{% extends 'layout.html' %} {% set title = _('Deeptime') %} {% block body %}

Deeptime

Deeptime is a Python library for analysis of time series data. In particular, methods for dimension reduction, clustering, and Markov model estimation are implemented.

The API is similar to that of scikit-learn and offers basic compatibility to its tools via ducktyping.

Deeptime can be installed via conda (conda install -c conda-forge deeptime) delivering pre-compiled binaries and is also available via pip (pip install deeptime), causing the binaries to be compiled locally.

Please note our preprint https://arxiv.org/abs/2110.15013.

Main algorithms

Tools and data

Citation

When using deeptime in your work, please cite the following preprint
@article{hoffmann2021deeptime,
      title={Deeptime: a Python library for machine learning dynamical models from time series data},
      author={Moritz Hoffmann and Martin Scherer and Tim Hempel and Andreas Mardt and Brian de Silva and Brooke E. Husic and Stefan Klus and Hao Wu and Nathan Kutz and Steven L. Brunton and Frank NoƩ},
      year={2021},
      journal={arXiv preprint arXiv:2110.15013}
}
            
{% endblock %}