checkclassifier.java

Java 编写的多种数据挖掘算法 包括聚类、分类、预处理等

      println("yes");
      result[0] = true;
    }
    else {
      println("no");
      result[0] = false;
    }
    
    return result;
  }
  
  /**
   * Checks basic prediction of the scheme, for simple non-troublesome
   * datasets.
   *
   * @param nominalPredictor if true use nominal predictor attributes
   * @param numericPredictor if true use numeric predictor attributes
   * @param stringPredictor if true use string predictor attributes
   * @param datePredictor if true use date predictor attributes
   * @param relationalPredictor if true use relational predictor attributes
   * @param multiInstance whether multi-instance is needed
   * @param classType the class type (NOMINAL, NUMERIC, etc.)
   * @return index 0 is true if the test was passed, index 1 is true if test 
   *         was acceptable
   */
  protected boolean[] canPredict(
      boolean nominalPredictor,
      boolean numericPredictor, 
      boolean stringPredictor, 
      boolean datePredictor,
      boolean relationalPredictor,
      boolean multiInstance,
      int classType) {
    
    print("basic predict");
    printAttributeSummary(
        nominalPredictor, numericPredictor, stringPredictor, datePredictor, relationalPredictor, multiInstance, classType);
    print("...");
    FastVector accepts = new FastVector();
    accepts.addElement("nominal");
    accepts.addElement("numeric");
    accepts.addElement("string");
    accepts.addElement("date");
    accepts.addElement("relational");
    accepts.addElement("multi-instance");
    accepts.addElement("not in classpath");
    int numTrain = getNumInstances(), numTest = getNumInstances(), 
    numClasses = 2, missingLevel = 0;
    boolean predictorMissing = false, classMissing = false;
    
    return runBasicTest(nominalPredictor, numericPredictor, stringPredictor, 
        datePredictor, relationalPredictor, 
        multiInstance,
        classType, 
        missingLevel, predictorMissing, classMissing,
        numTrain, numTest, numClasses, 
        accepts);
  }
  
  /**
   * Checks whether nominal schemes can handle more than two classes.
   * If a scheme is only designed for two-class problems it should
   * throw an appropriate exception for multi-class problems.
   *
   * @param nominalPredictor if true use nominal predictor attributes
   * @param numericPredictor if true use numeric predictor attributes
   * @param stringPredictor if true use string predictor attributes
   * @param datePredictor if true use date predictor attributes
   * @param relationalPredictor if true use relational predictor attributes
   * @param multiInstance whether multi-instance is needed
   * @param numClasses the number of classes to test
   * @return index 0 is true if the test was passed, index 1 is true if test 
   *         was acceptable
   */
  protected boolean[] canHandleNClasses(
      boolean nominalPredictor,
      boolean numericPredictor, 
      boolean stringPredictor, 
      boolean datePredictor,
      boolean relationalPredictor,
      boolean multiInstance,
      int numClasses) {
    
    print("more than two class problems");
    printAttributeSummary(
        nominalPredictor, numericPredictor, stringPredictor, datePredictor, relationalPredictor, multiInstance, Attribute.NOMINAL);
    print("...");
    FastVector accepts = new FastVector();
    accepts.addElement("number");
    accepts.addElement("class");
    int numTrain = getNumInstances(), numTest = getNumInstances(), 
    missingLevel = 0;
    boolean predictorMissing = false, classMissing = false;
    
    return runBasicTest(nominalPredictor, numericPredictor, stringPredictor, 
                        datePredictor, relationalPredictor, 
                        multiInstance,
                        Attribute.NOMINAL,
                        missingLevel, predictorMissing, classMissing,
                        numTrain, numTest, numClasses, 
                        accepts);
  }
  
  /**
   * Checks whether the scheme can handle class attributes as Nth attribute.
   *
   * @param nominalPredictor if true use nominal predictor attributes
   * @param numericPredictor if true use numeric predictor attributes
   * @param stringPredictor if true use string predictor attributes
   * @param datePredictor if true use date predictor attributes
   * @param relationalPredictor if true use relational predictor attributes
   * @param multiInstance whether multi-instance is needed
   * @param classType the class type (NUMERIC, NOMINAL, etc.)
   * @param classIndex the index of the class attribute (0-based, -1 means last attribute)
   * @return index 0 is true if the test was passed, index 1 is true if test 
   *         was acceptable
   * @see TestInstances#CLASS_IS_LAST
   */
  protected boolean[] canHandleClassAsNthAttribute(
      boolean nominalPredictor,
      boolean numericPredictor, 
      boolean stringPredictor, 
      boolean datePredictor,
      boolean relationalPredictor,
      boolean multiInstance,
      int classType,
      int classIndex) {
    
