tick.metrics

This small module gives some useful metrics computation, for now only tools to compute the FDP (False Discover Proportion) and the recall for the estimation of the support of the weights of a model.

support_fdp(x_truth, x[, eps])

Computes the False Discovery Proportion for selecting the support of x_truth using x, namely the proportion of false positive among all detected positives, given by FP / (FP + TP).

support_recall(x_truth, x[, eps])

Computes proportion of true positives (TP) among the number ground truth positives (namely TP + FN, where FN is the number of false negatives), hence TP / (TP + FN).