cutoff y_ticks. Additionally, the file was renamed from `watefall.py` to `waterfall.py` to match the function name [#377](https://github.com/mmschlk/shapiq/pull/377)
 - fixes a bug with `TabPFNExplainer`, where the model was not able to be used for predictions after it was explained. This was due to the model being fitted on a subset of features, which caused inconsistencies in the model's predictions after explanation. The fix includes that after each call to the `TabPFNImputer.value_function`, the tabpfn model is fitted on the whole dataset (without omitting features). This means that the original model can be used for predictions after it has been explained. [#396](https://github.com/mmschlk/shapiq/issues/396).
 - fixed a bug in computing `BII` or `BV` indices with `shapiq.approximator.MonteCarlo` approximators (affecting `SHAP-IQ`, `SVARM` and `SVARM-IQ`). All orders of BII should now be computed correctly. [#395](https://github.com/mmschlk/shapiq/pull/395)
 
-### v1.2.3 (2025-03-24)
+## v1.2.3 (2025-03-24)
 - substantially improves the runtime of all `Regression` approximators by a) a faster pre-computation of the regression matrices and b) a faster computation of the weighted least squares regression [#340](https://github.com/mmschlk/shapiq/issues/340)
 - removes `sample_replacements` parameter from `MarginalImputer` and removes the DeprecationWarning for it
 - adds a trivial computation to `TreeSHAP-IQ` for trees that use only one feature in the tree (this works for decision stumps or trees splitting on only one feature multiple times). In such trees, the computation is trivial as the whole effect of $\nu(N) - \nu(\emptyset)$ is all on the main effect of the single feature and there is no interaction effect. This expands on the fix in v1.2.1 [#286](https://github.com/mmschlk/shapiq/issues/286).
@@ -320,18 +338,18 @@ Built with ❤️ by the shapiq team.
 - adds the `RegressionFBII` approximator to estimate Faithful Banzhaf interactions via least squares regression [#333](https://github.com/mmschlk/shapiq/pull/333). Additionally, FBII support was introduced in TabularExplainer and MonteCarlo-Approximator.
 - adds a `RandomGame` class as part of `shapiq.games.benchmark` which always returns a random vector of integers between 0 and 100.
 
-### v1.2.2 (2025-03-11)
+## v1.2.2 (2025-03-11)
 - changes python support to 3.10-3.13 [#318](https://github.com/mmschlk/shapiq/pull/318)
 - fixes a bug that prohibited importing shapiq in environments without write access [#326](https://github.com/mmschlk/shapiq/issues/326)
 - adds `ExtraTreeRegressors` to supported models [#309](https://github.com/mmschlk/shapiq/pull/309)
 
-### v1.2.1 (2025-02-17)
+## v1.2.1 (2025-02-17)
 - fixes bugs regarding plotting [#315](https://github.com/mmschlk/shapiq/issues/315) and [#316](https://github.com/mmschlk/shapiq/issues/316)
 - fixes a bug with TreeExplainer and Trees that consist of only one feature [#286](https://github.com/mmschlk/shapiq/issues/286)
 - fixes SV init with explainer for permutation, svarm, kernelshap, and unbiased kernelshap [#319](https://github.com/mmschlk/shapiq/issues/319)
 - adds a progress bar to `explain_X()` [#324](https://github.com/mmschlk/shapiq/issues/324)
 
-### v1.2.0 (2025-01-15)
+## v1.2.0 (2025-01-15)
 - adds ``shapiq.TabPFNExplainer`` as a specialized version of the ``shapiq.TabularExplainer`` which offers a streamlined variant of the explainer for the TabPFN model [#301](https://github.com/mmschlk/shapiq/issues/301)
 - handles ``explainer.explain()`` now through a common interface for all explainer classes which now need to implement a ``explain_function()`` method
 - adds the baseline_value into the InteractionValues object's value storage for the ``()`` interaction if ``min_order=0`` (default usually) for all indices that are not ``SII```(SII has another baseline value) such that the values are efficient (sum up to the model prediction) without the awkward handling of the baseline_value attribute
@@ -346,20 +364,20 @@ Built with ❤️ by the shapiq team.
 - refactors game theory computations like `ExactComputer`, `MoebiusConverter`, `core`, among others to be more modular and flexible into the `game_theory` module [#258](https://github.com/mmschlk/shapiq/issues/258)
 - improves quality of the tests by adding many more semantic tests to the different interaction indices and computations [#285](https://github.com/mmschlk/shapiq/pull/285)
 
