normalize.java

来自「Weka」· Java 代码 · 共 570 行 · 第 1/2 页

/*
 *    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.
 */

/*
 *    Normalize.java
 *    Copyright (C) 1999 University of Waikato, Hamilton, New Zealand
 *
 */

package weka.filters.unsupervised.attribute;

import weka.core.Capabilities;
import weka.core.Instance;
import weka.core.Instances;
import weka.core.Option;
import weka.core.OptionHandler;
import weka.core.SparseInstance;
import weka.core.Utils;
import weka.core.Capabilities.Capability;
import weka.filters.Sourcable;
import weka.filters.UnsupervisedFilter;

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

/** 
 <!-- globalinfo-start -->
 * Normalizes all numeric values in the given dataset (apart from the class attribute, if set). The resulting values are by default in [0,1] for the data used to compute the normalization intervals. But with the scale and translation parameters one can change that, e.g., with scale = 2.0 and translation = -1.0 you get values in the range [-1,+1].
 * <p/>
 <!-- globalinfo-end -->
 *
 <!-- options-start -->
 * Valid options are: <p/>
 * 
 * <pre> -unset-class-temporarily
 *  Unsets the class index temporarily before the filter is
 *  applied to the data.
 *  (default: no)</pre>
 * 
 * <pre> -S &lt;num&gt;
 *  The scaling factor for the output range.
 *  (default: 1.0)</pre>
 * 
 * <pre> -T &lt;num&gt;
 *  The translation of the output range.
 *  (default: 0.0)</pre>
 * 
 <!-- options-end -->
 * 
 * @author Eibe Frank ([e-mail]) 
 * @author FracPete (fracpete at waikato dot ac dot nz)
 * @version $Revision: 1.12 $
 */
public class Normalize 
  extends PotentialClassIgnorer 
  implements UnsupervisedFilter, Sourcable, OptionHandler {
  
  /** for serialization. */
  static final long serialVersionUID = -8158531150984362898L;

  /** The minimum values for numeric attributes. */
  protected double[] m_MinArray;
  
  /** The maximum values for numeric attributes. */
  protected double[] m_MaxArray;

  /** The translation of the output range. */
  protected double m_Translation = 0;
  
  /** The scaling factor of the output range. */
  protected double m_Scale = 1.0;
  
  /**
   * Returns a string describing this filter.
   *
   * @return 		a description of the filter suitable for
   * 			displaying in the explorer/experimenter gui
   */
  public String globalInfo() {
    return 
        "Normalizes all numeric values in the given dataset (apart from the "
      + "class attribute, if set). The resulting values are by default "
      + "in [0,1] for the data used to compute the normalization intervals. "
      + "But with the scale and translation parameters one can change that, "
      + "e.g., with scale = 2.0 and translation = -1.0 you get values in the "
      + "range [-1,+1].";
  }

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

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

    result.addElement(new Option(
	"\tThe scaling factor for the output range.\n"
	+ "\t(default: 1.0)",
	"S", 1, "-S <num>"));

    result.addElement(new Option(
	"\tThe translation of the output range.\n"
	+"\t(default: 0.0)",
	"T", 1,"-T <num>"));

    return result.elements();
  }


  /**
   * Parses a given list of options. <p/>
   * 
   <!-- options-start -->
   * Valid options are: <p/>
   * 
   * <pre> -unset-class-temporarily
   *  Unsets the class index temporarily before the filter is
   *  applied to the data.
   *  (default: no)</pre>
   * 
   * <pre> -S &lt;num&gt;
   *  The scaling factor for the output range.
   *  (default: 1.0)</pre>
   * 
   * <pre> -T &lt;num&gt;
   *  The translation of the output range.
   *  (default: 0.0)</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;

    tmpStr = Utils.getOption('S', options);
    if (tmpStr.length() != 0)
      setScale(Double.parseDouble(tmpStr));
    else
      setScale(1.0);
    
    tmpStr = Utils.getOption('T', options);
    if (tmpStr.length() != 0)
      setTranslation(Double.parseDouble(tmpStr));
    else
      setTranslation(0.0);

    if (getInputFormat() != null)
      setInputFormat(getInputFormat());
  }

  /**
   * Gets the current settings of the filter.
   *
   * @return an array of strings suitable for passing to setOptions
   */
  public String[] getOptions() {
    Vector<String>	result;
    
    result = new Vector<String>();

    result.add("-S");
    result.add("" + getScale());

    result.add("-T");
    result.add("" + getTranslation());
    
    return result.toArray(new String[result.size()]);
  }

  /** 
   * Returns the Capabilities of this filter.
   *
   * @return            the capabilities of this object
   * @see               Capabilities
   */
  public Capabilities getCapabilities() {
    Capabilities result = super.getCapabilities();

    // attributes
    result.enableAllAttributes();
    result.enable(Capability.MISSING_VALUES);
    
    // class
    result.enableAllClasses();
    result.enable(Capability.MISSING_CLASS_VALUES);
    result.enable(Capability.NO_CLASS);
    
    return result;
  }

  /**
   * Sets the format of the input instances.
   *
   * @param instanceInfo 	an Instances object containing the input 
   * 				instance structure (any instances contained in 
   * 				the object are ignored - only the structure is 
   * 				required).
   * @return 			true if the outputFormat may be collected 
   * 				immediately
   * @throws Exception 		if the input format can't be set successfully
   */
  public boolean setInputFormat(Instances instanceInfo) 
       throws Exception {

    super.setInputFormat(instanceInfo);
    setOutputFormat(instanceInfo);
    m_MinArray = m_MaxArray = null;
    return true;
  }

  /**
   * Input an instance for filtering. Filter requires all
   * training instances be read before producing output.
   *
   * @param instance 	the input instance
   * @return 		true if the filtered instance may now be
   * 			collected with output().
   * @throws Exception 	if an error occurs
   * @throws IllegalStateException 	if no input format has been set.
   */
  public boolean input(Instance instance) throws Exception {
    if (getInputFormat() == null)
      throw new IllegalStateException("No input instance format defined");
    
    if (m_NewBatch) {
      resetQueue();
      m_NewBatch = false;
    }
    if (m_MinArray == null) {
      bufferInput(instance);
      return false;
    }
    else {
      convertInstance(instance);
      return true;
    }
  }

  /**
   * Signify that this batch of input to the filter is finished. 
   * If the filter requires all instances prior to filtering,
   * output() may now be called to retrieve the filtered instances.
   *
   * @return 		true if there are instances pending output
   * @throws Exception 	if an error occurs
   * @throws IllegalStateException 	if no input structure has been defined
   */
  public boolean batchFinished() throws Exception {
    if (getInputFormat() == null)
      throw new IllegalStateException("No input instance format defined");

    if (m_MinArray == null) {
      Instances input = getInputFormat();
      // Compute minimums and maximums
      m_MinArray = new double[input.numAttributes()];
      m_MaxArray = new double[input.numAttributes()];
      for (int i = 0; i < input.numAttributes(); i++)
	m_MinArray[i] = Double.NaN;

      for (int j = 0; j < input.numInstances(); j++) {
	double[] value = input.instance(j).toDoubleArray();
	for (int i = 0; i < input.numAttributes(); i++) {
	  if (input.attribute(i).isNumeric() &&
	      (input.classIndex() != i)) {
	    if (!Instance.isMissingValue(value[i])) {