principalcomponentstransformation.java

一个很好的LIBSVM的JAVA源码。对于要研究和改进SVM算法的学者。可以参考。来自数据挖掘工具YALE工具包。

/*
 *  YALE - Yet Another Learning Environment
 *  Copyright (C) 2001-2004
 *      Simon Fischer, Ralf Klinkenberg, Ingo Mierswa, 
 *          Katharina Morik, Oliver Ritthoff
 *      Artificial Intelligence Unit
 *      Computer Science Department
 *      University of Dortmund
 *      44221 Dortmund,  Germany
 *  email: [e-mail]
 *  web:   http://yale.cs.uni-dortmund.de/
 *
 *  This program is free software; you can redistribute it and/or
 *  modify it under the terms of the GNU General Public License as 
 *  published by the Free Software Foundation; either version 2 of the
 *  License, or (at your option) any later version. 
 *
 *  This program is distributed in the hope that it will be useful, but
 *  WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
 *  General Public License for more details.
 *
 *  You should have received a copy of the GNU General Public License
 *  along with this program; if not, write to the Free Software
 *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
 *  USA.
 */
package edu.udo.cs.yale.operator.features;

import edu.udo.cs.yale.operator.Operator;
import edu.udo.cs.yale.operator.OperatorException;
import edu.udo.cs.yale.operator.UserError;
import edu.udo.cs.yale.operator.IOObject;
import edu.udo.cs.yale.operator.parameter.*;
import edu.udo.cs.yale.example.ExampleSet;
import edu.udo.cs.yale.example.Attribute;
import edu.udo.cs.yale.tools.WekaTools;
import edu.udo.cs.yale.tools.LogService;

import weka.attributeSelection.PrincipalComponents;
import weka.core.Instances;

import java.util.List;

/** Builds the principal components of the given data. The user can specify the amount of variance to cover in 
 *  the original data when retaining the best number of principal components. This operator makes use of the Weka
 *  implementation <code>PrincipalComponent</code>.
 *   
 *  @version $Id: PrincipalComponentsTransformation.java,v 1.1 2004/09/01 12:39:50 ingomierswa Exp $
 */
public class PrincipalComponentsTransformation extends Operator {

    public IOObject[] apply() throws OperatorException {
	ExampleSet exampleSet = (ExampleSet)getInput(ExampleSet.class);

	PrincipalComponents transformation = new PrincipalComponents();
	transformation.setNormalize(false); // if the user wants to normalize the data he has to apply the filter before
	transformation.setVarianceCovered(getParameterAsDouble("min_variance_coverage"));
	
	LogService.logMessage(getName() + ": Converting to Weka instances.", LogService.MINIMUM);
	Instances instances = WekaTools.toWekaInstances(exampleSet, "TempInstances", exampleSet.getLabel(), true);
	try {
	    LogService.logMessage(getName() + ": Building principal components.", LogService.MINIMUM);
	    transformation.buildEvaluator(instances);
	} catch (Exception e) {
	    throw new UserError(this, e, 905, new Object[] {"PrincipalComponents", e});
	}
	
	ExampleSet result = null;
	try {
	    Instances transformed = transformation.transformedData();
	    result = WekaTools.toYaleExampleSet(transformed, "pc");
	} catch (Exception e) {
	    throw new OperatorException("Cannot convert to principal components: " + e);
	}
	return new IOObject[] { result };
    }

    public Class[] getOutputClasses() {
	return new Class[] { ExampleSet.class };
    }

    public Class[] getInputClasses() {
	return new Class[] { ExampleSet.class };
    }
    
    public List getParameterTypes() {
	List types = super.getParameterTypes();
	ParameterType type = new ParameterTypeDouble("min_variance_coverage", 
						     "The minimum variance to cover in the original data to determine the number of principal components.",
						     0.0, 1.0, 0.95);
	type.setExpert(false);
	types.add(type);
	return types;
    }
}