    if (classIndex == TestInstances.CLASS_IS_LAST)
      print("class attribute as last attribute");
    else
      print("class attribute as " + (classIndex + 1) + ". attribute");
    printAttributeSummary(
        nominalPredictor, numericPredictor, stringPredictor, datePredictor, relationalPredictor, multiInstance, classType);
    print("...");
    FastVector accepts = new FastVector();
    int numTrain = getNumInstances(), numTest = getNumInstances(), numClasses = 2, 
    missingLevel = 0;
    boolean predictorMissing = false, classMissing = false;
    
    return runBasicTest(nominalPredictor, numericPredictor, stringPredictor, 
                        datePredictor, relationalPredictor, 
                        multiInstance,
                        classType,
                        classIndex,
                        missingLevel, predictorMissing, classMissing,
                        numTrain, numTest, numClasses, 
                        accepts);
  }
  
  /**
   * Checks whether the scheme can handle zero training instances.
   *
   * @param nominalPredictor if true use nominal predictor attributes
   * @param numericPredictor if true use numeric predictor attributes
   * @param stringPredictor if true use string predictor attributes
   * @param datePredictor if true use date predictor attributes
   * @param relationalPredictor if true use relational predictor attributes
   * @param multiInstance whether multi-instance is needed
   * @param classType the class type (NUMERIC, NOMINAL, etc.)
   * @return index 0 is true if the test was passed, index 1 is true if test 
   *         was acceptable
   */
  protected boolean[] canHandleZeroTraining(
      boolean nominalPredictor,
      boolean numericPredictor, 
      boolean stringPredictor, 
      boolean datePredictor,
      boolean relationalPredictor,
      boolean multiInstance,
      int classType) {
    
    print("handle zero training instances");
    printAttributeSummary(
        nominalPredictor, numericPredictor, stringPredictor, datePredictor, relationalPredictor, multiInstance, classType);
    print("...");
    FastVector accepts = new FastVector();
    accepts.addElement("train");
    accepts.addElement("value");
    int numTrain = 0, numTest = getNumInstances(), numClasses = 2, 
    missingLevel = 0;
    boolean predictorMissing = false, classMissing = false;
    
    return runBasicTest(
              nominalPredictor, numericPredictor, stringPredictor, 
              datePredictor, relationalPredictor, 
              multiInstance,
              classType, 
              missingLevel, predictorMissing, classMissing,
              numTrain, numTest, numClasses, 
              accepts);
  }
  
  /**
   * Checks whether the scheme correctly initialises models when 
   * buildClassifier is called. This test calls buildClassifier with
   * one training dataset and records performance on a test set. 
   * buildClassifier is then called on a training set with different
   * structure, and then again with the original training set. The
   * performance on the test set is compared with the original results
   * and any performance difference noted as incorrect build initialisation.
   *
   * @param nominalPredictor if true use nominal predictor attributes
   * @param numericPredictor if true use numeric predictor attributes
   * @param stringPredictor if true use string predictor attributes
   * @param datePredictor if true use date predictor attributes
   * @param relationalPredictor if true use relational predictor attributes
   * @param multiInstance whether multi-instance is needed
   * @param classType the class type (NUMERIC, NOMINAL, etc.)
   * @return index 0 is true if the test was passed, index 1 is true if the
   *         scheme performs worse than ZeroR, but without error (index 0 is
   *         false)
   */
  protected boolean[] correctBuildInitialisation(
      boolean nominalPredictor,
      boolean numericPredictor, 
      boolean stringPredictor, 
      boolean datePredictor,
      boolean relationalPredictor,
      boolean multiInstance,
      int classType) {

    boolean[] result = new boolean[2];
    
    print("correct initialisation during buildClassifier");
    printAttributeSummary(
        nominalPredictor, numericPredictor, stringPredictor, datePredictor, relationalPredictor, multiInstance, classType);
    print("...");
    int numTrain = getNumInstances(), numTest = getNumInstances(), 
    numClasses = 2, missingLevel = 0;
    boolean predictorMissing = false, classMissing = false;
    
