skip to navigation
skip to content

Not Logged In

cluster 1.1.2

python-cluster is a "simple" package that allows to create several groups (clusters) of objects from a list

DESCRIPTION

python-cluster is a "simple" package that allows to create several groups (clusters) of objects from a list. It's meant to be flexible and able to cluster any object. To ensure this kind of flexibility, you need not only to supply the list of objects, but also a function that calculates the similarity between two of those objects. For simple datatypes, like integers, this can be as simple as a subtraction, but more complex calculations are possible. Right now, it is possible to generate the clusters using a hierarchical clustering and the popular K-Means algorithm. For the hierarchical algorithm there are different "linkage" (single, complete, average and uclus) methods available. I plan to implement other algoithms as well on an "as-needed" or "as-I-have-time" basis.

Algorithms are based on the document found at http://www.elet.polimi.it/upload/matteucc/Clustering/tutorial_html/

USAGE

A simple python program could look like this:

>>> from cluster import *
>>> data = [12,34,23,32,46,96,13]
>>> cl = HierarchicalClustering(data, lambda x,y: abs(x-y))
>>> cl.getlevel(10)     # get clusters of items closer than 10
[96, 46, [12, 13, 23, 34, 32]]
>>> cl.getlevel(5)      # get clusters of items closer than 5
[96, 46, [12, 13], 23, [34, 32]]

Note, that when you retrieve a set of clusters, it immediately starts the clustering process, which is quite complex. If you intend to create clusters from a large dataset, consider doing that in a separate thread.

For K-Means clustering it would look like this:

>>> from cluster import KMeansClustering
>>> cl = KMeansClustering([(1,1), (2,1), (5,3), ...])
>>> clusters = cl.getclusters(2)

The parameter passed to getclusters is the count of clusters generated.

 
File Type Py Version Uploaded on Size
cluster-1.1.2.linux-i686.exe (md5) MS Windows installer any 2013-03-11 187KB
cluster-1.1.2.tar.gz (md5) Source 2013-03-11 37KB
  • Downloads (All Versions):
  • 93 downloads in the last day
  • 725 downloads in the last week
  • 2427 downloads in the last month