simplesampling.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.preprocessing;

import edu.udo.cs.yale.operator.Operator;
import edu.udo.cs.yale.operator.IOObject;
import edu.udo.cs.yale.operator.OperatorException;
import edu.udo.cs.yale.operator.parameter.*;
import edu.udo.cs.yale.example.Attribute;
import edu.udo.cs.yale.example.Example;
import edu.udo.cs.yale.example.ExampleSet;
import edu.udo.cs.yale.example.ExampleReader;
import edu.udo.cs.yale.example.ExampleTable;
import edu.udo.cs.yale.example.MemoryExampleTable;
import edu.udo.cs.yale.example.DoubleArrayDataRow;
import edu.udo.cs.yale.example.ListDataRowReader;
import edu.udo.cs.yale.example.SimpleExampleSet;

import java.util.List;
import java.util.LinkedList;
import java.util.Arrays;
import java.util.Iterator;


/** Simple sampling operator.
 *
 *  @version $Id: SimpleSampling.java,v 1.4 2004/09/17 12:57:42 ingomierswa Exp $
 */
public class SimpleSampling extends Operator {

    private double fraction = 0.1d;

    public IOObject[] apply() throws OperatorException {
	ExampleSet exampleSet = (ExampleSet)getInput(ExampleSet.class);
	this.fraction = getParameterAsDouble("sample_size");

	// fill new table
	Attribute[] allAttributes = exampleSet.getExampleTable().getAttributes();
	List dataList = new LinkedList();
	ExampleReader reader = exampleSet.getExampleReader();
	while (reader.hasNext()) {
	    Example example = reader.next();
	    if (accept(example)) {
		double[] values = new double[allAttributes.length];
		for (int i = 0; i < values.length; i++)
		    values[i] = example.getValue(allAttributes[i]);
		dataList.add(new DoubleArrayDataRow(values));
	    }
	}

	List attributes = Arrays.asList(exampleSet.getExampleTable().getAttributes());
	ExampleTable exampleTable = new MemoryExampleTable(attributes, new ListDataRowReader(dataList.iterator()));

	// regular attributes.
	List regularAttributes = new LinkedList();
	for (int i = 0; i < exampleSet.getNumberOfAttributes(); i++)
	    regularAttributes.add(exampleSet.getAttribute(i));

	// special attributes.
	ExampleSet result = new SimpleExampleSet(exampleTable, regularAttributes);
	Iterator special = exampleSet.getSpecialAttributeNames().iterator();
	while (special.hasNext()) {
	    String name = (String)special.next();
	    result.setSpecialAttribute(name, exampleSet.getAttribute(name));
	}

	result.recalculateAllAttributeStatistics();

	return new IOObject[] { result };
    }

    private boolean accept(Example example) {
	return edu.udo.cs.yale.tools.RandomGenerator.getGlobalRandomGenerator().nextDouble() < fraction;
    }

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

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

    public List getParameterTypes() {
	List types = super.getParameterTypes();
	ParameterType type = new ParameterTypeDouble("sample_size", "The fraction of examples which should be sampled", 0.0d, 1.0d, 0.1d);
	type.setExpert(false);
	types.add(type);
	return types;
    }
}