bedroc_score#

skfp.metrics.bedroc_score(y_true: ndarray | list[int], y_score: ndarray | list[float], alpha: float = 20) → float#

Boltzmann-enhanced discrimination of ROC (BEDROC).

A normalized alternative to Robust Initial Enhancement (RIE), scaled to have values in range [0, 1]. alpha is directly passed to underlying RIE function, and is roughly equivalent to 1 / fraction from enrichment factor (EF). See [1] [2] for details.

Defined as:

\[BEDROC(\alpha) = \frac{RIE(\alpha) - RIE_{min}(\alpha)}{RIE_{max}(\alpha) - RIE_{min}(\alpha)}\]
Parameters:

  • y_true (array-like of shape (n_samples,)) – Ground truth (correct) target values.

  • y_score (array-like of shape (n_samples,)) – Target scores, e.g. probability of the positive class, or similarities to active compounds.

  • alpha (float, default=20) – Exponential weight, roughly equivalent to 1 / fraction from EF.

References

Returns:

score – BEDROC value.

Return type:

float

Examples

>>> import numpy as np
>>> from skfp.metrics import bedroc_score
>>> y_true = [0, 0, 1]
>>> y_score = [0.1, 0.2, 0.7]
>>> bedroc_score(y_true, y_score)  
0.9999999999999999