weka.attributeSelection.OneRAttributeEval Maven / Gradle / Ivy

Show more of this group Show more artifacts with this name
Show all versions of weka-dev Show documentation
The Waikato Environment for Knowledge Analysis (WEKA), a machine learning workbench. This version represents the developer version, the "bleeding edge" of development, you could say. New functionality gets added to this version.
There is a newer version: 3.9.6
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 3 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, see .
 */

/*
 *    OneRAttributeEval.java
 *    Copyright (C) 1999-2012 University of Waikato, Hamilton, New Zealand
 *
 */

package weka.attributeSelection;

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

import weka.classifiers.AbstractClassifier;
import weka.classifiers.Classifier;
import weka.classifiers.Evaluation;
import weka.core.Capabilities;
import weka.core.Capabilities.Capability;
import weka.core.Instances;
import weka.core.Option;
import weka.core.OptionHandler;
import weka.core.RevisionUtils;
import weka.core.Utils;
import weka.filters.Filter;
import weka.filters.unsupervised.attribute.Remove;

/**
 *  OneRAttributeEval :

 * 

 * Evaluates the worth of an attribute by using the OneR classifier.

 * 
 * 
 * 
 *  Valid options are:
 * 

 * 
 * 
 * -S <seed>
 *  Random number seed for cross validation
 *  (default = 1)
 * 
 * 
 *  * -F <folds>
 *  Number of folds for cross validation
 *  (default = 10)
 * 
 * 
 *  * -D
 *  Use training data for evaluation rather than cross validaton
 * 
 * 
 *  * -B <minimum bucket size>
 *  Minimum number of objects in a bucket
 *  (passed on to OneR, default = 6)
 * 
 * 
 * 
 * 
 * @author Mark Hall ([email protected])
 * @version $Revision: 10172 $
 */
public class OneRAttributeEval extends ASEvaluation implements
  AttributeEvaluator, OptionHandler {

  /** for serialization */
  static final long serialVersionUID = 4386514823886856980L;

  /** The training instances */
  private Instances m_trainInstances;

  /** Random number seed */
  private int m_randomSeed;

  /** Number of folds for cross validation */
  private int m_folds;

  /** Use training data to evaluate merit rather than x-val */
  private boolean m_evalUsingTrainingData;

  /** Passed on to OneR */
  private int m_minBucketSize;

  /**
   * Returns a string describing this attribute evaluator
   * 
   * @return a description of the evaluator suitable for displaying in the
   *         explorer/experimenter gui
   */
  public String globalInfo() {
    return "OneRAttributeEval :\n\nEvaluates the worth of an attribute by "
      + "using the OneR classifier.\n";
  }

  /**
   * Returns a string for this option suitable for display in the gui as a tip
   * text
   * 
   * @return a string describing this option
   */
  public String seedTipText() {
    return "Set the seed for use in cross validation.";
  }

  /**
   * Set the random number seed for cross validation
   * 
   * @param seed the seed to use
   */
  public void setSeed(int seed) {
    m_randomSeed = seed;
  }

  /**
   * Get the random number seed
   * 
   * @return an int value
   */
  public int getSeed() {
    return m_randomSeed;
  }

  /**
   * Returns a string for this option suitable for display in the gui as a tip
   * text
   * 
   * @return a string describing this option
   */
  public String foldsTipText() {
    return "Set the number of folds for cross validation.";
  }

  /**
   * Set the number of folds to use for cross validation
   * 
   * @param folds the number of folds
   */
  public void setFolds(int folds) {
    m_folds = folds;
    if (m_folds < 2) {
      m_folds = 2;
    }
  }

  /**
   * Get the number of folds used for cross validation
   * 
   * @return the number of folds
   */
  public int getFolds() {
    return m_folds;
  }

  /**
   * Returns a string for this option suitable for display in the gui as a tip
   * text
   * 
   * @return a string describing this option
   */
  public String evalUsingTrainingDataTipText() {
    return "Use the training data to evaluate attributes rather than "
      + "cross validation.";
  }

  /**
   * Use the training data to evaluate attributes rather than cross validation
   * 
   * @param e true if training data is to be used for evaluation
   */
  public void setEvalUsingTrainingData(boolean e) {
    m_evalUsingTrainingData = e;
  }

  /**
   * Returns a string for this option suitable for display in the gui as a tip
   * text
   * 
   * @return a string describing this option
   */
  public String minimumBucketSizeTipText() {
    return "The minimum number of objects in a bucket " + "(passed to OneR).";
  }

  /**
   * Set the minumum bucket size used by OneR
   * 
   * @param minB the minimum bucket size to use
   */
  public void setMinimumBucketSize(int minB) {
    m_minBucketSize = minB;
  }

  /**
   * Get the minimum bucket size used by oneR
   * 
   * @return the minimum bucket size used
   */
  public int getMinimumBucketSize() {
    return m_minBucketSize;
  }

  /**
   * Returns true if the training data is to be used for evaluation
   * 
   * @return true if training data is to be used for evaluation
   */
  public boolean getEvalUsingTrainingData() {
    return m_evalUsingTrainingData;
  }

  /**
   * Returns an enumeration describing the available options.
   * 
   * @return an enumeration of all the available options.
   */
  @Override
  public Enumeration