mfauvel / fffs

Fast Forward Feature Selection

README for Fast Forward Feature Selection

Objectives

The package provides the python codes to perform a fast forward feature selection using a Gaussian Mixture Model. The algorithm is based on the following papers http://arxiv.org/abs/1501.00857 and Nonlinear parsimonious feature selection for the classification of hyperspectral images.

Install

Just download the file npfs.py and import it with python. It has been tested on linux, Debian Wheezy.

Requirements

Scipy needs to be installed. For a fast processing, a good linear algebra library is required too. Openblas is a good option.

Usage

See the file test_sparse_classif.py