API

This is the application programming interface (API) reference for classes (CamelCase names) and functions (underscore_case names) of MNE-ICALabel.

Most-used function

The most commonly used function is mne_icalabel.label_components() which takes an mne instance (mne.io.Raw, mne.Epochs) and its ICA decomposition to label the components using the specified method/model.

label_components(inst, ica, method)

Automatically label the ICA components with the selected method.

Models

ICLabel

iclabel.html

Features

On top of the available models, mne-icalabel provides a set of functions to extract features from ICA instance and Raw / Epochs instances using MNE-Python. Those features can then be used to train new models.

get_topomaps(ica[, picks, res, ...])

Generate an array of scalp topographies for the picked components.

Annotating Components

Finally, to facilitate annotation of the ICA components, we provide an API that conforms to the derivative standard of BIDS for EEG data to write the annotations to a TSV file.

mark_component(component, fname, method, ...)	Mark a component with a label.
write_components_tsv(ica, fname)	Write channels tsv file for ICA components.

In addition, as of version 0.3, we have introduced a beta-version of a GUI that assists in annotated ICA components. This was heavily inspired by the annotation process in ICLabel.

label_ica_components(inst, ica[, show, block])

Launch the IC labelling GUI.