fairscoring.metrics
===================

.. py:module:: fairscoring.metrics

.. autoapi-nested-parse::

   A collection fairness metrics to measure the bias of scores.

   The package consists of multiple classes that cover different fairness concepts and distance metrics.
   A concrete fairness metric is an instance of these classes with a concrete parametrization.


   There are recommended **default instances** are already included:

   =========================  =========================  =========================================
   Metric                     Bias                       Class
   =========================  =========================  =========================================
   :const:`bias_metric_cal`   Calibration Bias           :class:`~.calibration.CalibrationMetric`
   :const:`bias_metric_eo`    Equal Opportunity Bias     :class:`~.integral.WassersteinMetric`
   :const:`bias_metric_pe`    Predictive Equality Bias   :class:`~.integral.WassersteinMetric`
   =========================  =========================  =========================================

   .. versionchanged:: 0.2.0
      The ``bias_`` prefixed constants are now prefixed by ``bias_metric_``



Submodules
----------

.. toctree::
   :maxdepth: 1

   /autoapi/fairscoring/metrics/base/index
   /autoapi/fairscoring/metrics/calibration/index
   /autoapi/fairscoring/metrics/integral/index
   /autoapi/fairscoring/metrics/roc/index