wavelet.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.
 */

/*
 * Wavelet.java
 * Copyright (C) 2006 University of Waikato, Hamilton, New Zealand
 *
 */

package weka.filters.unsupervised.attribute;

import weka.core.Attribute;
import weka.core.Capabilities;
import weka.core.FastVector;
import weka.core.Instance;
import weka.core.Instances;
import weka.core.Option;
import weka.core.OptionHandler;
import weka.core.SelectedTag;
import weka.core.Tag;
import weka.core.TechnicalInformation;
import weka.core.TechnicalInformationHandler;
import weka.core.Utils;
import weka.core.Capabilities.Capability;
import weka.core.TechnicalInformation.Field;
import weka.core.TechnicalInformation.Type;
import weka.filters.Filter;
import weka.filters.MultiFilter;
import weka.filters.SimpleBatchFilter;

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

/** 
 <!-- globalinfo-start -->
 * A filter for wavelet transformation.<br/>
 * <br/>
 * For more information see:<br/>
 * <br/>
 * Wikipedia (2004). Discrete wavelet transform.<br/>
 * <br/>
 * Kristian Sandberg (2000). The Haar wavelet transform. University of Colorado at Boulder, USA.
 * <p/>
 <!-- globalinfo-end -->
 *
 <!-- technical-bibtex-start -->
 * BibTeX:
 * <pre>
 * &#64;misc{Wikipedia2004,
 *    author = {Wikipedia},
 *    title = {Discrete wavelet transform},
 *    year = {2004},
 *    HTTP = {http://en.wikipedia.org/wiki/Discrete_wavelet_transform}
 * }
 * 
 * &#64;misc{Sandberg2000,
 *    address = {University of Colorado at Boulder, USA},
 *    author = {Kristian Sandberg},
 *    institution = {Dept. of Applied Mathematics},
 *    title = {The Haar wavelet transform},
 *    year = {2000},
 *    HTTP = {http://amath.colorado.edu/courses/5720/2000Spr/Labs/Haar/haar.html}
 * }
 * </pre>
 * <p/>
 <!-- technical-bibtex-end -->
 *
 <!-- options-start -->
 * Valid options are: <p/>
 * 
 * <pre> -D
 *  Turns on output of debugging information.</pre>
 * 
 * <pre> -A &lt;Haar&gt;
 *  The algorithm to use.
 *  (default: HAAR)</pre>
 * 
 * <pre> -P &lt;Zero&gt;
 *  The padding to use.
 *  (default: ZERO)</pre>
 * 
 * <pre> -F &lt;filter specification&gt;
 *  The filter to use as preprocessing step (classname and options).
 *  (default: MultiFilter with ReplaceMissingValues and Normalize)</pre>
 * 
 * <pre> 
 * Options specific to filter weka.filters.MultiFilter ('-F'):
 * </pre>
 * 
 * <pre> -D
 *  Turns on output of debugging information.</pre>
 * 
 * <pre> -F &lt;classname [options]&gt;
 *  A filter to apply (can be specified multiple times).</pre>
 * 
 <!-- options-end -->
 *
 * @author FracPete (fracpete at waikato dot ac dot nz)
 * @version $Revision: 1.2 $
 */
public class Wavelet
  extends SimpleBatchFilter 
  implements TechnicalInformationHandler {

  /** for serialization */
  static final long serialVersionUID = -3335106965521265631L;

  /** the type of algorithm: Haar wavelet */
  public static final int ALGORITHM_HAAR = 0;
  /** the types of algorithm */
  public static final Tag[] TAGS_ALGORITHM = {
    new Tag(ALGORITHM_HAAR, "Haar")
  };

  /** the type of padding: Zero padding */
  public static final int PADDING_ZERO = 0;
  /** the types of padding */
  public static final Tag[] TAGS_PADDING = {
    new Tag(PADDING_ZERO, "Zero")
  };

  /** an optional filter for preprocessing of the data */
  protected Filter m_Filter = null;
  
  /** the type of algorithm */
  protected int m_Algorithm = ALGORITHM_HAAR;
  
  /** the type of padding */
  protected int m_Padding = PADDING_ZERO;
  
  /**
   * default constructor
   */
  public Wavelet() {
    super();
    
    m_Filter = new MultiFilter();
    ((MultiFilter) m_Filter).setFilters(
	new Filter[]{
	    new weka.filters.unsupervised.attribute.ReplaceMissingValues(),
	    new weka.filters.unsupervised.attribute.Normalize()
	    });
  }
  
  /**
   * Returns a string describing this classifier.
   *
   * @return      a description of the classifier suitable for
   *              displaying in the explorer/experimenter gui
   */
  public String globalInfo() {
    return 
        "A filter for wavelet transformation.\n\n"
      + "For more information see:\n\n"
      + getTechnicalInformation().toString();
  }

