This package contains a generic implementation of greedy Information Theoretic Feature Selection (FS) methods. The implementation is based on the common theoretic framework presented by Gavin Brown. Implementations of mRMR, InfoGain, JMI and other commonly used FS filters are provided.
Unfortunately I committed the pom file change at the same time as a change to InfoThSelector.scala, so I can't (or don't know how to) pull the POM file change into a pull request by itself.
The change to InfoThSelector.scala exposes the raw mutual information scores for the feature vector. I use this during feature engineering to understand how changes to the feature space might affect model decisions.
Unfortunately I committed the pom file change at the same time as a change to InfoThSelector.scala, so I can't (or don't know how to) pull the POM file change into a pull request by itself.
The change to InfoThSelector.scala exposes the raw mutual information scores for the feature vector. I use this during feature engineering to understand how changes to the feature space might affect model decisions.