Skip to content

A python library for unsupervised time series analysis

License

Notifications You must be signed in to change notification settings

nickprock/pynuTS

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

pynuTS

A little Python library for Time Series


peanuts


pynuTS is a little python library based on my articles pubblished in 2020 on IAML blog.

The articles are written in italian, you can read them at the follow links:


iaml


Work in progress

The project is work in progress. It is mantained by some voluntiers and me.

What's New?

New features in version 0.2.2:

  • changing the names of some hyperparameters in DTWKMeans
  • bug fixing
  • demos update

New features in version 0.2.1:

  • SAX Encoding refactoring: new module decompose
  • Time series generator (experimental)
  • New demo notebooks

Installation


Dependencies

* Python (>= 3.8.5)
* NumPy (>= 1.19.2)
* Pandas (>= 1.1.3)
* Scikit-learn (>= 0.23.2)
* tqdm (>= 4.50.2)
* dtw (>= 1.4.0)

User Installation

The easiest way to install pynuTS is using:

sudo apt install git

pip install git+https://github.com/nickprock/pynuTS.git@main

Or clone the repo and:

pip install pynuTS-master.zip

Demos

After installation, you can try the demo notebooks.

Contributing

To learn more about making a contribution to pynuTS, please see our Contribution Guide.

Citation

If you use pynuTS in a scientific publication, please cite:

@misc{pynuTS,
  author =       {Nicola Procopio and Marcello Morchio},
  title =        {pynuTS},
  version = 	 {0.2.2}
  howpublished = {\url{https://github.com/nickprock/pynuTS/}},
  year =         {2021}
}

License

The code present in this project is licensed under the MIT LICENSE.

License: MIT

Licenza Creative Commons
This work is licensed under Creative Commons Attribution 4.0 International.