moabb.paradigms.base.BaseParadigm#
- class moabb.paradigms.base.BaseParadigm(filters, events: List[str] | None = None, tmin=0.0, tmax=None, baseline=None, channels=None, resample=None, overlap=None, scorer=None)[source]#
Base class for paradigms.
- Parameters:
events (list of str or None) – Events to use for epoching. If None, default to all events defined in the dataset. Defaults to
None.scorer (str, callable, or None) – Sklearn-compatible string or a compatible sklearn scorer. If None, and n_classes==2 use the roc_auc, else use accuracy. Defaults to
None.
- abstract property scoring#
Property that defines scoring metric (e.g. ROC-AUC or accuracy or f-score), given as a sklearn-compatible string or a compatible sklearn scorer.
Examples using moabb.paradigms.base.BaseParadigm#
Tutorial 5: Combining Multiple Datasets into a Single Dataset
Tutorial 5: Combining Multiple Datasets into a Single Dataset
Tutorial: Within-Session Splitting on Real MI Dataset
Tutorial: Within-Session Splitting on Real MI Dataset
Using X y data (epoched data) instead of continuous signal
Using X y data (epoched data) instead of continuous signal
