mne.simulation.metrics.roc_auc_score#

mne.simulation.metrics.roc_auc_score(stc_true, stc_est, per_sample=True)[source]#

Compute ROC AUC between 2 source estimates.

ROC stands for receiver operating curve and AUC is Area under the curve. When computing this metric the stc_true must be thresholded as any non-zero value will be considered as a positive.

The ROC-AUC metric is computed between amplitudes of the source estimates, i.e. after taking the absolute values.

Parameters:
stc_trueinstance of (Vol|Mixed)SourceEstimate

The source estimates containing correct values.

stc_estinstance of (Vol|Mixed)SourceEstimate

The source estimates containing estimated values e.g. obtained with a source imaging method.

per_samplebool

If True the metric is computed for each sample separately. If False, the metric is spatio-temporal.

Returns:
metricfloat | array, shape (n_times,)

The metric. float if per_sample is False, else array with the values computed for each time point.

Notes

New in v1.2.