-### v1.1.1 (2024-11-13)
+## v1.1.1 (2024-11-13)
 
-#### Improvements and Ease of Use
+### Improvements and Ease of Use
 - adds a `class_index` parameter to `TabularExplainer` and `Explainer` to specify the class index to be explained for classification models [#271](https://github.com/mmschlk/shapiq/issues/271) (renames `class_label` parameter in TreeExplainer to `class_index`)
 - adds support for `PyTorch` models to `Explainer` [#272](https://github.com/mmschlk/shapiq/issues/272)
 - adds new tests comparing `shapiq` outputs for SVs with alues computed with `shap`
 - adds new tests for checking `shapiq` explainers with different types of models
 
-#### Bug Fixes
+### Bug Fixes
 - fixes a bug that `RandomForestClassifier` models were not working with the `TreeExplainer` [#273](https://github.com/mmschlk/shapiq/issues/273)
 
-### v1.1.0 (2024-11-07)
+## v1.1.0 (2024-11-07)
 
-#### New Features and Improvements
+### New Features and Improvements
 - adds computation of the Egalitarian Core (`EC`) and Egalitarian Least-Core (`ELC`) to the `ExactComputer` [#182](https://github.com/mmschlk/shapiq/issues/182)
 - adds `waterfall_plot` [#34](https://github.com/mmschlk/shapiq/issues/34) that visualizes the contributions of features to the model prediction
 - adds `BaselineImputer` [#107](https://github.com/mmschlk/shapiq/issues/107) which is now responsible for handling the `sample_replacements` parameter. Added a DeprecationWarning for the parameter in `MarginalImputer`, which will be removed in the next release.
@@ -372,7 +390,7 @@ Built with ❤️ by the shapiq team.
 - a `shapiq.Game` can now be called more intuitively with coalitions data types (tuples of int or str) and also allows to add `player_names` to the game at initialization [#183](https://github.com/mmschlk/shapiq/issues/183)
 - improve tests across the package
 
-#### Documentation
+### Documentation
 - adds a notebook showing how to use custom tree models with the `TreeExplainer` [#66](https://github.com/mmschlk/shapiq/issues/66)
 - adds a notebook show how to use the `shapiq.Game` API to create custom games [#184](https://github.com/mmschlk/shapiq/issues/184)
 - adds a notebook showing hot to visualize interactions [#252](https://github.com/mmschlk/shapiq/issues/252)
@@ -380,17 +398,17 @@ Built with ❤️ by the shapiq team.
 - adds a notebook for conducting data valuation [#190](https://github.com/mmschlk/shapiq/issues/190)
 - adds a notebook showcasing introducing the Core and how to compute it with `shapiq` [#191](https://github.com/mmschlk/shapiq/issues/191)
 
-#### Bug Fixes
+### Bug Fixes
 - fixes a bug with SIs not adding up to the model prediction because of wrong values in the empty set [#264](https://github.com/mmschlk/shapiq/issues/264)
 - fixes a bug that `TreeExplainer` did not have the correct baseline_value when using XGBoost models [#250](https://github.com/mmschlk/shapiq/issues/250)
 - fixes the force plot not showing and its baseline value
 
-### v1.0.1 (2024-06-05)
+## v1.0.1 (2024-06-05)
 
 - add `max_order=1` to `TabularExplainer` and `TreeExplainer`
 - fix `TreeExplainer.explain_X(..., n_jobs=2, random_state=0)`
 
-### v1.0.0 (2024-06-04)
+## v1.0.0 (2024-06-04)
 
 Major release of the `shapiq` Python package including (among others):
 

