overconfidence

pycalib.scoring.overconfidence(y, p_pred)

Computes the overconfidence of a classifier.

Computes the empirical overconfidence of a classifier on a test sample by evaluating the average confidence on the false predictions.

Parameters

• y (array-like) – Ground truth labels

• p_pred (array-like) – Array of confidence estimates

Returns

Overconfidence

Return type

float