mne.datasets.eegbci.load_data

mne.datasets.eegbci.load_data(subjects=None, runs=None, *, subject=None, path=None, force_update=False, update_path=None, base_url='https://physionet.org/files/eegmmidb/1.0.0/', verbose=None)

Get paths to local copies of EEGBCI dataset files.

This will fetch data for the EEGBCI dataset [1], which is also available at PhysioNet [2]. Metadata, such as the meaning of event markers may be obtained from the PhysioNet documentation page.

Parameters:

subjectsint | list of int

The subjects to use. Can be in the range of 1-109 (inclusive).

runsint | list of int

The runs to use (see Notes for details).

subjectint

This parameter is deprecated and will be removed in mne version 1.9. Please use subjects instead.

pathNone | path-like

Location of where to look for the EEGBCI data. If None, the environment variable or config parameter MNE_DATASETS_EEGBCI_PATH is used. If neither exists, the ~/mne_data directory is used. If the EEGBCI dataset is not found under the given path, the data will be automatically downloaded to the specified folder.

force_updatebool

Force update of the dataset even if a local copy exists.

update_pathbool | None

If True, set MNE_DATASETS_EEGBCI_PATH in the configuration to the given path. If None, the user is prompted.

base_urlstr

The URL root for the data.

verbosebool | str | int | None

Control verbosity of the logging output. If None, use the default verbosity level. See the logging documentation and mne.verbose() for details. Should only be passed as a keyword argument.

Returns:

pathslist

List of local data paths of the given type.

Notes

The run numbers correspond to:

run	task
1	Baseline, eyes open
2	Baseline, eyes closed
3, 7, 11	Motor execution: left vs right hand
4, 8, 12	Motor imagery: left vs right hand
5, 9, 13	Motor execution: hands vs feet
6, 10, 14	Motor imagery: hands vs feet

For example, one could do:

>>> from mne.datasets import eegbci
>>> eegbci.load_data([1, 2], [6, 10, 14], "~/datasets") 

This would download runs 6, 10, and 14 (hand/foot motor imagery) runs from subjects 1 and 2 in the EEGBCI dataset to “~/datasets” and prompt the user to store this path in the config (if it does not already exist).

References

[1]

Gerwin Schalk, Dennis J. McFarland, Thilo Hinterberger, Niels Birbaumer, and Jonathan R. Wolpaw. BCI2000: a general-purpose brain-computer interface (BCI) system. IEEE Transactions on Biomedical Engineering, 51(6):1034–1043, 2004. doi:10.1109/TBME.2004.827072.

[2]

Ary L. Goldberger, Luis A. N. Amaral, Leon Glass, Jeffrey M. Hausdorff, Plamen Ch. Ivanov, Roger G. Mark, Joseph E. Mietus, George B. Moody, Chung-Kang Peng, and H. Eugene Stanley. PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation, 2000. doi:10.1161/01.CIR.101.23.e215.