PyNeon is a lightweight Python package designed to streamline the processing and analysis of multimodal eye-tracking data from the Neon eye-tracking system (Pupil Labs GmbH). This community-driven effort provides a versatile set of tools to work with Neon's rich data, including gaze, eye states, IMU, video, events, and more.
Currently, PyNeon supports the Timeseries Data or Timeseries Data + Scene Video formats of data, downloaded from Pupil Cloud. For reading data in the native format, please refer to the
pl-neon-recording project, which inspired the design of PyNeon.
Documentation for PyNeon is available at https://ncc-brain.github.io/PyNeon/ which includes detailed references for classes and functions, as well as step-by-step tutorials presented as Jupyter notebooks.
- (Tutorial) Easy API for reading in datasets and recordings. Quick access to various modalities of data.
- (Tutorial) Various preprocessing functions, including data cropping, interpolation, concatenation, etc.
- (Tutorial) Flexible epoching of data for trial-based analysis.
- (Tutorial) Methods for working with scene video, including scanpath estimation and AprilTags-based mapping.
- (Tutorial) Exportation to Motion-BIDS (and forthcoming Eye-Tracking-BIDS) format for interoperability across the cognitive neuroscience community.
To install PyNeon, clone the PyNeon repository from https://github.com/ncc-brain/PyNeon and run:
pip install .PyPI and conda releases are planned for the future.
If you use PyNeon in your research, please cite the accompanying paper as follows:
@misc{pyneon,
title={PyNeon: a Python package for the analysis of Neon multimodal mobile eye-tracking data},
url={osf.io/preprints/psyarxiv/y5jmg_v1},
DOI={10.31234/osf.io/y5jmg_v1},
publisher={PsyArXiv},
author={Chu, Qian and Hartel, Jan-Gabriel and Lepauvre, Alex and Melloni, Lucia},
year={2025},
month={Jun}
}