weka.experiment.ClassifierSplitEvaluator 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 .
 */

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

package weka.experiment;

import java.io.ByteArrayOutputStream;
import java.io.ObjectOutputStream;
import java.io.ObjectStreamClass;
import java.io.Serializable;
import java.lang.management.ManagementFactory;
import java.lang.management.ThreadMXBean;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.Collections;
import java.util.Enumeration;
import java.util.List;
import java.util.Vector;

import weka.classifiers.AbstractClassifier;
import weka.classifiers.Classifier;
import weka.classifiers.Evaluation;
import weka.classifiers.evaluation.AbstractEvaluationMetric;
import weka.classifiers.rules.ZeroR;
import weka.core.AdditionalMeasureProducer;
import weka.core.Attribute;
import weka.core.Instances;
import weka.core.Option;
import weka.core.OptionHandler;
import weka.core.RevisionHandler;
import weka.core.RevisionUtils;
import weka.core.Summarizable;
import weka.core.Utils;

/**
 *  A SplitEvaluator that produces results for a
 * classification scheme on a nominal class attribute.
 * 
 * 
 *
 *  Valid options are:
 * 

 *
 * 
 * -W <class name>
 *  The full class name of the classifier.
 *  eg: weka.classifiers.bayes.NaiveBayes
 * 
 *
 *  * -C <index>
 *  The index of the class for which IR statistics
 *  are to be output. (default 1)
 * 
 *
 *  * -I <index>
 *  The index of an attribute to output in the
 *  results. This attribute should identify an
 *  instance in order to know which instances are
 *  in the test set of a cross validation. if 0
 *  no output (default 0).
 * 
 *
 *  * -P
 *  Add target and prediction columns to the result
 *  for each fold.
 * 
 *
 *  * -no-size
 *  Skips the determination of sizes (train/test/classifier)
 *  (default: sizes are determined)
 * 
 *
 *  * Options specific to classifier weka.classifiers.rules.ZeroR:
 * 
 *
 *  * -D
 *  If set, classifier is run in debug mode and
 *  may output additional info to the console
 * 
 *
 * 
 *
 * All options after -- will be passed to the classifier.
 *
 * @author Len Trigg ([email protected])
 * @version $Revision: 11323 $
 */
public class ClassifierSplitEvaluator implements SplitEvaluator, OptionHandler,
  AdditionalMeasureProducer, RevisionHandler {

  /** for serialization */
  static final long serialVersionUID = -8511241602760467265L;

  /** The template classifier */
  protected Classifier m_Template = new ZeroR();

  /** The classifier used for evaluation */
  protected Classifier m_Classifier;

  /** Holds the most recently used Evaluation object */
  protected Evaluation m_Evaluation;

  /** The names of any additional measures to look for in SplitEvaluators */
  protected String[] m_AdditionalMeasures = null;

  /**
   * Array of booleans corresponding to the measures in m_AdditionalMeasures
   * indicating which of the AdditionalMeasures the current classifier can
   * produce
   */
  protected boolean[] m_doesProduce = null;

  /**
   * The number of additional measures that need to be filled in after taking
   * into account column constraints imposed by the final destination for
   * results
   */
  protected int m_numberAdditionalMeasures = 0;

  /** Holds the statistics for the most recent application of the classifier */
  protected String m_result = null;

  /** The classifier options (if any) */
  protected String m_ClassifierOptions = "";

  /** The classifier version */
  protected String m_ClassifierVersion = "";

  /** The length of a key */
  private static final int KEY_SIZE = 3;

  /** The length of a result */
  private static final int RESULT_SIZE = 32;

  /** The number of IR statistics */
  private static final int NUM_IR_STATISTICS = 16;

  /** The number of averaged IR statistics */
  private static final int NUM_WEIGHTED_IR_STATISTICS = 10;

  /** The number of unweighted averaged IR statistics */
  private static final int NUM_UNWEIGHTED_IR_STATISTICS = 2;

  /** Class index for information retrieval statistics (default 0) */
  private int m_IRclass = 0;

  /** Flag for prediction and target columns output. */
  private boolean m_predTargetColumn = false;

  /** Attribute index of instance identifier (default -1) */
  private int m_attID = -1;

  /** whether to skip determination of sizes (train/test/classifier). */
  private boolean m_NoSizeDetermination;

  protected final List m_pluginMetrics =
    new ArrayList();
  protected int m_numPluginStatistics = 0;

  /**
   * No args constructor.
   */
  public ClassifierSplitEvaluator() {

    updateOptions();

    List pluginMetrics = AbstractEvaluationMetric
      .getPluginMetrics();
    if (pluginMetrics != null) {
      for (AbstractEvaluationMetric m : pluginMetrics) {
        System.err.println(m.getMetricName());
        if (m.appliesToNominalClass()) {
          m_pluginMetrics.add(m);
          m_numPluginStatistics += m.getStatisticNames().size();
        }
      }
    }
  }

  /**
   * Returns a string describing this split evaluator
   *
   * @return a description of the split evaluator suitable for displaying in the
   *         explorer/experimenter gui
   */
  public String globalInfo() {
    return " A SplitEvaluator that produces results for a classification "
      + "scheme on a nominal class attribute.";
  }

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