meeg_utils.steps.AutoReject

class meeg_utils.steps.AutoReject(method='local', *, n_interpolate=None, consensus=None, cv=None, thresh_method='bayesian_optimization', random_state=42, n_jobs=1)

Reject or repair bad epochs with thresholds learned from the data.

Wraps autoreject (Jas et al., 2017, NeuroImage 159:417):

• "local": autoreject.AutoReject learns a peak-to-peak threshold per channel by cross-validation; in each epoch the worst channels are interpolated, and epochs with too many bad channels are dropped. Needs sensor positions.

• "global": autoreject.get_rejection_threshold() learns one peak-to-peak threshold per channel type; epochs exceeding it are dropped.

Parameters:

• method ({"local", "global"}) – See above.

• n_interpolate (list of int | None) – Local: candidate numbers of channels to interpolate per epoch (None: autoreject’s default, 1, 4 and 32).

• consensus (list of float | None) – Local: candidate fractions of bad channels that make an epoch bad (None: autoreject’s default, 0 to 1 in steps of 0.1).

• cv (int) – Cross-validation folds (autoreject defaults: 10 local, 5 global).

• thresh_method ({"bayesian_optimization", "random_search"}) – Local: how thresholds are searched.

• random_state (int | None) – Seed.

• n_jobs (int) – Parallel jobs.

reject_log_

Bad epochs and channel labels on the fitted data.

Type:

autoreject.RejectLog

thresholds_

Learned thresholds: per channel (local) or per channel type (global).

Type:

dict

qc_

n_epochs, n_dropped, fraction_dropped, n_interpolated (channels interpolated per epoch, mean) and the most interpolated channels.

Type:

dict

Notes

Figures (plot()): "reject_log" (epochs x channels: bad, interpolated, dropped) and "thresholds".

__init__(method='local', *, n_interpolate=None, consensus=None, cv=None, thresh_method='bayesian_optimization', random_state=42, n_jobs=1)

Methods

__init__([method, n_interpolate, consensus, ...])
fit(inst[, y, system])	Learn the step's state from the data.
fit_transform(inst[, y, system, copy])	Fit the step on the data and transform the same data.
get_metadata_routing()	Get metadata routing of this object.
get_params([deep])	Get parameters for this estimator.
plot([kind, inst])	Draw quality-control figures.
set_fit_request(*[, inst, system])	Configure whether metadata should be requested to be passed to the fit method.
set_params(**params)	Set the parameters of this estimator.
set_transform_request(*[, copy, inst])	Configure whether metadata should be requested to be passed to the transform method.
transform(inst, *[, copy])	Apply the fitted step to the data.

Attributes

accepts	Data types the step accepts.
adds_annotations	Whether the step may add BAD_ annotations (existing ones are kept).
changes_channels	Whether the step may add, drop or reorder channels.
changes_times	Whether the step may change the time axis (e.g. resampling, cropping).
drops_epochs	Whether the step may drop epochs (e.g. artifact rejection).
plot_kinds	kind -> whether it needs data (inst).
returns	Data type the step returns; None means the same type as its input.
systems	Acquisition systems the step applies to; None means all systems.

accepts: ClassVar[tuple[type, ...]] = (<class 'mne.epochs.BaseEpochs'>,)

Data types the step accepts.

drops_epochs: ClassVar[bool] = True

Whether the step may drop epochs (e.g. artifact rejection).

plot_kinds: ClassVar[dict[str, bool]] = {'reject_log': False, 'thresholds': False}

kind -> whether it needs data (inst). Each kind is drawn by a _plot_<kind>(inst, **kwargs) method.

Type:

Figures the object can draw once fitted