Skip to main content

coclustering algorithms for data mining

Project description

Description

coclust is a Python module which provides implementations for several co-clustering algorithms. Co-clustering (also known as biclustering), is an important extension of cluster analysis since it allows to simultaneously groups objects and features in a matrix, resulting in both row and column clusters. coclust is distributed under the 3-Clause BSD license.

Usage

To use coclust, just use:

>>> import coclust

See the available HTML documentation for details and usage samples.

Install

coclust relies on the numpy and scipy libraries, and also on scikit and matplotlib for some of the demos included in the package.

If these libraries are already installed on your machine, you can install coclust by just entering:

pip install coclust

If this is not the case, the following subsections show how to install the required libraries and then coclust.

On Windows

The simplest method is to use a distribution which includes all the libraries. For example, when using the Continuum distro go to the download site to get and double-click the graphical installer. Then, enter pip install coclust at the command line.

On Ubuntu, Debian

The easiest method is to use your package manager. For example, on Ubuntu:

sudo apt-get install python-numpy python-scipy python-sklearn
sudo pip install coclust

You can also try to compile from source, but compiling Scipy may be tricky, so it is not the recommended way. Try at your own risk:

sudo apt-get install gfortran python-dev
sudo apt-get install libopenblas-base
sudo apt-get install liblapack-dev
sudo pip install coclust

OpenBLAS provides a fast multi-threaded implementation. If other implementations are installed on your system, you can select OpenBLAS with:

sudo update-alternatives --config libblas.so.3

Changelog

0.1.3 - April, 2016

  • New visualization methods in the utils module.

  • New demos.

  • Better PEP 8 conformance

  • Improved documentation.

0.1.1 - March 07, 2016

  • First release.

Code

You can check the latest sources with the command:

git clone https://github.com/franrole/cclust_package.git

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

coclust-0.1.3.zip (483.4 kB view hashes)

Uploaded Source

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page