mnextend 0.2.2

Additional functionality for MNE-Python

MNEXTEND

This package provides additional functionality for working with MNE-Python, the most popular Python package for processing electrophysiological data (EEG, MEG, ...).

Features

Reading additional file formats

MNEXTEND provides readers for the following file formats that are not natively supported by MNE-Python:

• XDF (Extensible Data Format)
• MAT (MATLAB)
• NPY (NumPy)

In addition, MNEXTEND adds the following readers from third-party packages:

• BVRF (via PyBVRF)

Together with the native MNE-Python readers, read_raw() and read_epochs() provide a unified interface for reading electrophysiological data from a wide range of file formats, so all you have to do is:

from mnextend import read_raw, read_epochs

raw = read_raw("my_data-raw.xdf", stream_ids=[1, 2, 3])
epochs = read_epochs("my_data-epochs.fif.gz")

Inspecting files before reading

Some formats require inspecting file contents before calling read_raw(), e.g. to let a user pick which stream(s) or participant(s) to load:

from mnextend.io.bvrf import read_bvrf_header
from mnextend.io.xdf import resolve_streams

streams = resolve_streams("my_data.xdf")
header = read_bvrf_header("my_data.bvrh")

Writing raw data

Writing raw data is supported via write_raw(), which does not implement any new file formats, but provides a unified interface for writing raw data to the file formats that are natively supported by MNE-Python:

from mnextend import write_raw

write_raw("my_data-raw.fif.gz", raw)

ICLabel classification

MNEXTEND includes ICLabel, a pre-trained classifier that labels ICA components as one of seven types: brain, muscle, eye, heart, line noise, channel noise, or other. In contrast to MNE-ICALabel, the classifier is implemented in pure NumPy and does not depend on ONNX Runtime.

run_iclabel() takes a fitted ICA object and the corresponding Raw or Epochs instance (which must have a montage set), and returns an array of class probabilities:

from mnextend import plot_ica_components, run_iclabel

probs = run_iclabel(raw, ica)
figs = plot_ica_components(raw, ica, probs)