weka.attributeSelection.ConsistencySubsetEval Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of weka-stable Show documentation
The Waikato Environment for Knowledge Analysis (WEKA), a machine learning workbench. This is the stable version. Apart from bugfixes, this version does not receive any other updates.
There is a newer version: 3.8.6
Show newest version
/*
 *    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.
 */

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

package  weka.attributeSelection;

import weka.core.Capabilities;
import weka.core.Instance;
import weka.core.Instances;
import weka.core.RevisionHandler;
import weka.core.RevisionUtils;
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.supervised.attribute.Discretize;

import java.io.Serializable;
import java.util.BitSet;
import java.util.Enumeration;
import java.util.Hashtable;

/** 
 
 * ConsistencySubsetEval :

 * 

 * Evaluates the worth of a subset of attributes by the level of consistency in the class values when the training instances are projected onto the subset of attributes. 

 * 

 * Consistency of any subset can never be lower than that of the full set of attributes, hence the usual practice is to use this subset evaluator in conjunction with a Random or Exhaustive search which looks for the smallest subset with consistency equal to that of the full set of attributes.

 * 

 * For more information see:

 * 

 * H. Liu, R. Setiono: A probabilistic approach to feature selection - A filter solution. In: 13th International Conference on Machine Learning, 319-327, 1996.
 * 
 
 *
 
 * BibTeX:
 * 
 * @inproceedings{Liu1996,
 *    author = {H. Liu and R. Setiono},
 *    booktitle = {13th International Conference on Machine Learning},
 *    pages = {319-327},
 *    title = {A probabilistic approach to feature selection - A filter solution},
 *    year = {1996}
 * }
 * 
 * 
 
 *
 * @author Mark Hall ([email protected])
 * @version $Revision: 5511 $
 * @see Discretize
 */
public class ConsistencySubsetEval 
  extends ASEvaluation
  implements SubsetEvaluator,
             TechnicalInformationHandler {
  
  /** for serialization */
  static final long serialVersionUID = -2880323763295270402L;
  
  /** training instances */
  private Instances m_trainInstances;

  /** class index */
  private int m_classIndex;

  /** number of attributes in the training data */
  private int m_numAttribs;

  /** number of instances in the training data */
  private int m_numInstances;

  /** Discretise numeric attributes */
  private Discretize m_disTransform;

  /** Hash table for evaluating feature subsets */
  private Hashtable m_table;

  /**
   * Class providing keys to the hash table.
   */
  public class hashKey 
    implements Serializable, RevisionHandler {
    
    /** for serialization */
    static final long serialVersionUID = 6144138512017017408L;
    
    /** Array of attribute values for an instance */
    private double [] attributes;
    
    /** True for an index if the corresponding attribute value is missing. */
    private boolean [] missing;

    /** The key */
    private int key;

    /**
     * Constructor for a hashKey
     *
     * @param t an instance from which to generate a key
     * @param numAtts the number of attributes
     * @throws Exception if something goes wrong
     */
    public hashKey(Instance t, int numAtts) throws Exception {

      int i;
      int cindex = t.classIndex();

      key = -999;
      attributes = new double [numAtts];
      missing = new boolean [numAtts];
      for (i=0;i