/mne-features

MNE-Features software for extracting features from multivariate time series

Primary LanguagePythonBSD 3-Clause "New" or "Revised" LicenseBSD-3-Clause

MNE-Features

GitHub Actions Codecov

This repository provides code for feature extraction with M/EEG data. The documentation of the MNE-Features module is available at: documentation.

Installation

To install the package, the simplest way is to use pip to get the latest release:

$ pip install mne-features

Or if you prefer conda:

$ conda install --channel=conda-forge mne-features

Or to get the latest version of the code:

$ pip install git+https://github.com/mne-tools/mne-features.git#egg=mne_features

Dependencies

These are the dependencies to use MNE-Features:

  • numpy (>=1.17)
  • matplotlib (>=1.5)
  • scipy (>=1.0)
  • numba (>=0.46.0)
  • llvmlite (>=0.30)
  • scikit-learn (>=0.21)
  • mne (>=0.18.2)
  • PyWavelets (>=0.5.2)
  • pandas (>=0.25)

Cite

If you use this code in your project, please cite:

Jean-Baptiste SCHIRATTI, Jean-Eudes LE DOUGET, Michel LE VAN QUYEN, Slim ESSID, Alexandre GRAMFORT,
"An ensemble learning approach to detect epileptic seizures from long intracranial EEG recordings"
Proc. IEEE ICASSP Conf. 2018