fairlearn.postprocessing.plot_threshold_optimizer

fairlearn.postprocessing.plot_threshold_optimizer(threshold_optimizer, ax=None, show_plot=True)

Plot the chosen solution of the threshold optimizer.

For ThresholdOptimizer objects that have their constraint set to demographic_parity this will result in a selection/error curve plot. For ThresholdOptimizer objects that have their constraint set to equalized_odds this will result in a ROC curve plot.

Added in version 0.4.5.

Parameters:

• threshold_optimizer (ThresholdOptimizer) – The ThresholdOptimizer instance for which the results should be illustrated.

• ax (matplotlib.axes.Axes, default = None) – A custom matplotlib.axes.Axes object to use for the plots.

• show_plot (bool, default = True) – Whether or not the generated plot should be shown, default True

Raises:

• ValueError – If threshold_optimizer is not a ThresholdOptimizer.

• sklearn.exceptions.NotFittedError – If threshold_optimizer has not been fitted.

• RuntimeError – If matplotlib is not installed.

Gallery examples

Passing pipelines to mitigation techniques

Passing pipelines to mitigation techniques