{shapiq-1.3.0 → shapiq-1.3.2}/pyproject.toml

@@ -84,8 +84,9 @@ ml = [
     "transformers",
     "scikit-image",
     "joblib",
-    "tensorflow; python_version < '3.13'",
-    "tf-keras; python_version < '3.13'",
+    # tf only for python < 3.13 and not windows
+    "tensorflow; python_version < '3.13' and platform_system != 'Windows'",
+    "tf-keras; python_version < '3.13' and platform_system != 'Windows'",
 ]
 
 [tool.pytest.ini_options]
@@ -106,7 +107,7 @@ ignore = [
     "E501",  # Line too long
     "N803",  # Variable X in function should be lowercase
     "N806",  # Variable X in function should be lowercase
-    "S301",  # exclude pickle restriction, atm. games are unpickled this will need to be fixed # TODO: must be fixed in the future
+    "S301",  # we will remove pickle in version 1.4.0 (https://github.com/mmschlk/shapiq/issues/413)
     "COM812",  # this is redundant with the formatter which anyways does this (must be excluded) in the future # TODO: add remove pickle calls and remove this exclusion
     "FIX002",  # we use TODOs atm to track potential code improvements  # TODO: add this in the future
     "PLR0913",  # Too many arguments are passed to function
@@ -150,6 +151,9 @@ exclude = [
 # Exclude a variety of commonly ignored directories.
 # Note to developers: If you add a new ignore at least put a comment next to it why it is ignored
 [tool.ruff.lint.per-file-ignores]
+"shapiq/typing.py" = [
+    "A005",  # we want to be similar to other libraries that also shadow typing
+]
 "tests/*.py" = [
     # "ALL",
     "S101", # we need asserts in tests
@@ -197,7 +201,10 @@ exclude = [
 "scripts/*.py" = [
     "INP", # imports can be different here
     "I002",  # script code does not have to import required modules
-    "PTH"  # in script code we use a lot of os, which is okay
+    "PTH",  # in script code we use a lot of os, which is okay
+    "T201",  # scripts can have print statements
+    "BLE001",  # scripts can have bare excepts
+    "TRY"
 ]
 
 [tool.ruff.lint.pydocstyle]
@@ -211,16 +218,23 @@ force-wrap-aliases = true
 no-lines-before = ["future"]
 required-imports = ["from __future__ import annotations"]
 
+[tool.pyright]
+include = ["shapiq"]
+exclude = ["tests", "docs", "benchmark", "scripts", "shapiq/plot"]
+pythonVersion = "3.10"
+
 [dependency-groups]
 test = [
     "pytest>=8.3.5",
     "pytest-cov>=6.0.0",
     "pytest-xdist>=3.6.1",
     "pytest-randomly",
+    "packaging>=24.2",
 ]
 lint = [
     "ruff>=0.11.2",
     "pre-commit>=4.2.0",
+    "pyright>=1.1.402",
 ]
 docs = [
     "sphinx>=8.0.0",
@@ -233,6 +247,10 @@ docs = [
     "nbconvert",
     "nbsphinx",
     "commonmark",  # Markdown parser and renderer
+    # TODO(mmschlk): remove the pin in ipython when we drop python 3.10 support and pin to
+    # ipython>=9.0.0, since ipython==8.7.0 introduces a bug with parsing notebooks also discussed
+    # here: https://github.com/spatialaudio/nbsphinx/issues/24
+    "ipython<8.7.0",
 ]
 dev = [
     "build>=1.2.2.post1",

{shapiq-1.3.0 → shapiq-1.3.2}/shapiq/__init__.py

@@ -4,7 +4,7 @@ shapiq is a library creating explanations for machine learning models based on
 the well established Shapley value and its generalization to interaction.
 """
 
-__version__ = "1.3.0"
+__version__ = "1.3.2"
 
 # approximator classes
 from .approximator import (
@@ -64,6 +64,7 @@ from .interaction_values import InteractionValues
 # plotting functions
 from .plot import (
     bar_plot,
+    beeswarm_plot,
     force_plot,
     network_plot,
     sentence_plot,
@@ -125,6 +126,7 @@ __all__ = [
     "waterfall_plot",
     "sentence_plot",
     "upset_plot",
+    "beeswarm_plot",
     # public utils
     "powerset",
     "get_explicit_subsets",

{shapiq-1.3.0 → shapiq-1.3.2}/shapiq/explainer/tabpfn.py

@@ -25,16 +25,14 @@ class TabPFNExplainer(TabularExplainer):
     """The TabPFN explainer as the main interface for the shapiq package.
 
