Metadata-Version: 2.4
Name: keypoint-moseq
Version: 0.7.1
Summary: Unsupervised discovery of behavioral syllables from keypoint tracking data
Home-page: https://github.com/dattalab/keypoint-moseq
Author: Caleb Weinreb
Author-email: calebsw@gmail.com
Classifier: Programming Language :: Python :: 3
Classifier: Operating System :: OS Independent
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE.md
License-File: NOTICE.md
Requires-Dist: seaborn
Requires-Dist: cytoolz
Requires-Dist: matplotlib
Requires-Dist: tqdm
Requires-Dist: ipykernel
Requires-Dist: imageio[ffmpeg]
Requires-Dist: statsmodels
Requires-Dist: pyyaml
Requires-Dist: vidio
Requires-Dist: holoviews[recommended]
Requires-Dist: bokeh
Requires-Dist: pandas
Requires-Dist: tables
Requires-Dist: panel
Requires-Dist: networkx
Requires-Dist: sleap_io
Requires-Dist: pynwb
Requires-Dist: ndx_pose
Requires-Dist: plotly
Requires-Dist: ipython_genutils
Requires-Dist: tabulate
Requires-Dist: commentjson
Requires-Dist: jax-moseq>=0.3.7
Requires-Dist: joblib
Requires-Dist: numpy
Requires-Dist: ipywidgets
Requires-Dist: ipympl
Requires-Dist: jax
Requires-Dist: jax-cuda12-pjrt
Requires-Dist: jax-cuda12-plugin
Requires-Dist: jaxlib
Provides-Extra: dev
Requires-Dist: sphinx; extra == "dev"
Requires-Dist: sphinx-rtd-theme; extra == "dev"
Requires-Dist: autodocsumm; extra == "dev"
Requires-Dist: myst-nb; extra == "dev"
Requires-Dist: pytest; extra == "dev"
Provides-Extra: test
Requires-Dist: pytest; extra == "test"
Requires-Dist: pytest-regressions; extra == "test"
Requires-Dist: pooch; extra == "test"
Provides-Extra: cuda
Requires-Dist: jax-moseq[cuda]; extra == "cuda"
Dynamic: license-file

# Keypoint MoSeq 

![logo](https://raw.githubusercontent.com/dattalab/keypoint-moseq/main/docs/source/_static/logo.jpg)

Motion Sequencing (MoSeq) is an unsupervised machine learning method for animal behavior analysis. Given behavioral recordings, MoSeq learns a set of stereotyped movement patterns and when they occur over time. This package provides tools for fitting a MoSeq model to keypoint tracking data [(Weinreb et al., 2023)](https://www.biorxiv.org/content/10.1101/2023.03.16.532307v1). 

## [Documentation](https://keypoint-moseq.readthedocs.io/en/stable/)

- [Colab](https://colab.research.google.com/github/dattalab/keypoint-moseq/blob/main/docs/keypoint_moseq_colab.ipynb)

- [Installation](https://keypoint-moseq.readthedocs.io/en/stable/install.html)

- [Modeling Tutorial](https://keypoint-moseq.readthedocs.io/en/stable/modeling.html)

- [Keypoint-MoSeq paper](https://www.nature.com/articles/s41592-024-02318-2)

- [Slack workspace](https://join.slack.com/t/moseqworkspace/shared_invite/zt-151x0shoi-z4J0_g_5rwJDlO1IfCU34A)

- [MoSeq homepage](https://dattalab.github.io/moseq2-website/index.html)


# License
MoSeq is freely available for academic use under a license provided by Harvard University. Please refer to the license file for details. If you are interested in using MoSeq for commercial purposes please contact Bob Datta directly at srdatta@hms.harvard.edu, who will put you in touch with the appropriate people in the Harvard Technology Transfer office.