  /**
   * Returns an instance of a TechnicalInformation object, containing 
   * detailed information about the technical background of this class,
   * e.g., paper reference or book this class is based on.
   * 
   * @return the technical information about this class
   */
  public TechnicalInformation getTechnicalInformation() {
    TechnicalInformation 	result;
    TechnicalInformation 	additional;
    
    result = new TechnicalInformation(Type.MISC);
    result.setValue(Field.AUTHOR, "Wikipedia");
    result.setValue(Field.YEAR, "2004");
    result.setValue(Field.TITLE, "Discrete wavelet transform");
    result.setValue(Field.HTTP, "http://en.wikipedia.org/wiki/Discrete_wavelet_transform");
    
    additional = result.add(Type.MISC);
    additional.setValue(Field.AUTHOR, "Kristian Sandberg");
    additional.setValue(Field.YEAR, "2000");
    additional.setValue(Field.TITLE, "The Haar wavelet transform");
    additional.setValue(Field.INSTITUTION, "Dept. of Applied Mathematics");
    additional.setValue(Field.ADDRESS, "University of Colorado at Boulder, USA");
    additional.setValue(Field.HTTP, "http://amath.colorado.edu/courses/5720/2000Spr/Labs/Haar/haar.html");
    
    return result;
  }

  /**
   * Gets an enumeration describing the available options.
   *
   * @return an enumeration of all the available options.
   */
  public Enumeration listOptions() {
    Vector		result;
    Enumeration		enm;
    String		param;
    SelectedTag		tag;
    int			i;

    result = new Vector();

    enm = super.listOptions();
    while (enm.hasMoreElements())
      result.addElement(enm.nextElement());

    param = "";
    for (i = 0; i < TAGS_ALGORITHM.length; i++) {
      if (i > 0)
	param += "|";
      tag = new SelectedTag(TAGS_ALGORITHM[i].getID(), TAGS_ALGORITHM);
      param += tag.getSelectedTag().getReadable();
    }
    result.addElement(new Option(
	"\tThe algorithm to use.\n"
	+ "\t(default: HAAR)",
	"A", 1, "-A <" + param + ">"));

    param = "";
    for (i = 0; i < TAGS_PADDING.length; i++) {
      if (i > 0)
	param += "|";
      tag = new SelectedTag(TAGS_PADDING[i].getID(), TAGS_PADDING);
      param += tag.getSelectedTag().getReadable();
    }
    result.addElement(new Option(
	"\tThe padding to use.\n"
	+ "\t(default: ZERO)",
	"P", 1, "-P <" + param + ">"));

    result.addElement(new Option(
	"\tThe filter to use as preprocessing step (classname and options).\n"
	+ "\t(default: MultiFilter with ReplaceMissingValues and Normalize)",
	"F", 1, "-F <filter specification>"));

    if (getFilter() instanceof OptionHandler) {
      result.addElement(new Option(
	  "",
	  "", 0, "\nOptions specific to filter "
	  + getFilter().getClass().getName() + " ('-F'):"));
      
      enm = ((OptionHandler) getFilter()).listOptions();
      while (enm.hasMoreElements())
	result.addElement(enm.nextElement());
    }

    return result.elements();
  }

  /**
   * returns the options of the current setup
   *
   * @return      the current options
   */
  public String[] getOptions() {
    int       i;
    Vector    result;
    String[]  options;

    result = new Vector();
    options = super.getOptions();
    for (i = 0; i < options.length; i++)
      result.add(options[i]);

    result.add("-A");
    result.add("" + getAlgorithm().getSelectedTag().getReadable());

    result.add("-P");
    result.add("" + getPadding().getSelectedTag().getReadable());

    result.add("-F");
    if (getFilter() instanceof OptionHandler)
      result.add(
	  getFilter().getClass().getName() 
	+ " " 
	+ Utils.joinOptions(((OptionHandler) getFilter()).getOptions()));
    else
      result.add(
	  getFilter().getClass().getName());

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

  /**
   * Parses the options for this object. <p/>
   *
   <!-- options-start -->
   * Valid options are: <p/>
   * 
   * <pre> -D
   *  Turns on output of debugging information.</pre>
   * 
   * <pre> -A &lt;Haar&gt;
   *  The algorithm to use.
   *  (default: HAAR)</pre>
   * 
   * <pre> -P &lt;Zero&gt;
   *  The padding to use.
   *  (default: ZERO)</pre>
   * 
   * <pre> -F &lt;filter specification&gt;
   *  The filter to use as preprocessing step (classname and options).
   *  (default: MultiFilter with ReplaceMissingValues and Normalize)</pre>
   * 
   * <pre> 
   * Options specific to filter weka.filters.MultiFilter ('-F'):
   * </pre>
   * 
   * <pre> -D
   *  Turns on output of debugging information.</pre>
   * 
   * <pre> -F &lt;classname [options]&gt;
   *  A filter to apply (can be specified multiple times).</pre>
   * 
   <!-- options-end -->
   *
   * @param options	the options to use
   * @throws Exception	if the option setting fails
   */
  public void setOptions(String[] options) throws Exception {
    String	tmpStr;
    String[]	tmpOptions;
    Filter	filter;

    super.setOptions(options);

    tmpStr = Utils.getOption("A", options);
    if (tmpStr.length() != 0)
      setAlgorithm(new SelectedTag(tmpStr, TAGS_ALGORITHM));
    else
      setAlgorithm(new SelectedTag(ALGORITHM_HAAR, TAGS_ALGORITHM));

    tmpStr = Utils.getOption("P", options);
    if (tmpStr.length() != 0)
      setPadding(new SelectedTag(tmpStr, TAGS_PADDING));
    else
      setPadding(new SelectedTag(PADDING_ZERO, TAGS_PADDING));

    tmpStr     = Utils.getOption("F", options);
    tmpOptions = Utils.splitOptions(tmpStr);