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_sample
bool
If True the metric is computed for each sample separately. If False, the metric is spatio-temporal.
- Returns:
Notes
New in version 1.2.