holisticai.bias.metrics.clustering_bias_metrics

holisticai.bias.metrics.clustering_bias_metrics(group_a, group_b, y_pred, data=None, centroids=None, metric_type='equal_outcome')

Clustering bias metrics batch computation

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

Parameters

group_aarray-like

Group membership vector (binary)

group_barray-like

Group membership vector (binary)

y_predarray-like

Cluster predictions (categorical)

datamatrix-like, optional

Data matrix of shape (num_inst, dim)

centroidsmatrix-like, optional

Centroids (centers)

metric_typestr, optional

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

Returns

pandas DataFrame

Metrics | Values | Reference