checkclassifier.java

Java 编写的多种数据挖掘算法 包括聚类、分类、预处理等

    Instances train = null;
    Instances test = null;
    Classifier [] classifiers = null;
    Evaluation evaluationB = null;
    Evaluation evaluationI = null;
    boolean built = false;
    boolean evalFail = false;
    try {
      train = makeTestDataset(42, numTrain, 
                              nominalPredictor ? 3 : 0,
                              numericPredictor ? 2 : 0, 
                              stringPredictor ? 1 : 0, 
                              datePredictor ? 1 : 0, 
                              relationalPredictor ? 1 : 0, 
                              numClasses, 
                              classType,
                              multiInstance);
      test = makeTestDataset(24, numTest,
                             nominalPredictor ? 3 : 0,
                             numericPredictor ? 2 : 0, 
                             stringPredictor ? 1 : 0, 
                             datePredictor ? 1 : 0, 
                             relationalPredictor ? 1 : 0, 
                             numClasses, 
                             classType,
                             multiInstance);
      if (missingLevel > 0) {
        addMissing(train, missingLevel, predictorMissing, classMissing);
        addMissing(test, Math.min(missingLevel, 50), predictorMissing, 
            classMissing);
      }
      classifiers = Classifier.makeCopies(getClassifier(), 2);
      evaluationB = new Evaluation(train);
      evaluationI = new Evaluation(train);
      classifiers[0].buildClassifier(train);
      testWRTZeroR(classifiers[0], evaluationB, train, test);
    } catch (Exception ex) {
      throw new Error("Error setting up for tests: " + ex.getMessage());
    }
    try {
      
      // Now modify instance weights and re-built/test
      for (int i = 0; i < train.numInstances(); i++) {
        train.instance(i).setWeight(0);
      }
      Random random = new Random(1);
      for (int i = 0; i < train.numInstances() / 2; i++) {
        int inst = Math.abs(random.nextInt()) % train.numInstances();
        int weight = Math.abs(random.nextInt()) % 10 + 1;
        train.instance(inst).setWeight(weight);
      }
      classifiers[1].buildClassifier(train);
      built = true;
      testWRTZeroR(classifiers[1], evaluationI, train, test);
      if (evaluationB.equals(evaluationI)) {
        //	println("no");
        evalFail = true;
        throw new Exception("evalFail");
      }
      
      println("yes");
      result[0] = true;
    } catch (Exception ex) {
      println("no");
      result[0] = false;
      
      if (m_Debug) {
        println("\n=== Full Report ===");
        
        if (evalFail) {
          println("Results don't differ between non-weighted and "
              + "weighted instance models.");
          println("Here are the results:\n");
          println(evaluationB.toSummaryString("\nboth methods\n",
              true));
        } else {
          print("Problem during");
          if (built) {
            print(" testing");
          } else {
            print(" training");
          }
          println(": " + ex.getMessage() + "\n");
        }
        println("Here are the datasets:\n");
        println("=== Train Dataset ===\n"
            + train.toString() + "\n");
        println("=== Train Weights ===\n");
        for (int i = 0; i < train.numInstances(); i++) {
          println(" " + (i + 1) 
              + "    " + train.instance(i).weight());
        }
        println("=== Test Dataset ===\n"
            + test.toString() + "\n\n");	
        println("(test weights all 1.0\n");
      }
    }
    
    return result;
  }
  
  /**
   * Checks whether the scheme alters the training dataset during
   * training. If the scheme needs to modify the training
   * data it should take a copy of the training data. Currently checks
   * for changes to header structure, number of instances, order of
   * instances, instance weights.
   *
   * @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 predictorMissing true if we know the classifier can handle
   * (at least) moderate missing predictor values
   * @param classMissing true if we know the classifier can handle
   * (at least) moderate missing class values
   * @return index 0 is true if the test was passed
   */
  protected boolean[] datasetIntegrity(
      boolean nominalPredictor,
      boolean numericPredictor, 
      boolean stringPredictor, 
      boolean datePredictor,
      boolean relationalPredictor,
      boolean multiInstance,
      int classType,
      boolean predictorMissing,
      boolean classMissing) {
    
    print("classifier doesn't alter original datasets");
    printAttributeSummary(
        nominalPredictor, numericPredictor, stringPredictor, datePredictor, relationalPredictor, multiInstance, classType);
    print("...");
    int numTrain = getNumInstances(), numTest = getNumInstances(), 
    numClasses = 2, missingLevel = 20;
    
    boolean[] result = new boolean[2];
    Instances train = null;
    Instances test = null;
    Classifier classifier = null;
    Evaluation evaluation = null;
    boolean built = false;
    try {
      train = makeTestDataset(42, numTrain, 
                              nominalPredictor ? 2 : 0,
                              numericPredictor ? 1 : 0, 
                              stringPredictor ? 1 : 0, 
                              datePredictor ? 1 : 0, 
                              relationalPredictor ? 1 : 0, 
                              numClasses, 
                              classType,
                              multiInstance);
      test = makeTestDataset(24, numTest,
                             nominalPredictor ? 2 : 0,
                             numericPredictor ? 1 : 0, 
                             stringPredictor ? 1 : 0, 
                             datePredictor ? 1 : 0, 
                             relationalPredictor ? 1 : 0, 
                             numClasses, 
                             classType,
                             multiInstance);
      if (missingLevel > 0) {
        addMissing(train, missingLevel, predictorMissing, classMissing);
        addMissing(test, Math.min(missingLevel, 50), predictorMissing, 
            classMissing);
      }
      classifier = Classifier.makeCopies(getClassifier(), 1)[0];
      evaluation = new Evaluation(train);
    } catch (Exception ex) {
      throw new Error("Error setting up for tests: " + ex.getMessage());
    }
    try {
      Instances trainCopy = new Instances(train);
      Instances testCopy = new Instances(test);
      classifier.buildClassifier(trainCopy);
      compareDatasets(train, trainCopy);
      built = true;
      testWRTZeroR(classifier, evaluation, trainCopy, testCopy);
      compareDatasets(test, testCopy);
      
