.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "auto_examples/visualization/plot_shapley_values.py"
.. LINE NUMBERS ARE GIVEN BELOW.

.. only:: html

    .. note::
        :class: sphx-glr-download-link-note

        :ref:`Go to the end <sphx_glr_download_auto_examples_visualization_plot_shapley_values.py>`
        to download the full example code.

.. rst-class:: sphx-glr-example-title

.. _sphx_glr_auto_examples_visualization_plot_shapley_values.py:

Computing Shapley Values.
=========================

A minimal example showing how to compute exact Shapley values for a small
cooperative game using :class:`~shapiq.ExactComputer`.

.. GENERATED FROM PYTHON SOURCE LINES 7-15

.. code-block:: Python


    from __future__ import annotations

    import matplotlib.pyplot as plt
    import numpy as np

    import shapiq








.. GENERATED FROM PYTHON SOURCE LINES 16-20

Define a Simple Game
--------------------
We define a 4-player weighted voting game as a callable.
The game value is 1 if the coalition's total weight exceeds a threshold, else 0.

.. GENERATED FROM PYTHON SOURCE LINES 20-30

.. code-block:: Python


    weights = np.array([0.4, 0.3, 0.2, 0.1])
    threshold = 0.5


    def voting_game(coalitions: np.ndarray) -> np.ndarray:
        """Return 1 if coalition weight exceeds the threshold, else 0."""
        return (coalitions @ weights > threshold).astype(float)









.. GENERATED FROM PYTHON SOURCE LINES 31-35

Compute Exact Shapley Values
----------------------------
:class:`~shapiq.ExactComputer` exhaustively evaluates all 2^n coalitions to
compute exact interaction values. It accepts any callable game directly.

.. GENERATED FROM PYTHON SOURCE LINES 35-39

.. code-block:: Python


    computer = shapiq.ExactComputer(voting_game, n_players=4)
    sv = computer(index="SV", order=1)








.. GENERATED FROM PYTHON SOURCE LINES 40-42

Visualize with a Bar Plot
-------------------------

.. GENERATED FROM PYTHON SOURCE LINES 42-52

.. code-block:: Python


    fig, ax = plt.subplots(figsize=(5, 3))
    ax.bar(range(4), [sv[(i,)] for i in range(4)], color="#5b9bd5")
    ax.set_xticks(range(4))
    ax.set_xticklabels([f"Player {i}" for i in range(4)])
    ax.set_ylabel("Shapley Value")
    ax.set_title("Shapley Values for a Weighted Voting Game")
    ax.axhline(0, color="black", linewidth=0.8, linestyle="--")
    plt.tight_layout()
    plt.show()



.. image-sg:: /auto_examples/visualization/images/sphx_glr_plot_shapley_values_001.png
   :alt: Shapley Values for a Weighted Voting Game
   :srcset: /auto_examples/visualization/images/sphx_glr_plot_shapley_values_001.png
   :class: sphx-glr-single-img






.. rst-class:: sphx-glr-timing

   **Total running time of the script:** (0 minutes 0.051 seconds)


.. _sphx_glr_download_auto_examples_visualization_plot_shapley_values.py:

.. only:: html

  .. container:: sphx-glr-footer sphx-glr-footer-example

    .. container:: sphx-glr-download sphx-glr-download-jupyter

      :download:`Download Jupyter notebook: plot_shapley_values.ipynb <plot_shapley_values.ipynb>`

    .. container:: sphx-glr-download sphx-glr-download-python

      :download:`Download Python source code: plot_shapley_values.py <plot_shapley_values.py>`

    .. container:: sphx-glr-download sphx-glr-download-zip

      :download:`Download zipped: plot_shapley_values.zip <plot_shapley_values.zip>`