weka.clusterers.CheckClusterer Maven / Gradle / Ivy

Go to download
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 .
 */

/*
 * CheckClusterer.java
 * Copyright (C) 2006-2012 University of Waikato, Hamilton, New Zealand
 *
 */

package weka.clusterers;

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

import weka.core.CheckScheme;
import weka.core.Instance;
import weka.core.Instances;
import weka.core.MultiInstanceCapabilitiesHandler;
import weka.core.Option;
import weka.core.OptionHandler;
import weka.core.RevisionUtils;
import weka.core.SerializationHelper;
import weka.core.TestInstances;
import weka.core.Utils;
import weka.core.WeightedInstancesHandler;

/**
 * Class for examining the capabilities and finding problems with clusterers. If
 * you implement a clusterer using the WEKA.libraries, you should run the checks
 * on it to ensure robustness and correct operation. Passing all the tests of
 * this object does not mean bugs in the clusterer don't exist, but this will
 * help find some common ones.
 * 
 * 
 * Typical usage:
 * 

 * java weka.clusterers.CheckClusterer -W clusterer_name 
 * -- clusterer_options 
 * 

 * 
 * CheckClusterer reports on the following:
 * 

 * Clusterer abilities
 * 
 * Possible command line options to the clusterer
 * Whether the clusterer can predict nominal, numeric, string, date or
 * relational class attributes.
 * Whether the clusterer can handle numeric predictor attributes
 * Whether the clusterer can handle nominal predictor attributes
 * Whether the clusterer can handle string predictor attributes
 * Whether the clusterer can handle date predictor attributes
 * Whether the clusterer can handle relational predictor attributes
 * Whether the clusterer can handle multi-instance data
 * Whether the clusterer can handle missing predictor values
 * Whether the clusterer can handle instance weights
 * 
 * 
 * Correct functioning
 * 
 * Correct initialisation during buildClusterer (i.e. no result changes when
 * buildClusterer called repeatedly)
 * Whether the clusterer alters the data pased to it (number of instances,
 * instance order, instance weights, etc)
 * 
 * 
 * Degenerate cases
 * 
 * building clusterer with zero training instances
 * all but one predictor attribute values missing
 * all predictor attribute values missing
 * all but one class values missing
 * all class values missing
 * 
 * 
 * 
 * Running CheckClusterer with the debug option set will output the training
 * dataset for any failed tests.
 * 
 * 
 * The weka.clusterers.AbstractClustererTest uses this class to
 * test all the clusterers. Any changes here, have to be checked in that
 * abstract test class, too.
 * 

 * 
 *  Valid options are:
 * 

 * 
 * 
 * -D
 *  Turn on debugging output.
 * 
 * 
 *  * -S
 *  Silent mode - prints nothing to stdout.
 * 
 * 
 *  * -N <num>
 *  The number of instances in the datasets (default 20).
 * 
 * 
 *  * -nominal <num>
 *  The number of nominal attributes (default 2).
 * 
 * 
 *  * -nominal-values <num>
 *  The number of values for nominal attributes (default 1).
 * 
 * 
 *  * -numeric <num>
 *  The number of numeric attributes (default 1).
 * 
 * 
 *  * -string <num>
 *  The number of string attributes (default 1).
 * 
 * 
 *  * -date <num>
 *  The number of date attributes (default 1).
 * 
 * 
 *  * -relational <num>
 *  The number of relational attributes (default 1).
 * 
 * 
 *  * -num-instances-relational <num>
 *  The number of instances in relational/bag attributes (default 10).
 * 
 * 
 *  * -words <comma-separated-list>
 *  The words to use in string attributes.
 * 
 * 
 *  * -word-separators <chars>
 *  The word separators to use in string attributes.
 * 
 * 
 *  * -W
 *  Full name of the clusterer analyzed.
 *  eg: weka.clusterers.SimpleKMeans
 *  (default weka.clusterers.SimpleKMeans)
 * 
 * 
 *  * Options specific to clusterer weka.clusterers.SimpleKMeans:
 * 
 * 
 *  * -N <num>
 *  number of clusters.
 *  (default 2).
 * 
 * 
 *  * -V
 *  Display std. deviations for centroids.
 * 
 * 
 *  * -M
 *  Replace missing values with mean/mode.
 * 
 * 
 *  * -S <num>
 *  Random number seed.
 *  (default 10)
 * 
 * 
 * 
 * 
 * Options after -- are passed to the designated clusterer.
 * 
 * 
 * @author Len Trigg ([email protected])
 * @author FracPete (fracpete at waikato dot ac dot nz)
 * @version $Revision: 11451 $
 * @see TestInstances
 */
public class CheckClusterer extends CheckScheme {

  /*
   * Note about test methods: - methods return array of booleans - first index:
   * success or not - second index: acceptable or not (e.g., Exception is OK)
   * 
   * FracPete (fracpete at waikato dot ac dot nz)
   */

  /*** The clusterer to be examined */
  protected Clusterer m_Clusterer = new SimpleKMeans();

