accusleepy 0.12.1

Python implementation of AccuSleep

AccuSleePy

Description

AccuSleePy is set of graphical user interfaces for scoring rodent sleep using EEG and EMG recordings. It offers the following improvements over the MATLAB version (AccuSleep):

• Up to 10 brain states can be configured through the user interface
• Classification models can be trained through the user interface
  • Model files contain useful metadata (brain state configuration, epoch length, number of epochs)
  • Models optimized for real-time scoring can be trained
• Confidence scores can be saved and visualized
• Lists of recordings can be imported and exported for repeatable batch processing
• Undo/redo functionality in the manual scoring interface

If you use AccuSleep in your research, please cite our publication:

Barger, Z., Frye, C. G., Liu, D., Dan, Y., & Bouchard, K. E. (2019). Robust, automated sleep scoring by a compact neural network with distributional shift correction. PLOS ONE, 14(12), 1–18.

The data and models associated with AccuSleep are available at https://osf.io/py5eb/

Please contact zekebarger (at) gmail (dot) com with any questions or comments about the software.

Installation

• make sure you have python >=3.11,<3.14
• (recommended) create a new virtual environment (using venv, conda, etc.)
• (optional) if you have a CUDA device and want to speed up model training, install PyTorch
• pip install accusleepy
• (optional) download a classification model from https://osf.io/py5eb/ under /python_format/models/

There have been issues reported with installing pytorch on M1 Macs. Please contact us if you have trouble with this.

Usage

python -m accusleepy will open the primary interface.

Your settings are saved to a platform-specific location (e.g., ~/Library/Application Support/accusleepy/config.json on macOS)

Guide to the primary interface

Guide to the manual scoring interface

Developer guide

If you want to contribute to the project or modify the code for your own use, please consult the developer guide.

Changelog

• 0.12.0-0.12.1: Make plots more interactive
• 0.11.2: Simplify GUI editing
• 0.11.1: Add integration tests
• 0.11.0: Store config file in a user directory
• 0.10.0-0.10.1: Improved zoom behavior, updated dependencies
• 0.7.0-0.9.3: Bugfixes, code cleanup, additional config settings
• 0.6.0: Confidence scores can now be displayed and saved. Retraining your models is recommended since the new calibration feature will make the confidence scores more accurate.
• 0.4.5: Add support for python 3.13, remove support for python 3.10.
• 0.1.0-0.4.4: Early development versions

Screenshots

Primary interface

Manual scoring interface

Acknowledgements

We would like to thank Franz Weber for creating an early version of the manual labeling interface. The code that creates spectrograms comes from the Prerau lab with only minor modifications. Jim Bohnslav's deepethogram served as an incredibly useful reference when reimplementing this project in python. The model calibration code added in version 0.6.0 comes from Geoff Pleiss' temperature scaling repo.