holisticai.bias.metrics.statistical_parity_auc

holisticai.bias.metrics.statistical_parity_auc(group_a, group_b, y_pred)

Statistical parity (AUC)

This function computes the area under the statistical parity versus threshold curve.

Interpretation

A value of 0 is desired. Values below 0.075 are considered acceptable.

Parameters

group_aarray-like

Group membership vector (binary)

group_barray-like

Group membership vector (binary)

y_predarray-like

Predictions vector (regression)

Returns

float

statistical parity (AUC)

Examples

>>> import numpy as np
>>> from holisticai.bias.metrics import statistical_parity_auc
>>> group_a = np.array([1] * 50 + [0] * 50)
>>> group_b = np.array([0] * 50 + [1] * 50)
>>> y_pred = np.concatenate((np.linspace(-1, 1, 50), np.linspace(-1, 1, 50) ** 3))
>>> statistical_parity_auc(group_a, group_b, y_pred)
0.12106666666666668