     The ``TabPFNExplainer`` class is the dedicated interface for the ``shapiq`` package and
-    TabPFN [Hof25]_ models such as the ``TabPFNClassifier`` and ``TabPFNRegressor``. The explainer
-    does not rely on classical imputation methods and is optimized for TabPFN's in-context learning
-    approach. The explanation paradigm for TabPFN is described in Rundel et al. (2024) [Run24]_. In
-    essence the explainer is a wrapper around the ``TabularExplainer`` class and uses the same API.
-
+    TabPFN :footcite:t:`Hollmann.2025` models such as the ``TabPFNClassifier`` and
+    ``TabPFNRegressor``. The explainer does not rely on classical imputation methods and is
+    optimized for TabPFN's in-context learning approach. The explanation paradigm for TabPFN is
+    described in :footcite:t:`Rundel.2024`. In essence the explainer is a wrapper around the
+    :class:~`shapiq.explainer.tabular.TabularExplainer` class and uses the same API.
 
     References:
-        .. [Run24] Rundel, D., Kobialka, J., von Crailsheim, C., Feurer, M., Nagler, T., Rügamer, D. (2024). Interpretable Machine Learning for TabPFN. In: Longo, L., Lapuschkin, S., Seifert, C. (eds) Explainable Artificial Intelligence. xAI 2024. Communications in Computer and Information Science, vol 2154. Springer, Cham. https://doi.org/10.1007/978-3-031-63797-1_23
-        .. [Hol25] Hollmann, N., Müller, S., Purucker, L. et al. Accurate predictions on small data with a tabular foundation model. Nature 637, 319-326 (2025). https://doi.org/10.1038/s41586-024-08328-6
-
+        .. footbibliography::
     """
 
     def __init__(

{shapiq-1.3.0 → shapiq-1.3.2}/shapiq/explainer/tabular.py

@@ -5,8 +5,6 @@ from __future__ import annotations
 from typing import TYPE_CHECKING, Any, Literal
 from warnings import warn
 
-from overrides import overrides
-
 from shapiq.explainer.base import Explainer
 from shapiq.interaction_values import InteractionValues, finalize_computed_interactions
 
@@ -165,7 +163,6 @@ class TabularExplainer(Explainer):
             approximator, self._index, self._max_order, self._n_features, random_state
         )
 
-    @overrides
     def explain_function(
         self,
         x: np.ndarray,

{shapiq-1.3.0 → shapiq-1.3.2}/shapiq/explainer/tree/base.py

@@ -3,11 +3,15 @@
 from __future__ import annotations
 
 from dataclasses import dataclass
+from typing import TYPE_CHECKING
 
 import numpy as np
 
 from .utils import compute_empty_prediction
 
+if TYPE_CHECKING:
+    from numpy.typing import NDArray
+
 
 @dataclass
 class TreeModel:
@@ -52,22 +56,22 @@ class TreeModel:
 
     """
 
