Metaheuristic Clustering

As the name suggests, this is a repository for metaheuristic clustering algorithms, implemented in Python 3, that I could not find implemented elsewhere.

Implementations are designed to work with or without the sklearn implementation style.

Currently the algorithms implemented are:

• Artifical Bee Colony (ABC)
  • D. Karaboga and C. Ozturk (2011). "A novel clustering approach: Artificial Bee Colony (ABC) algorithm", Applied soft computing, 11(1), 652–657, 2011.
• Shuffled Frog Leaping Algorithm (SFLA)
  • B. Amiri, M. Fathian, and A. Maroosi (2009). "Application of shuffled frog-leaping algorithm on clustering", The International Journal of Advanced Manufacturing Technology, 45(1-2), 199-209.

Installation

metaheristic_clustering can be installed with:

pip install metaheuristic-clustering

Or you can fork this repository

Dependencies

Numpy

PyClustering

scikit-learn - only needed for interop with scikit-learn

Contributing Guidelines

Please create a pull request or an issue if you would like to contribute or have any bug reports, issues, or suggestions.

Example

There is example code using the metaheuristic-clusteing library available:

• python file
• jupyter notebook

Or for a breif overview see below:

Sklearn/Object style

data = X  # your data

# SFLA Clustering
from metaheuristic_clustering.sfla import SFLAClustering

sfla_model = SFLAClustering()
sfla_labels = sfla_model.fit_predict(data)

# ABC Clustering
from metaheuristic_clustering.abc import ABCClustering

abc_model = ABCClustering()
abc_labels = abc_model.fit_predict(data)

Function style

import metaheuristic_clustering.util as util

data = X  # your data

# SFLA Clustering
import metaheuristic_clustering.sfla as sfla

best_frog = sfla.sfla(data)
sfla_labels = util.get_labels(data, best_frog)

# ABC Clustering
import metaheuristic_clustering.abc as abc

best_bee = abc.abc(data)
abc_labels = util.get_labels(data, best_bee)

Sample Results

ABC

SFLA