cc.mallet.classify.FeatureSelectingClassifierTrainer Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of jcore-mallet-2.0.9 Show documentation

MALLET is a Java-based package for statistical natural language processing, document classification, clustering, topic modeling, information extraction, and other machine learning applications to text.

The newest version!

/* Copyright (C) 2002 Univ. of Massachusetts Amherst, Computer Science Dept.
   This file is part of "MALLET" (MAchine Learning for LanguagE Toolkit).
   http://www.cs.umass.edu/~mccallum/mallet
   This software is provided under the terms of the Common Public License,
   version 1.0, as published by http://www.opensource.org.  For further
   information, see the file `LICENSE' included with this distribution. */






package cc.mallet.classify;

import cc.mallet.classify.Classifier;
import cc.mallet.types.FeatureSelector;
import cc.mallet.types.InstanceList;
/**
 * Adaptor for adding feature selection to a classifier trainer.
   @author Andrew McCallum [email protected]
 */
public class FeatureSelectingClassifierTrainer extends ClassifierTrainer
{
	ClassifierTrainer underlyingTrainer;
	FeatureSelector featureSelector;
	Classifier classifier;
	public Classifier getClassifier () { return classifier; }

	public FeatureSelectingClassifierTrainer (ClassifierTrainer underlyingTrainer,
																						FeatureSelector featureSelector)
	{
		this.underlyingTrainer = underlyingTrainer;
		this.featureSelector = featureSelector;
	}

	public Classifier train (InstanceList trainingSet)
	{
		featureSelector.selectFeaturesFor (trainingSet);
		// TODO What about also selecting features for the validation set?
		this.classifier = underlyingTrainer.train (trainingSet);
		return classifier;
	}

}