/pyFmax

Feature F-Measure, Feature Maximisation, Feature selection, and clustering quality indexes based on feature contrasts

Primary LanguagePythonGNU General Public License v3.0GPL-3.0

pyFmax

A package to deal with Feature F-Measure**[1][2][3][4]**, Feature Maximisation, Feature selection, and clustering quality indexes based on feature contrasts [1].

####Install To make it work, your need to set up python and to install the numpy package

pip install numpy

####Usage

Exemple exemple.py gives a good example of how to use the package in your Python code. This example makes use of data stored in data/exemple that are extracted from [1].

####References

[1] Jean-Charles Lamirel, Nicolas Dugué, Pascal Cuxac. New efficient clustering quality indexes. In Neural Networks (IJCNN), The 2016 Inter- national Joint Conference on IEEE, 2016.

[2] Nicolas Dugué, Ali Tebbakh, Pascal Cuxac, Jean-Charles Lamirel. Feature selection and complex networks methods for an analysis of collaboration evolution in science: an application to the ISTEX digital library. ISKO-MAGHREB 2015, Nov 2015, Hammamet, Tunisia

[3] Nicolas Dugué, Jean-Charles Lamire, Pascal Cuxac. Diachronic'Explorer : Keep track of your clusters. RCIS 2016.

[4] Jean-Charles Lamirel, Raghvendra Mall, Pascal Cuxac, and Ghada Safi. Variations to incremental growing neural gas algorithm based on label maximization. In Neural Networks (IJCNN), The 2011 Inter- national Joint Conference on, pages 956–965. IEEE, 2011.