.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "auto_examples/model_evaluation/plot_custom_metrics.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_model_evaluation_plot_custom_metrics.py>`
        to download the full example code.

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

.. _sphx_glr_auto_examples_model_evaluation_plot_custom_metrics.py:


.. _example_custom_metrics:

=======================================================
Adapt skore to your use-case by adding your own metrics
=======================================================

By default, :meth:`~skore.EstimatorReport.metrics.summarize` reports a curated
set of metrics for your ML task. In practice you often need domain-specific
scores: a business cost function, a custom fairness measure, an F-beta with a
particular beta, etc.

This example walks through how to register such metrics with
:meth:`~skore.EstimatorReport.metrics.add` so they are computed and displayed
alongside the built-in ones.

.. GENERATED FROM PYTHON SOURCE LINES 19-21

Setting up a classification problem
===================================

.. GENERATED FROM PYTHON SOURCE LINES 23-29

.. code-block:: Python

    import skore
    from sklearn.datasets import load_breast_cancer
    from sklearn.linear_model import LogisticRegression

    X, y = load_breast_cancer(return_X_y=True)








.. GENERATED FROM PYTHON SOURCE LINES 30-33

We create an :class:`~skore.EstimatorReport` through :func:`~skore.evaluate`
using a simple train/test split. ``pos_label=1`` marks the *malignant* class
as the positive class.

.. GENERATED FROM PYTHON SOURCE LINES 35-39

.. code-block:: Python

    report = skore.evaluate(
        LogisticRegression(max_iter=10_000), X, y, pos_label=1, splitter=0.2
    )








.. GENERATED FROM PYTHON SOURCE LINES 40-41

Let's look at the default metrics:

.. GENERATED FROM PYTHON SOURCE LINES 41-43

.. code-block:: Python

    report.metrics.summarize().frame()





.. rst-class:: sphx-glr-script-out

 .. code-block:: none


    metric
    accuracy        0.947368
    precision       0.984127
    recall          0.925373
    roc_auc         0.993649
    log_loss        0.110247
    brier_score     0.036154
    fit_time        0.327117
    predict_time    0.000175
    Name: LogisticRegression, dtype: float64



.. GENERATED FROM PYTHON SOURCE LINES 44-53

Adding a plain callable
=======================

Any function with the signature ``(estimator, X, y, **kwargs) -> score`` can be
registered with :meth:`~skore.EstimatorReport.metrics.add`. The function name
is used as the metric name by default.
If your metric can be expressed as a callable with the signature
``(y_true, y_pred, **kwargs) -> score``, then you can use sklearn's ``make_scorer``
utility function to convert it.

.. GENERATED FROM PYTHON SOURCE LINES 56-68

.. code-block:: Python

    from sklearn.metrics import make_scorer


    def specificity(y_true, y_pred):
        """Proportion of true negatives among actual negatives."""
        tn = ((y_true == 0) & (y_pred == 0)).sum()
        fp = ((y_true == 0) & (y_pred == 1)).sum()
        return tn / (tn + fp)


    report.metrics.add(make_scorer(specificity))








.. GENERATED FROM PYTHON SOURCE LINES 69-71

.. code-block:: Python

    report.metrics.summarize().frame()





.. rst-class:: sphx-glr-script-out

 .. code-block:: none


    metric
    specificity     0.978723
    accuracy        0.947368
    precision       0.984127
    recall          0.925373
    roc_auc         0.993649
    log_loss        0.110247
    brier_score     0.036154
    fit_time        0.327117
    predict_time    0.000175
    Name: LogisticRegression, dtype: float64



.. GENERATED FROM PYTHON SOURCE LINES 72-74

``specificity`` now appears alongside the built-in metrics. It can also be computed
individually using the :meth:`~skore.EstimatorReport.metrics.get` method:

.. GENERATED FROM PYTHON SOURCE LINES 74-76

.. code-block:: Python

    report.metrics.get("specificity")





.. rst-class:: sphx-glr-script-out

 .. code-block:: none


    0.9787234042553191



.. GENERATED FROM PYTHON SOURCE LINES 77-79

Further, if the metric name is a valid identifier, the metric is also exposed as a
method:

.. GENERATED FROM PYTHON SOURCE LINES 79-81

.. code-block:: Python

    report.metrics.specificity()





