holisticai.bias.metrics.multiclass_bias_metrics

holisticai.bias.metrics.multiclass_bias_metrics(p_attr, y_pred, y_true, groups=None, classes=None, metric_type='equal_outcome')

Multiclass bias metrics batch computation

This function computes all the relevant multiclass bias metrics, and displays them as a pandas dataframe.

Parameters

p_attrarray-like

Multiclass protected attribute vector

y_predarray-like

Regression predictions vector

y_truenumpy array

Regression target vector

groupslist, optional

Unique groups from p_attr in order

classeslist, optional

The unique output classes in order

metric_typestr, optional

Specifies which metrics we compute: ‘both’, ‘equal_outcome’ or ‘equal_opportunity’

Returns

pandas DataFrame

Metrics | Values | Reference