simplemi.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.
 */

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

package weka.classifiers.mi;

import weka.classifiers.SingleClassifierEnhancer;
import weka.classifiers.Evaluation;
import weka.core.Attribute;
import weka.core.Capabilities;
import weka.core.Instance;
import weka.core.Instances;
import weka.core.MultiInstanceCapabilitiesHandler;
import weka.core.Option;
import weka.core.OptionHandler;
import weka.core.SelectedTag;
import weka.core.Tag;
import weka.core.Utils;
import weka.core.Capabilities.Capability;

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

/**
 <!-- globalinfo-start -->
 * Reduces MI data into mono-instance data.
 * <p/>
 <!-- globalinfo-end -->
 *
 <!-- options-start -->
 * Valid options are: <p/>
 * 
 * <pre> -M [1|2|3]
 *  The method used in transformation:
 *  1.arithmatic average; 2.geometric centor;
 *  3.using minimax combined features of a bag (default: 1)
 * 
 *  Method 3:
 *  Define s to be the vector of the coordinate-wise maxima
 *  and minima of X, ie., 
 *  s(X)=(minx1, ..., minxm, maxx1, ...,maxxm), transform
 *  the exemplars into mono-instance which contains attributes
 *  s(X)</pre>
 * 
 * <pre> -D
 *  If set, classifier is run in debug mode and
 *  may output additional info to the console</pre>
 * 
 * <pre> -W
 *  Full name of base classifier.
 *  (default: weka.classifiers.rules.ZeroR)</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>
 * 
 <!-- options-end -->
 *
 * @author Eibe Frank ([e-mail])
 * @author Xin Xu ([e-mail])
 * @author Lin Dong ([e-mail])
 * @version $Revision: 1.3 $ 
 */
public class SimpleMI 
  extends SingleClassifierEnhancer
  implements OptionHandler, MultiInstanceCapabilitiesHandler {  

  /** for serialization */
  static final long serialVersionUID = 9137795893666592662L;
  
  /** arithmetic average */
  public static final int TRANSFORMMETHOD_ARITHMETIC = 1;
  /** geometric average */
  public static final int TRANSFORMMETHOD_GEOMETRIC = 2;
  /** using minimax combined features of a bag */
  public static final int TRANSFORMMETHOD_MINIMAX = 3;
  /** the transformation methods */
  public static final Tag[] TAGS_TRANSFORMMETHOD = {
    new Tag(TRANSFORMMETHOD_ARITHMETIC, "arithmetic average"),
    new Tag(TRANSFORMMETHOD_GEOMETRIC, "geometric average"),
    new Tag(TRANSFORMMETHOD_MINIMAX, "using minimax combined features of a bag")
  };

  /** the method used in transformation */
  protected int m_TransformMethod = TRANSFORMMETHOD_ARITHMETIC;

  /**
   * Returns a string describing this filter
   *
   * @return a description of the filter suitable for
   * displaying in the explorer/experimenter gui
   */
  public String globalInfo() {
    return "Reduces MI data into mono-instance data.";
  }

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

    result.addElement(new Option(
          "\tThe method used in transformation:\n"
          + "\t1.arithmatic average; 2.geometric centor;\n"
          + "\t3.using minimax combined features of a bag (default: 1)\n\n"
          + "\tMethod 3:\n"
          + "\tDefine s to be the vector of the coordinate-wise maxima\n"
          + "\tand minima of X, ie., \n"
          + "\ts(X)=(minx1, ..., minxm, maxx1, ...,maxxm), transform\n"
          + "\tthe exemplars into mono-instance which contains attributes\n"
          + "\ts(X)",
          "M", 1, "-M [1|2|3]"));

    Enumeration enu = super.listOptions();
    while (enu.hasMoreElements()) {
      result.addElement(enu.nextElement());
    }

    return result.elements();
  }


  /**
   * Parses a given list of options. <p/>
   *
   <!-- options-start -->
   * Valid options are: <p/>
   * 
   * <pre> -M [1|2|3]
   *  The method used in transformation:
   *  1.arithmatic average; 2.geometric centor;
   *  3.using minimax combined features of a bag (default: 1)
   * 
   *  Method 3:
   *  Define s to be the vector of the coordinate-wise maxima
   *  and minima of X, ie., 
   *  s(X)=(minx1, ..., minxm, maxx1, ...,maxxm), transform
   *  the exemplars into mono-instance which contains attributes
   *  s(X)</pre>
   * 
   * <pre> -D
   *  If set, classifier is run in debug mode and
   *  may output additional info to the console</pre>
   * 
   * <pre> -W
   *  Full name of base classifier.
   *  (default: weka.classifiers.rules.ZeroR)</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>
   * 
   <!-- 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 {	

    setDebug(Utils.getFlag('D', options));

    String methodString = Utils.getOption('M', options);
    if (methodString.length() != 0) {
      setTransformMethod(
          new SelectedTag(
            Integer.parseInt(methodString), TAGS_TRANSFORMMETHOD));
    } else {
      setTransformMethod(
          new SelectedTag(
            TRANSFORMMETHOD_ARITHMETIC, TAGS_TRANSFORMMETHOD));
    }	

    super.setOptions(options);
  }

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

    return (String[]) result.toArray(new String[result.size()]);
  }

  /**
   * Returns the tip text for this property
   *
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String transformMethodTipText() {
    return "The method used in transformation.";
  }

  /**
   * Set the method used in transformation. 
   *
   * @param newMethod the index of method to use.
   */
  public void setTransformMethod(SelectedTag newMethod) {
    if (newMethod.getTags() == TAGS_TRANSFORMMETHOD)
      m_TransformMethod = newMethod.getSelectedTag().getID();
  }

  /**
   * Get the method used in transformation.
   *
   * @return the index of method used.
   */
  public SelectedTag getTransformMethod() {