.. rst-class:: sphx-glr-script-out

 .. code-block:: none


    0.9787234042553191



.. GENERATED FROM PYTHON SOURCE LINES 82-91

Passing extra keyword arguments
===============================

If your metric needs extra data at scoring time (e.g. sample-level amounts,
a cost matrix, ...), they can be passed as keyword arguments to
:meth:`~skore.EstimatorReport.metrics.add`; they will be forwarded to the
metric function when it is computed.
Alternatively, if the metric takes ``y_true`` and ``y_pred``, the keyword
arguments can be passed to ``make_scorer``:

.. GENERATED FROM PYTHON SOURCE LINES 93-100

.. code-block:: Python

    from sklearn.metrics import fbeta_score, make_scorer

    f2_scorer = make_scorer(fbeta_score, beta=2, pos_label=1)
    report.metrics.add(f2_scorer, name="f2")

    report.metrics.summarize().frame()





.. rst-class:: sphx-glr-script-out

 .. code-block:: none


    metric
    f2              0.936556
    specificity     0.978723
    accuracy        0.947368
    precision       0.984127
    recall          0.925373
    roc_auc         0.993649
    log_loss        0.110247
    brier_score     0.036154
    fit_time        0.327117
    predict_time    0.000175
    Name: LogisticRegression, dtype: float64



.. GENERATED FROM PYTHON SOURCE LINES 101-106

Cherry-picking metrics to display
==================================

Once registered, custom metrics can be selected by name in
:meth:`~skore.EstimatorReport.metrics.summarize`:

.. GENERATED FROM PYTHON SOURCE LINES 108-110

.. code-block:: Python

    report.metrics.summarize(metric=["specificity", "f2"]).frame()





.. rst-class:: sphx-glr-script-out

 .. code-block:: none


    metric
    specificity    0.978723
    f2             0.936556
    Name: LogisticRegression, dtype: float64



.. GENERATED FROM PYTHON SOURCE LINES 111-112

Selecting ``data_source="both"`` lets you compare train vs. test in one call:

.. GENERATED FROM PYTHON SOURCE LINES 114-116

.. code-block:: Python

    report.metrics.summarize(metric=["specificity", "f2"], data_source="both").frame()






.. raw:: html

    <div class="output_subarea output_html rendered_html output_result">
    <div>
    <style scoped>
        .dataframe tbody tr th:only-of-type {
            vertical-align: middle;
        }

        .dataframe tbody tr th {
            vertical-align: top;
        }

        .dataframe thead th {
            text-align: right;
        }
    </style>
    <table border="1" class="dataframe">
      <thead>
        <tr style="text-align: right;">
          <th></th>
          <th>LogisticRegression (train)</th>
          <th>LogisticRegression (test)</th>
        </tr>
        <tr>
          <th>metric</th>
          <th></th>
          <th></th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th>specificity</th>
          <td>0.933333</td>
          <td>0.978723</td>
        </tr>
        <tr>
          <th>f2</th>
          <td>0.975945</td>
          <td>0.936556</td>
        </tr>
      </tbody>
    </table>
    </div>
    </div>
    <br />
    <br />

.. GENERATED FROM PYTHON SOURCE LINES 117-122

Using a different response method
==================================

By default, callables receive the output of ``estimator.predict(X)``. If your
metric needs probabilities instead, set ``response_method="predict_proba"``.

.. GENERATED FROM PYTHON SOURCE LINES 124-135

.. code-block:: Python

    import numpy as np


    def mean_confidence(y_true, y_proba):
        """Average predicted probability assigned to the true class."""
        return np.where(y_true == 1, y_proba[:, 1], y_proba[:, 0]).mean()


    report.metrics.add(make_scorer(mean_confidence, response_method="predict_proba"))

    report.metrics.summarize(metric="mean_confidence").frame()




.. rst-class:: sphx-glr-script-out

 .. code-block:: none


    metric
    mean_confidence    0.931087
    Name: LogisticRegression, dtype: float64




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

   **Total running time of the script:** (0 minutes 0.380 seconds)


.. _sphx_glr_download_auto_examples_model_evaluation_plot_custom_metrics.py:

.. only:: html

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

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

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

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

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

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

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


.. only:: html

 .. rst-class:: sphx-glr-signature

    `Gallery generated by Sphinx-Gallery <https://sphinx-gallery.github.io>`_