bayesnet.java

代码是一个分类器的实现,其中使用了部分weka的源代码。可以将项目导入eclipse运行

/*
 *    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., 675 Mass Ave, Cambridge, MA 02139, USA.
 */

/*
 * BayesNet.java
 * Copyright (C) 2005 University of Waikato, Hamilton, New Zealand
 *
 */

package weka.datagenerators.classifiers.classification;

import weka.classifiers.bayes.net.BayesNetGenerator;
import weka.core.Instance;
import weka.core.Instances;
import weka.core.Option;
import weka.core.Utils;
import weka.datagenerators.ClassificationGenerator;

import java.util.Enumeration;
import java.util.Vector;

/**
 <!-- globalinfo-start -->
 * Generates random instances based on a Bayes network.
 * <p/>
 <!-- globalinfo-end -->
 *
 <!-- options-start -->
 * Valid options are: <p/>
 * 
 * <pre> -h
 *  Prints this help.</pre>
 * 
 * <pre> -o &lt;file&gt;
 *  The name of the output file, otherwise the generated data is
 *  printed to stdout.</pre>
 * 
 * <pre> -r &lt;name&gt;
 *  The name of the relation.</pre>
 * 
 * <pre> -d
 *  Whether to print debug informations.</pre>
 * 
 * <pre> -S
 *  The seed for random function (default 1)</pre>
 * 
 * <pre> -n &lt;num&gt;
 *  The number of examples to generate (default 100)</pre>
 * 
 * <pre> -A &lt;num&gt;
 *  The number of arcs to use. (default 20)</pre>
 * 
 * <pre> -C &lt;num&gt;
 *  The cardinality of the attributes and the class. (default 2)</pre>
 * 
 <!-- options-end -->
 *
 * @author FracPete (fracpete at waikato dot ac dot nz)
 * @version $Revision: 1.3 $
 * @see BayesNetGenerator
 */

public class BayesNet
  extends ClassificationGenerator {
  
  /** for serialization */
  static final long serialVersionUID = -796118162379901512L;
  
  /** the bayesian net generator, that produces the actual data */
  protected BayesNetGenerator m_Generator;

  /**
   * initializes the generator
   */
  public BayesNet() {
    super();

    setNumAttributes(defaultNumAttributes());
    setNumArcs(defaultNumArcs());
    setCardinality(defaultCardinality());
  }
  
  /**
   * Returns a string describing this data generator.
   *
   * @return a description of the data generator suitable for
   * displaying in the explorer/experimenter gui
   */
  public String globalInfo() {
    return 
        "Generates random instances based on a Bayes network.";
  }

 /**
   * Returns an enumeration describing the available options.
   *
   * @return an enumeration of all the available options
   */
  public Enumeration listOptions() {
    Vector result = enumToVector(super.listOptions());

    result.add(new Option(
              "\tThe number of arcs to use. (default " 
              + defaultNumArcs() + ")",
              "A", 1, "-A <num>"));

    result.add(new Option(
              "\tThe cardinality of the attributes and the class. (default " 
              + defaultCardinality() + ")",
              "C", 1, "-C <num>"));

    return result.elements();
  }

  /**
   * Parses a list of options for this object. <p/>
   *
   <!-- options-start -->
   * Valid options are: <p/>
   * 
   * <pre> -h
   *  Prints this help.</pre>
   * 
   * <pre> -o &lt;file&gt;
   *  The name of the output file, otherwise the generated data is
   *  printed to stdout.</pre>
   * 
   * <pre> -r &lt;name&gt;
   *  The name of the relation.</pre>
   * 
   * <pre> -d
   *  Whether to print debug informations.</pre>
   * 
   * <pre> -S
   *  The seed for random function (default 1)</pre>
   * 
   * <pre> -n &lt;num&gt;
   *  The number of examples to generate (default 100)</pre>
   * 
   * <pre> -A &lt;num&gt;
   *  The number of arcs to use. (default 20)</pre>
   * 
   * <pre> -C &lt;num&gt;
   *  The cardinality of the attributes and the class. (default 2)</pre>
   * 
   <!-- options-end -->
   *
   * @param options the list of options as an array of strings
   * @throws Exception if an option is not supported
   */
  public void setOptions(String[] options) throws Exception {
    String        tmpStr;
    Vector        list;

    super.setOptions(options);

    list = new Vector();

    list.add("-N");
    list.add("" + getNumAttributes());

    list.add("-M");
    list.add("" + getNumExamples());
    
    list.add("-S");
    list.add("" + getSeed());
    
    list.add("-A");
    tmpStr = Utils.getOption('A', options);
    if (tmpStr.length() != 0)
      list.add(tmpStr);
    else
      list.add("" + defaultNumArcs());

    list.add("-C");
    tmpStr = Utils.getOption('C', options);
    if (tmpStr.length() != 0)
      list.add(tmpStr);
    else
      list.add("" + defaultCardinality());

    setGeneratorOptions(list);
  }

  /**
   * Gets the current settings of the datagenerator.
   *
   * @return an array of strings suitable for passing to setOptions
   */
  public String[] getOptions() {
    Vector        result;
    String[]      options;
    int           i;
    
    result  = new Vector();
    options = removeBlacklist(super.getOptions());
    for (i = 0; i < options.length; i++)
      result.add(options[i]);

    // determine options from generator
    options = getGenerator().getOptions();

    try {
      result.add("-A");
      result.add(Utils.getOption('A', options));
    }
    catch (Exception e) {
      e.printStackTrace();
    }

    try {
      result.add("-C");
      result.add(Utils.getOption('C', options));
    }
    catch (Exception e) {
      e.printStackTrace();
    }
    
    return (String[]) result.toArray(new String[result.size()]);
  }

  /**
   * sets the given options of the BayesNetGenerator
   * 
   * @param generator the generator to set the options for
   * @param options the options to set
   */
  protected void setGeneratorOptions(
      BayesNetGenerator generator, Vector options) {

    try {
      generator.setOptions(
          (String[]) options.toArray(new String[options.size()]));
    }
    catch (Exception e) {
      e.printStackTrace();
    }
  }

  /**
   * returns the actual datagenerator
   * 
   * @return the actual datagenerator
   */
  protected BayesNetGenerator getGenerator() {
    if (m_Generator == null)
      m_Generator = new BayesNetGenerator();

    return m_Generator;
  }

  /**
   * sets the given options of the BayesNetGenerator
   * 
   * @param options the options to set
   */
  protected void setGeneratorOptions(Vector options) {
    setGeneratorOptions(getGenerator(), options);
  }

  /**
   * sets a specific option/value of the generator (option must be w/o
   * then '-')
   * @param generator       the generator to set the option for
   * @param option          the option to set
   * @param value           the new value for the option
   */
  protected void setGeneratorOption( BayesNetGenerator generator, 
                                     String option, String value ) {

    String[]      options;
    Vector        list;
    int           i;

    try {
      // get options and remove specific option
      options = generator.getOptions();
      Utils.getOption(option, options);

      // add option and set the new options
      list = new Vector();
      for (i = 0; i < options.length; i++) {
        if (options[i].length() != 0)
          list.add(options[i]);
      }
      list.add("-" + option);
      list.add(value);
      setGeneratorOptions(generator, list);
    }