dataeval.metrics.estimators

Estimators calculate performance bounds and the statistical distance between datasets.

Output Classes

BEROutput

Output class for ber() estimator metric.

ClustererOutput

Output class for clusterer().

DivergenceOutput

Output class for divergence() estimator metric.

UAPOutput

Output class for uap() estimator metric.

Functions

ber(embeddings, labels[, k, method])

An estimator for Multi-class Bayes error rate using FR or KNN test statistic basis.

clusterer(data)

Uses hierarchical clustering on the flattened data and returns clustering

divergence(emb_a, emb_b[, method])

Calculates the divergence and any errors between the datasets.

uap(labels, scores)

FR Test Statistic based estimate of the empirical mean precision for the upperbound average precision.