autoreject.get_rejection_threshold¶

autoreject.get_rejection_threshold(epochs, decim=1, random_state=None, ch_types=None, cv=5, verbose=True)[source]¶

Compute global rejection thresholds.

Parameters

epochsmne.Epochs object

The epochs from which to estimate the epochs dictionary

decimint

The decimation factor: Increment for selecting every nth time slice.

random_stateint seed, RandomState instance, or None (default)

The seed of the pseudo random number generator to use.

ch_typesstr | list of str | None

The channel types for which to find the rejection dictionary. e.g., [‘mag’, ‘grad’]. If None, the rejection dictionary will have keys [‘mag’, ‘grad’, ‘eeg’, ‘eog’, ‘hbo’, ‘hbr’].

cva scikit-learn cross-validation object

Defaults to cv=5

verbosebool

The verbosity of progress messages. If False, suppress all output messages.

Returns

rejectdict

The rejection dictionary with keys as specified by ch_types.

Notes

Sensors marked as bad by user will be excluded when estimating the rejection dictionary.