checkkernel.java

代码是一个分类器的实现,其中使用了部分weka的源代码。可以将项目导入eclipse运行

    m_ClasspathProblems = false;
    println("--> Checking for interfaces");
    canTakeOptions();
    boolean weightedInstancesHandler = weightedInstancesHandler()[0];
    boolean multiInstanceHandler = multiInstanceHandler()[0];
    println("--> Kernel tests");
    testsPerClassType(Attribute.NOMINAL,    weightedInstancesHandler, multiInstanceHandler);
    testsPerClassType(Attribute.NUMERIC,    weightedInstancesHandler, multiInstanceHandler);
    testsPerClassType(Attribute.DATE,       weightedInstancesHandler, multiInstanceHandler);
    testsPerClassType(Attribute.STRING,     weightedInstancesHandler, multiInstanceHandler);
    testsPerClassType(Attribute.RELATIONAL, weightedInstancesHandler, multiInstanceHandler);
  }
  
  /**
   * Set the lernel to test. 
   *
   * @param value the kernel to use.
   */
  public void setKernel(Kernel value) {
    m_Kernel = value;
  }
  
  /**
   * Get the kernel being tested
   *
   * @return the kernel being tested
   */
  public Kernel getKernel() {
    return m_Kernel;
  }
  
  /**
   * Run a battery of tests for a given class attribute type
   *
   * @param classType true if the class attribute should be numeric
   * @param weighted true if the kernel says it handles weights
   * @param multiInstance true if the kernel is a multi-instance kernel
   */
  protected void testsPerClassType(int classType, 
                                   boolean weighted,
                                   boolean multiInstance) {
    
    boolean PNom = canPredict(true,  false, false, false, false, multiInstance, classType)[0];
    boolean PNum = canPredict(false, true,  false, false, false, multiInstance, classType)[0];
    boolean PStr = canPredict(false, false, true,  false, false, multiInstance, classType)[0];
    boolean PDat = canPredict(false, false, false, true,  false, multiInstance, classType)[0];
    boolean PRel;
    if (!multiInstance)
      PRel = canPredict(false, false, false, false,  true, multiInstance, classType)[0];
    else
      PRel = false;

    if (PNom || PNum || PStr || PDat || PRel) {
      if (weighted)
        instanceWeights(PNom, PNum, PStr, PDat, PRel, multiInstance, classType);
      
      if (classType == Attribute.NOMINAL)
        canHandleNClasses(PNom, PNum, PStr, PDat, PRel, multiInstance, 4);

      if (!multiInstance) {
	canHandleClassAsNthAttribute(PNom, PNum, PStr, PDat, PRel, multiInstance, classType, 0);
	canHandleClassAsNthAttribute(PNom, PNum, PStr, PDat, PRel, multiInstance, classType, 1);
      }
      
      canHandleZeroTraining(PNom, PNum, PStr, PDat, PRel, multiInstance, classType);
      boolean handleMissingPredictors = canHandleMissing(PNom, PNum, PStr, PDat, PRel, 
          multiInstance, classType, 
          true, false, 20)[0];
      if (handleMissingPredictors)
        canHandleMissing(PNom, PNum, PStr, PDat, PRel, multiInstance, classType, true, false, 100);
      
      boolean handleMissingClass = canHandleMissing(PNom, PNum, PStr, PDat, PRel, 
          multiInstance, classType, 
          false, true, 20)[0];
      if (handleMissingClass)
        canHandleMissing(PNom, PNum, PStr, PDat, PRel, multiInstance, classType, false, true, 100);
      
      correctBuildInitialisation(PNom, PNum, PStr, PDat, PRel, multiInstance, classType);
      datasetIntegrity(PNom, PNum, PStr, PDat, PRel, multiInstance, classType,
          handleMissingPredictors, handleMissingClass);
    }
  }
  
  /**
   * Checks whether the scheme can take command line options.
   *
   * @return index 0 is true if the kernel can take options
   */
  protected boolean[] canTakeOptions() {
    
    boolean[] result = new boolean[2];
    
    print("options...");
    if (m_Kernel instanceof OptionHandler) {
      println("yes");
      if (m_Debug) {
        println("\n=== Full report ===");
        Enumeration enu = ((OptionHandler)m_Kernel).listOptions();
        while (enu.hasMoreElements()) {
          Option option = (Option) enu.nextElement();
          print(option.synopsis() + "\n" 
              + option.description() + "\n");
        }
        println("\n");
      }
      result[0] = true;
    }
    else {
      println("no");
      result[0] = false;
    }
    
    return result;
  }
  
  /**
   * Checks whether the scheme says it can handle instance weights.
   *
   * @return true if the kernel handles instance weights
   */
  protected boolean[] weightedInstancesHandler() {
    
    boolean[] result = new boolean[2];
    
    print("weighted instances kernel...");
    if (m_Kernel instanceof WeightedInstancesHandler) {
      println("yes");
      result[0] = true;
    }
    else {
      println("no");
      result[0] = false;
    }
    
    return result;
  }
  
  /**
   * Checks whether the scheme handles multi-instance data.
   * 
   * @return true if the kernel handles multi-instance data
   */
  protected boolean[] multiInstanceHandler() {
    boolean[] result = new boolean[2];
    
    print("multi-instance kernel...");
    if (m_Kernel instanceof MultiInstanceCapabilitiesHandler) {
      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("unary");
    accepts.addElement("binary");
    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(), numClasses = 2, missingLevel = 0;
    boolean predictorMissing = false, classMissing = false;
    
    return runBasicTest(nominalPredictor, numericPredictor, stringPredictor, 
        datePredictor, relationalPredictor, 
        multiInstance,
        classType, 
        missingLevel, predictorMissing, classMissing,
        numTrain, 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(), missingLevel = 0;
    boolean predictorMissing = false, classMissing = false;
    
    return runBasicTest(nominalPredictor, numericPredictor, stringPredictor, 
                        datePredictor, relationalPredictor, 
                        multiInstance,
                        Attribute.NOMINAL,
                        missingLevel, predictorMissing, classMissing,
                        numTrain, 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(), numClasses = 2, missingLevel = 0;
    boolean predictorMissing = false, classMissing = false;
    
    return runBasicTest(nominalPredictor, numericPredictor, stringPredictor, 
                        datePredictor, relationalPredictor, 
                        multiInstance,
                        classType,
                        classIndex,
                        missingLevel, predictorMissing, classMissing,
                        numTrain, 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, numClasses = 2, missingLevel = 0;
    boolean predictorMissing = false, classMissing = false;
    
    return runBasicTest(
              nominalPredictor, numericPredictor, stringPredictor, 
              datePredictor, relationalPredictor, 
              multiInstance,
              classType, 
              missingLevel, predictorMissing, classMissing,
              numTrain, numClasses, 
              accepts);
  }
  
  /**
   * Checks whether the scheme correctly initialises models when 
   * buildKernel is called. This test calls buildKernel with
   * one training dataset. buildKernel is then called on a training 
   * set with different structure, and then again with the original training 
   * set. If the equals method of the KernelEvaluation class returns 
   * false, this is 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