PECUZAL automatic embedding of uni- and multivariate time series
Project description
PECUZAL Python
We introduce the PECUZAL automatic embedding of time series method for Python. It is solely based on the paper [kraemer2020] (Open Source), where the functionality is explained in detail. Here we give an introduction to its easy usage in three examples. Enjoy Embedding!
Getting started
Install from PyPI by simply typing
pip install pecuzal-embedding
in your console.
NOTE
This implementation is not profiled well. We recommend to use the implementation in the Julia language or in Matlab, in order to get fast results, especially in the multivariate case. Moreover, it is well documented and embedded in the DynamicalSystems.jl ecosystem. For instance, the compuations made in the sec_univariate and the sec_multivariate in this documentation took approximately 500s and 1680s, respectively. In the Julia implementation the exact same computation took 3s and 20s, respectively! (running on a 2.8GHz Quad-Core i7, 16GB 1600 MHz DDR3)
Documentation
There is a documentation available including some basic usage examples.
Citing and reference
If you enjoy this tool and find it valuable for your research please cite
Kraemer et al., “A unified and automated approach to attractor reconstruction”, arXiv:2011.07040 [physics.data-an], 2020.
or as BiBTeX-entry:
@misc{kraemer2020, title={A unified and automated approach to attractor reconstruction}, author={K. H. Kraemer and G. Datseris and J. Kurths and I. Z. Kiss and J. L. Ocampo-Espindola and N. Marwan}, year={2020}, eprint={2011.07040}, archivePrefix={arXiv}, primaryClass={physics.data-an} url={https://arxiv.org/abs/2011.07040} }
Licence
This is program is free software and runs under MIT Licence.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for pecuzal_embedding-1.0.3-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 0f9d36edbd8956b24092c62b072dc07c28c4197adf50d6ece17132e3869692bd |
|
MD5 | b0e8603a2da58870160782a952ccadd5 |
|
BLAKE2b-256 | 20678eaa9d75605f0935e8116389cde6c18725d4c53d673577851018a950121d |