standarddeviationweighting.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.weighting;

import edu.udo.cs.yale.operator.IOObject;
import edu.udo.cs.yale.operator.Operator;
import edu.udo.cs.yale.operator.OperatorException;
import edu.udo.cs.yale.example.ExampleSet;
import edu.udo.cs.yale.example.Attribute;
import edu.udo.cs.yale.example.AttributeWeights;
import edu.udo.cs.yale.operator.parameter.*;
import edu.udo.cs.yale.Statistics;
import edu.udo.cs.yale.gui.SimplePlotterDialog;

import java.util.List;

/** <p>
 *  Creates a plot of the standard deviations of all attributes. The values can be normalized
 *  by the average, the minimum, or the maximum of the attribute. Additionally, this operator 
 *  can create attribute weights based on the standard deviation.
 *  </p>
 *
 *  @author Ingo Mierswa
 *  @version $Id: StandardDeviationWeighting.java,v 1.1 2004/08/30 15:08:29 ingomierswa Exp $
 */
public class StandardDeviationWeighting extends Operator {

    private static final String[] NORMALIZATIONS = {
	"none", "average", "minimum", "maximum"
    };

    private static final int NONE    = 0;
    private static final int AVERAGE = 1;
    private static final int MINIMUM = 2;
    private static final int MAXIMUM = 3;
    
    public IOObject[] apply() throws OperatorException {
	ExampleSet exampleSet = (ExampleSet)getInput(ExampleSet.class, false);
	
	int normalization = getParameterAsInt("normalize");
	
	Statistics stats = new Statistics("Standard Deviation Plot");
	stats.init(new String[] { "Attribute index", "StandardDeviation/" + NORMALIZATIONS[normalization] });
	AttributeWeights weights = new AttributeWeights();

	for (int i = 0; i < exampleSet.getNumberOfAttributes(); i++) {
	    Attribute attribute = exampleSet.getAttribute(i);
	    double data = Math.sqrt(attribute.getVariance());
	    switch (normalization) {
	    case AVERAGE: data /= attribute.getAverage(); break;
	    case MINIMUM: data /= attribute.getMinimum(); break;
	    case MAXIMUM: data /= attribute.getMaximum(); break;
	    default: break;
	    }
	    data = Math.abs(data);
	    stats.add(new Object[] { new Double(i), new Double(data) });
	    weights.setWeight(attribute.getName(), data);
	}
	
	if (getParameterAsBoolean("create_plot")) {
	    SimplePlotterDialog plotter = new SimplePlotterDialog(stats);
	    plotter.setXAxis(0);
	    plotter.plotColumn(1, true);
	    plotter.show();
	}

	if (getParameterAsBoolean("create_weights")) {
	    return new IOObject[] { weights };
	} else {
	    return new IOObject[0];
	}
    }

    public Class[] getInputClasses() {
	return new Class[0];
    }

    public Class[] getOutputClasses() {
	if (getParameterAsBoolean("create_weights")) {
	    return new Class[] { AttributeWeights.class };
	} else {
	    return new Class[0];
	}
    }

    public List getParameterTypes() {
	List types = super.getParameterTypes();
	ParameterType type = 
	    new ParameterTypeCategory("normalize", 
				      "Indicates if the standard deviation should be dividey by the minimum, maximum, or average of the attribute.", 
				      NORMALIZATIONS,
				      0);
	type.setExpert(false);
	types.add(type);

	type = new ParameterTypeBoolean("create_plot", 
					"Indicates if a plot with the standard deviations should be created.", 
					true);
	type.setExpert(false);
	types.add(type);

	type = new ParameterTypeBoolean("create_weights", 
					"Indicates if attribute weights should be created based on the standard deviation values for the attributes.", 
					false);
	type.setExpert(false);
	types.add(type);
	return types;
    }
}