  /**
   * default constructor
   */
  public CheckClusterer() {
    super();

    setNumInstances(40);
  }

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

   * 
   *  Valid options are:
   * 

   * 
   * 
   * -D
   *  Turn on debugging output.
   * 
   * 
   *    * -S
   *  Silent mode - prints nothing to stdout.
   * 
   * 
   *    * -N <num>
   *  The number of instances in the datasets (default 20).
   * 
   * 
   *    * -nominal <num>
   *  The number of nominal attributes (default 2).
   * 
   * 
   *    * -nominal-values <num>
   *  The number of values for nominal attributes (default 1).
   * 
   * 
   *    * -numeric <num>
   *  The number of numeric attributes (default 1).
   * 
   * 
   *    * -string <num>
   *  The number of string attributes (default 1).
   * 
   * 
   *    * -date <num>
   *  The number of date attributes (default 1).
   * 
   * 
   *    * -relational <num>
   *  The number of relational attributes (default 1).
   * 
   * 
   *    * -num-instances-relational <num>
   *  The number of instances in relational/bag attributes (default 10).
   * 
   * 
   *    * -words <comma-separated-list>
   *  The words to use in string attributes.
   * 
   * 
   *    * -word-separators <chars>
   *  The word separators to use in string attributes.
   * 
   * 
   *    * -W
   *  Full name of the clusterer analyzed.
   *  eg: weka.clusterers.SimpleKMeans
   *  (default weka.clusterers.SimpleKMeans)
   * 
   * 
   *    * Options specific to clusterer weka.clusterers.SimpleKMeans:
   * 
   * 
   *    * -N <num>
   *  number of clusters.
   *  (default 2).
   * 
   * 
   *    * -V
   *  Display std. deviations for centroids.
   * 
   * 
   *    * -M
   *  Replace missing values with mean/mode.
   * 
   * 
   *    * -S <num>
   *  Random number seed.
   *  (default 10)
   * 
   * 
   * 
   * 
   * @param options the list of options as an array of strings
   * @throws Exception if an option is not supported
   */
  @Override
  public void setOptions(String[] options) throws Exception {
    String tmpStr;

    tmpStr = Utils.getOption('N', options);

    if (tmpStr.length() != 0) {
      setNumInstances(Integer.parseInt(tmpStr));
    } else {
      setNumInstances(40);
    }

    super.setOptions(options);

    tmpStr = Utils.getOption('W', options);
    if (tmpStr.length() == 0) {
      tmpStr = weka.clusterers.SimpleKMeans.class.getName();
    }
    setClusterer((Clusterer) forName("weka.clusterers", Clusterer.class,
      tmpStr, Utils.partitionOptions(options)));

    Utils.checkForRemainingOptions(options);
  }

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

    if (getClusterer() != null) {
      result.add("-W");
      result.add(getClusterer().getClass().getName());
    }

    Collections.addAll(result, super.getOptions());

    if ((m_Clusterer != null) && (m_Clusterer instanceof OptionHandler)) {
      String[] options = ((OptionHandler) m_Clusterer).getOptions();

      if (options.length > 0) {
        result.add("--");
        Collections.addAll(result, options);
      }
    }

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

  /**
   * Begin the tests, reporting results to System.out
   */
  @Override
  public void doTests() {

    if (getClusterer() == null) {
      println("\n=== No clusterer set ===");
      return;
    }
    println("\n=== Check on Clusterer: " + getClusterer().getClass().getName()
      + " ===\n");

    // Start tests
    println("--> Checking for interfaces");
    canTakeOptions();
    boolean updateable = updateableClusterer()[0];
    boolean weightedInstancesHandler = weightedInstancesHandler()[0];
    boolean multiInstanceHandler = multiInstanceHandler()[0];
    println("--> Clusterer tests");
    declaresSerialVersionUID();
    runTests(weightedInstancesHandler, multiInstanceHandler, updateable);
  }

  /**
   * Set the clusterer for testing.
   * 
   * @param newClusterer the Clusterer to use.
   */
  public void setClusterer(Clusterer newClusterer) {
    m_Clusterer = newClusterer;
  }

  /**
   * Get the clusterer used as the clusterer
   * 
   * @return the clusterer used as the clusterer
   */
  public Clusterer getClusterer() {
    return m_Clusterer;
  }

  /**
   * Run a battery of tests
   * 
   * @param weighted true if the clusterer says it handles weights
   * @param multiInstance true if the clusterer is a multi-instance clusterer
   * @param updateable true if the classifier is updateable
   */
  protected void runTests(boolean weighted, boolean multiInstance,
    boolean updateable) {

    boolean PNom = canPredict(true, false, false, false, false, multiInstance)[0];
    boolean PNum = canPredict(false, true, false, false, false, multiInstance)[0];
    boolean PStr = canPredict(false, false, true, false, false, multiInstance)[0];
    boolean PDat = canPredict(false, false, false, true, false, multiInstance)[0];
    boolean PRel;
    if (!multiInstance) {
      PRel = canPredict(false, false, false, false, true, multiInstance)[0];
    } else {
      PRel = false;
    }

    if (PNom || PNum || PStr || PDat || PRel) {
      if (weighted) {
        instanceWeights(PNom, PNum, PStr, PDat, PRel, multiInstance);
      }

      canHandleZeroTraining(PNom, PNum, PStr, PDat, PRel, multiInstance);
      boolean handleMissingPredictors = canHandleMissing(PNom, PNum, PStr,
        PDat, PRel, multiInstance, true, 20)[0];
      if (handleMissingPredictors) {
        canHandleMissing(PNom, PNum, PStr, PDat, PRel, multiInstance, true, 100);
      }

      correctBuildInitialisation(PNom, PNum, PStr, PDat, PRel, multiInstance);
      datasetIntegrity(PNom, PNum, PStr, PDat, PRel, multiInstance,
        handleMissingPredictors);
      if (updateable) {
        updatingEquality(PNom, PNum, PStr, PDat, PRel, multiInstance);
      }
    }
  }

  /**
   * Checks whether the scheme can take command line options.
   * 
   * @return index 0 is true if the clusterer can take options
   */
  protected boolean[] canTakeOptions() {

    boolean[] result = new boolean[2];

    print("options...");
    if (m_Clusterer instanceof OptionHandler) {
      println("yes");
      if (m_Debug) {
        println("\n=== Full report ===");
        Enumeration