      println("yes");
      result[0] = true;
    } catch (Exception ex) {
      println("no");
      result[0] = false;
      
      if (m_Debug) {
        println("\n=== Full Report ===");
        print("Problem during");
        if (built) {
          print(" testing");
        } else {
          print(" training");
        }
        println(": " + ex.getMessage() + "\n");
        println("Here are the datasets:\n");
        println("=== Train Dataset ===\n"
            + train.toString() + "\n");
        println("=== Test Dataset ===\n"
            + test.toString() + "\n\n");
      }
    }
    
    return result;
  }
  
  /**
   * Runs a text on the datasets with the given characteristics.
   * 
   * @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 missingLevel the percentage of missing values
   * @param predictorMissing true if the missing values may be in 
   * the predictors
   * @param classMissing true if the missing values may be in the class
   * @param numTrain the number of instances in the training set
   * @param numTest the number of instaces in the test set
   * @param numClasses the number of classes
   * @param accepts the acceptable string in an exception
   * @return index 0 is true if the test was passed, index 1 is true if test 
   *         was acceptable
   */
  protected boolean[] runBasicTest(boolean nominalPredictor,
      boolean numericPredictor, 
      boolean stringPredictor,
      boolean datePredictor,
      boolean relationalPredictor,
      boolean multiInstance,
      int classType,
      int missingLevel,
      boolean predictorMissing,
      boolean classMissing,
      int numTrain,
      int numTest,
      int numClasses,
      FastVector accepts) {
    
    return runBasicTest(
		nominalPredictor, 
		numericPredictor,
		stringPredictor,
		datePredictor,
		relationalPredictor,
		multiInstance,
		classType, 
		TestInstances.CLASS_IS_LAST,
		missingLevel,
		predictorMissing,
		classMissing,
		numTrain,
		numTest,
		numClasses,
		accepts);
  }
  
  /**
   * Runs a text on the datasets with the given characteristics.
   * 
   * @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 attribute index of the class
   * @param missingLevel the percentage of missing values
   * @param predictorMissing true if the missing values may be in 
   * the predictors
   * @param classMissing true if the missing values may be in the class
   * @param numTrain the number of instances in the training set
   * @param numTest the number of instaces in the test set
   * @param numClasses the number of classes
   * @param accepts the acceptable string in an exception
   * @return index 0 is true if the test was passed, index 1 is true if test 
   *         was acceptable
   */
  protected boolean[] runBasicTest(boolean nominalPredictor,
      boolean numericPredictor, 
      boolean stringPredictor,
      boolean datePredictor,
      boolean relationalPredictor,
      boolean multiInstance,
      int classType,
      int classIndex,
      int missingLevel,
      boolean predictorMissing,
      boolean classMissing,
      int numTrain,
      int numTest,
      int numClasses,
      FastVector accepts) {
    
    boolean[] result = new boolean[2];
    Instances train = null;
    Instances test = null;
    Classifier classifier = null;
    Evaluation evaluation = null;
    boolean built = false;
    try {
      train = makeTestDataset(42, numTrain, 
                              nominalPredictor     ? 2 : 0,
                              numericPredictor     ? 1 : 0, 
                              stringPredictor      ? 1 : 0,
                              datePredictor        ? 1 : 0,
                              relationalPredictor  ? 1 : 0,
                              numClasses, 
                              classType,
                              classIndex,
                              multiInstance);
      test = makeTestDataset(24, numTest,
                             nominalPredictor     ? 2 : 0,
                             numericPredictor     ? 1 : 0, 
                             stringPredictor      ? 1 : 0,
                             datePredictor        ? 1 : 0,
                             relationalPredictor  ? 1 : 0,
                             numClasses, 
                             classType,
                             classIndex,
                             multiInstance);
      if (missingLevel > 0) {
        addMissing(train, missingLevel, predictorMissing, classMissing);
        addMissing(test, Math.min(missingLevel, 50), predictorMissing, 
            classMissing);
      }
      classifier = Classifier.makeCopies(getClassifier(), 1)[0];
      evaluation = new Evaluation(train);
    } catch (Exception ex) {
      ex.printStackTrace();
      throw new Error("Error setting up for tests: " + ex.getMessage());
    }
    try {
      classifier.buildClassifier(train);
      built = true;
      if (!testWRTZeroR(classifier, evaluation, train, test)[0]) {
        result[0] = true;
        result[1] = true;
        throw new Exception("Scheme performs worse than ZeroR");
      }
      
      println("yes");
      result[0] = true;
    } 
    catch (Exception ex) {
      boolean acceptable = false;
      String msg;
      if (ex.getMessage() == null)
	msg = "";
      else
        msg = ex.getMessage().toLowerCase();
      if (msg.indexOf("not in classpath") > -1)
	m_ClasspathProblems = true;
      if (msg.indexOf("worse than zeror") >= 0) {
        println("warning: performs worse than ZeroR");
        result[0] = true;
        result[1] = true;
      } else {
        for (int i = 0; i < accepts.size(); i++) {