    Instances train1 = null;
    Instances test1 = null;
    Instances train2 = null;
    Instances test2 = null;
    Classifier classifier = null;
    Evaluation evaluation1A = null;
    Evaluation evaluation1B = null;
    Evaluation evaluation2 = null;
    boolean built = false;
    int stage = 0;
    try {
      
      // Make two sets of train/test splits with different 
      // numbers of attributes
      train1 = makeTestDataset(42, numTrain, 
                               nominalPredictor ? 2 : 0,
                               numericPredictor ? 1 : 0, 
                               stringPredictor ? 1 : 0, 
                               datePredictor ? 1 : 0, 
                               relationalPredictor ? 1 : 0, 
                               numClasses, 
                               classType,
                               multiInstance);
      train2 = makeTestDataset(84, numTrain, 
                               nominalPredictor ? 3 : 0,
                               numericPredictor ? 2 : 0, 
                               stringPredictor ? 1 : 0, 
                               datePredictor ? 1 : 0, 
                               relationalPredictor ? 1 : 0, 
                               numClasses, 
                               classType,
                               multiInstance);
      test1 = makeTestDataset(24, numTest,
                              nominalPredictor ? 2 : 0,
                              numericPredictor ? 1 : 0, 
                              stringPredictor ? 1 : 0, 
                              datePredictor ? 1 : 0, 
                              relationalPredictor ? 1 : 0, 
                              numClasses, 
                              classType,
                              multiInstance);
      test2 = makeTestDataset(48, numTest,
                              nominalPredictor ? 3 : 0,
                              numericPredictor ? 2 : 0, 
                              stringPredictor ? 1 : 0, 
                              datePredictor ? 1 : 0, 
                              relationalPredictor ? 1 : 0, 
                              numClasses, 
                              classType,
                              multiInstance);
      if (missingLevel > 0) {
        addMissing(train1, missingLevel, predictorMissing, classMissing);
        addMissing(test1, Math.min(missingLevel,50), predictorMissing, 
            classMissing);
        addMissing(train2, missingLevel, predictorMissing, classMissing);
        addMissing(test2, Math.min(missingLevel,50), predictorMissing, 
            classMissing);
      }
      
      classifier = Classifier.makeCopies(getClassifier(), 1)[0];
      evaluation1A = new Evaluation(train1);
      evaluation1B = new Evaluation(train1);
      evaluation2 = new Evaluation(train2);
    } catch (Exception ex) {
      throw new Error("Error setting up for tests: " + ex.getMessage());
    }
    try {
      stage = 0;
      classifier.buildClassifier(train1);
      built = true;
      if (!testWRTZeroR(classifier, evaluation1A, train1, test1)[0]) {
        throw new Exception("Scheme performs worse than ZeroR");
      }
      
      stage = 1;
      built = false;
      classifier.buildClassifier(train2);
      built = true;
      if (!testWRTZeroR(classifier, evaluation2, train2, test2)[0]) {
        throw new Exception("Scheme performs worse than ZeroR");
      }
      
      stage = 2;
      built = false;
      classifier.buildClassifier(train1);
      built = true;
      if (!testWRTZeroR(classifier, evaluation1B, train1, test1)[0]) {
        throw new Exception("Scheme performs worse than ZeroR");
      }
      
      stage = 3;
      if (!evaluation1A.equals(evaluation1B)) {
        if (m_Debug) {
          println("\n=== Full report ===\n"
              + evaluation1A.toSummaryString("\nFirst buildClassifier()",
                  true)
                  + "\n\n");
          println(
              evaluation1B.toSummaryString("\nSecond buildClassifier()",
                  true)
                  + "\n\n");
        }
        throw new Exception("Results differ between buildClassifier calls");
      }
      println("yes");
      result[0] = true;
      
      if (false && m_Debug) {
        println("\n=== Full report ===\n"
            + evaluation1A.toSummaryString("\nFirst buildClassifier()",
                true)
                + "\n\n");
        println(
            evaluation1B.toSummaryString("\nSecond buildClassifier()",
                true)
                + "\n\n");
      }
    } 
    catch (Exception ex) {
      String msg = ex.getMessage().toLowerCase();
      if (msg.indexOf("worse than zeror") >= 0) {
        println("warning: performs worse than ZeroR");
        result[0] = true;
        result[1] = true;
      } else {
        println("no");
        result[0] = false;
      }
      if (m_Debug) {
        println("\n=== Full Report ===");
        print("Problem during");
        if (built) {
          print(" testing");
        } else {
          print(" training");
        }
        switch (stage) {
          case 0: