MOAFS: A Massive Online Analysis library for feature selection in data streams

MOAFS is a library for the Massive Online Analysis (MOA) framework. It is based on the MOAReduction extension and contains the implementation of seven feature selection algorithms to be used as dimensionality reduction techniques in data streams classification problems, especially in the text-domain field. MOAFS uses an incremental version of Naïve Bayes as the base classifier.