https://github.com/llimllib/ckmeans

ckmeans in python with numpy
https://github.com/llimllib/ckmeans

Last synced: about 1 month ago
JSON representation

ckmeans in python with numpy

• Host: GitHub
• URL: https://github.com/llimllib/ckmeans
• Owner: llimllib
• License: wtfpl
• Created: 2015-08-16T17:56:00.000Z (over 9 years ago)
• Default Branch: master
• Last Pushed: 2024-03-28T15:57:31.000Z (10 months ago)
• Last Synced: 2024-11-30T02:50:28.522Z (about 1 month ago)
• Language: Python
• Size: 20.5 KB
• Stars: 22
• Watchers: 3
• Forks: 8
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
ckmeans

=======

Ckmeans is a function to cluster a one-dimensional array of floats into `k` optimal clusters.

`Optimal` here means that the standard deviation inside each cluster is minimized.

Ckmeans was developed by

[Haizhou Wang and Mingzhou Song](http://journal.r-project.org/archive/2011-2/RJournal_2011-2_Wang+Song.pdf).

This code follows directly from Tom MacWright's code in

[simple-statistics](https://github.com/simple-statistics/simple-statistics/blob/master/src/ckmeans.js)

and David Schnurr's code in [d3-scale-cluster](https://github.com/schnerd/d3-scale-cluster/).

Please use this code in any way you wish, with or without attribution. It's licensed WTFPL.

If you'd rather use the original C++ code via a cython wrapper, check out

[rocketrip/ckmeans](https://github.com/rocketrip/ckmeans).

_2024 update_: I recommend [ckmeans_py](https://github.com/urschrei/ckmeans_py) (available on 

[pyPI](https://pypi.org/project/ckmeans/)) which wraps an efficient rust version of this algorithm

In 2022 ckmeans picked up a [citation](https://arxiv.org/ftp/arxiv/papers/2202/2202.04883.pdf)!