https://github.com/dokato/simple_kmeans

own implementation of kmeans algorithm
https://github.com/dokato/simple_kmeans

Last synced: 18 days ago
JSON representation

own implementation of kmeans algorithm

• Host: GitHub
• URL: https://github.com/dokato/simple_kmeans
• Owner: dokato
• Created: 2015-11-22T14:13:44.000Z (about 9 years ago)
• Default Branch: master
• Last Pushed: 2015-11-22T23:12:04.000Z (about 9 years ago)
• Last Synced: 2024-10-16T12:39:40.648Z (2 months ago)
• Language: Python
• Size: 489 KB
• Stars: 0
• Watchers: 3
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# K-means

Simple python implemetation of this well-known machine

learning algorithm. 

## How to use?

Kmeans algorithm has only one main parameter: *k* which is the number

of clusters into you want to divide your data. You may also want

to specify `eps` which is convergence constant and implies when

to stop algorithm.

In this case I decided to use Forgy initialization which is simply

chosing random data as initial clusters.

## Examples

Two examples provided:

* one in main `kmeans.py` script

* second shows image compression using k-means in `compression.py`