costsensitiveclassifiersplitevaluator.java

Java 编写的多种数据挖掘算法 包括聚类、分类、预处理等

/*
 *    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.
 */

/*
 *    CostSensitiveClassifierSplitEvaluator.java
 *    Copyright (C) 2002 University of Waikato
 *
 */


package weka.experiment;

import weka.classifiers.Classifier;
import weka.classifiers.CostMatrix;
import weka.classifiers.Evaluation;
import weka.core.AdditionalMeasureProducer;
import weka.core.Attribute;
import weka.core.Instance;
import weka.core.Instances;
import weka.core.Option;
import weka.core.Summarizable;
import weka.core.Utils;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileReader;
import java.lang.management.ManagementFactory;
import java.lang.management.ThreadMXBean;
import java.util.Enumeration;
import java.util.Vector;

/**
 <!-- globalinfo-start -->
 * SplitEvaluator that produces results for a classification scheme on a nominal class attribute, including weighted misclassification costs.
 * <p/>
 <!-- globalinfo-end -->
 *
 <!-- options-start -->
 * Valid options are: <p/>
 * 
 * <pre> -W &lt;class name&gt;
 *  The full class name of the classifier.
 *  eg: weka.classifiers.bayes.NaiveBayes</pre>
 * 
 * <pre> -C &lt;index&gt;
 *  The index of the class for which IR statistics
 *  are to be output. (default 1)</pre>
 * 
 * <pre> -I &lt;index&gt;
 *  The index of an attribute to output in the
 *  results. This attribute should identify an
 *  instance in order to know which instances are
 *  in the test set of a cross validation. if 0
 *  no output (default 0).</pre>
 * 
 * <pre> -P
 *  Add target and prediction columns to the result
 *  for each fold.</pre>
 * 
 * <pre> 
 * Options specific to classifier weka.classifiers.rules.ZeroR:
 * </pre>
 * 
 * <pre> -D
 *  If set, classifier is run in debug mode and
 *  may output additional info to the console</pre>
 * 
 * <pre> -D &lt;directory&gt;
 *  Name of a directory to search for cost files when loading
 *  costs on demand (default current directory).</pre>
 * 
 <!-- options-end -->
 *
 * All options after -- will be passed to the classifier.
 *
 * @author Len Trigg ([e-mail])
 * @version $Revision: 1.14 $
 */
public class CostSensitiveClassifierSplitEvaluator 
  extends ClassifierSplitEvaluator { 

  /** for serialization */
  static final long serialVersionUID = -8069566663019501276L;

  /** 
   * The directory used when loading cost files on demand, null indicates
   * current directory 
   */
  protected File m_OnDemandDirectory = new File(System.getProperty("user.dir"));

  /** The length of a result */
  private static final int RESULT_SIZE = 27; //23;

  /**
   * Returns a string describing this split evaluator
   * @return a description of the split evaluator suitable for
   * displaying in the explorer/experimenter gui
   */
  public String globalInfo() {
    return " SplitEvaluator that produces results for a classification scheme "
      +"on a nominal class attribute, including weighted misclassification "
      +"costs.";
  }

  /**
   * Returns an enumeration describing the available options..
   *
   * @return an enumeration of all the available options.
   */
  public Enumeration listOptions() {

    Vector newVector = new Vector(1);
    Enumeration enu = super.listOptions();
    while (enu.hasMoreElements()) {
      newVector.addElement(enu.nextElement());
    }

    newVector.addElement(new Option(
              "\tName of a directory to search for cost files when loading\n"
              +"\tcosts on demand (default current directory).",
              "D", 1, "-D <directory>"));

    return newVector.elements();
  }

  /**
   * Parses a given list of options. <p/>
   *
   <!-- options-start -->
   * Valid options are: <p/>
   * 
   * <pre> -W &lt;class name&gt;
   *  The full class name of the classifier.
   *  eg: weka.classifiers.bayes.NaiveBayes</pre>
   * 
   * <pre> -C &lt;index&gt;
   *  The index of the class for which IR statistics
   *  are to be output. (default 1)</pre>
   * 
   * <pre> -I &lt;index&gt;
   *  The index of an attribute to output in the
   *  results. This attribute should identify an
   *  instance in order to know which instances are
   *  in the test set of a cross validation. if 0
   *  no output (default 0).</pre>
   * 
   * <pre> -P
   *  Add target and prediction columns to the result
   *  for each fold.</pre>
   * 
   * <pre> 
   * Options specific to classifier weka.classifiers.rules.ZeroR:
   * </pre>
   * 
   * <pre> -D
   *  If set, classifier is run in debug mode and
   *  may output additional info to the console</pre>
   * 
   * <pre> -D &lt;directory&gt;
   *  Name of a directory to search for cost files when loading
   *  costs on demand (default current directory).</pre>
   * 
   <!-- options-end -->
   *
   * All options after -- will be passed to the classifier.
   *
   * @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 demandDir = Utils.getOption('D', options);
    if (demandDir.length() != 0) {
      setOnDemandDirectory(new File(demandDir));
    }

    super.setOptions(options);
  }

  /**
   * Gets the current settings of the Classifier.
   *
   * @return an array of strings suitable for passing to setOptions
   */
  public String [] getOptions() {

    String [] superOptions = super.getOptions();
    String [] options = new String [superOptions.length + 3];
    int current = 0;

    options[current++] = "-D";
    options[current++] = "" + getOnDemandDirectory();

    System.arraycopy(superOptions, 0, options, current, 
		     superOptions.length);
    current += superOptions.length;
    while (current < options.length) {
      options[current++] = "";
    }
    return options;
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String onDemandDirectoryTipText() {
    return "The directory to look in for cost files. This directory will be "
      +"searched for cost files when loading on demand.";
  }

  /**
   * Returns the directory that will be searched for cost files when
   * loading on demand.
   *
   * @return The cost file search directory.
   */
  public File getOnDemandDirectory() {

    return m_OnDemandDirectory;
  }

  /**
   * Sets the directory that will be searched for cost files when
   * loading on demand.
   *
   * @param newDir The cost file search directory.
   */
  public void setOnDemandDirectory(File newDir) {

    if (newDir.isDirectory()) {
      m_OnDemandDirectory = newDir;
    } else {
      m_OnDemandDirectory = new File(newDir.getParent());
    }
  }

  /**
   * Gets the data types of each of the result columns produced for a 
   * single run. The number of result fields must be constant
   * for a given SplitEvaluator.
   *
   * @return an array containing objects of the type of each result column. 
   * The objects should be Strings, or Doubles.
   */
  public Object [] getResultTypes() {
    int addm = (m_AdditionalMeasures != null)