-    children_left: np.ndarray[int]
-    children_right: np.ndarray[int]
-    features: np.ndarray[int]
-    thresholds: np.ndarray[float]
-    values: np.ndarray[float]
-    node_sample_weight: np.ndarray[float]
-    empty_prediction: float | None = None
-    leaf_mask: np.ndarray[bool] | None = None
-    n_features_in_tree: int | None = None
-    max_feature_id: int | None = None
-    feature_ids: set | None = None
-    root_node_id: int | None = None
-    n_nodes: int | None = None
-    nodes: np.ndarray[int] | None = None
-    feature_map_original_internal: dict[int, int] | None = None
-    feature_map_internal_original: dict[int, int] | None = None
+    children_left: NDArray[np.int_]
+    children_right: NDArray[np.int_]
+    features: NDArray[np.int_]
+    thresholds: NDArray[np.floating]
+    values: NDArray[np.floating]
+    node_sample_weight: NDArray[np.floating]
+    empty_prediction: float = None  # type: ignore[assignment]
+    leaf_mask: NDArray[np.bool_] = None  # type: ignore[assignment]
+    n_features_in_tree: int = None  # type: ignore[assignment]
+    max_feature_id: int = None  # type: ignore[assignment]
+    feature_ids: set = None  # type: ignore[assignment]
+    root_node_id: int = None  # type: ignore[assignment]
+    n_nodes: int = None  # type: ignore[assignment]
+    nodes: NDArray[np.int_] = None  # type: ignore[assignment]
+    feature_map_original_internal: dict[int, int] = None  # type: ignore[assignment]
+    feature_map_internal_original: dict[int, int] = None  # type: ignore[assignment]
     original_output_type: str = "raw"  # not used at the moment
 
     def compute_empty_prediction(self) -> None:
@@ -187,7 +191,7 @@ class TreeModel:
             else:
                 node = self.children_right[node]
             is_leaf = self.leaf_mask[node]
-        return self.values[node]
+        return float(self.values[node])
 
 
 @dataclass

{shapiq-1.3.0 → shapiq-1.3.2}/shapiq/explainer/tree/conversion/edges.py

@@ -2,22 +2,27 @@
 
 from __future__ import annotations
 
+from typing import TYPE_CHECKING
+
 import numpy as np
 from scipy.special import binom
 
 from shapiq.explainer.tree.base import EdgeTree
 
+if TYPE_CHECKING:
+    from numpy.typing import NDArray
+
 
 def create_edge_tree(
-    children_left: np.ndarray[int],
-    children_right: np.ndarray[int],
-    features: np.ndarray[int],
-    node_sample_weight: np.ndarray[float],
-    values: np.ndarray[float],
+    children_left: NDArray[np.int_],
+    children_right: NDArray[np.int_],
+    features: NDArray[np.int_],
+    node_sample_weight: NDArray[np.floating],
+    values: NDArray[np.floating],
     n_nodes: int,
     n_features: int,
     max_interaction: int,
-    subset_updates_pos_store: dict[int, dict[int, np.ndarray[int]]],
+    subset_updates_pos_store: dict[int, dict[int, NDArray[np.int_]]],
 ) -> EdgeTree:
     """Extracts edge information recursively from the tree information.
 

{shapiq-1.3.0 → shapiq-1.3.2}/shapiq/explainer/tree/utils.py

@@ -2,15 +2,21 @@
 
 from __future__ import annotations
 
+from typing import TYPE_CHECKING
+
 import numpy as np
 
+if TYPE_CHECKING:
+    from numpy.typing import NDArray
+
+
 __all__ = ["compute_empty_prediction", "get_conditional_sample_weights"]
 
 
 def get_conditional_sample_weights(
-    sample_count: np.ndarray[int],
-    parent_array: np.ndarray[int],
-) -> np.ndarray[float]:
+    sample_count: NDArray[np.int_],
+    parent_array: NDArray[np.int_],
+) -> NDArray[np.floating]:
     """Get the conditional sample weights for a tree at each decision node.
 
     The conditional sample weights are the probabilities of going left or right at each decision
@@ -41,8 +47,8 @@ def get_conditional_sample_weights(
 
 
 def compute_empty_prediction(
-    leaf_values: np.ndarray[float],
-    leaf_sample_weights: np.ndarray[float],
+    leaf_values: NDArray[np.floating],
+    leaf_sample_weights: NDArray[np.floating],
 ) -> float:
     """Compute the empty prediction of a tree model.
 
@@ -56,4 +62,4 @@ def compute_empty_prediction(
         The empty prediction of the tree model.
 
     """
-    return np.sum(leaf_values * leaf_sample_weights) / np.sum(leaf_sample_weights)
+    return float(np.sum(leaf_values * leaf_sample_weights) / np.sum(leaf_sample_weights))