checkattributeselection.java

这是关于数据挖掘的一些算法

   * 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 scheme can handle
   * (at least) moderate missing predictor values
   * @param classMissing true if we know the scheme 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("scheme doesn't alter original datasets");
    printAttributeSummary(
        nominalPredictor, numericPredictor, stringPredictor, datePredictor, relationalPredictor, multiInstance, classType);
    print("...");
    int numTrain = getNumInstances(), 
    numClasses = 2, missingLevel = 20;
    
    boolean[] result = new boolean[2];
    Instances train = null;
    Instances trainCopy = null;
    ASSearch search = null;
    ASEvaluation evaluation = null;
    try {
      train = makeTestDataset(42, numTrain, 
                              nominalPredictor    ? getNumNominal()    : 0,
                              numericPredictor    ? getNumNumeric()    : 0, 
                              stringPredictor     ? getNumString()     : 0, 
                              datePredictor       ? getNumDate()       : 0, 
                              relationalPredictor ? getNumRelational() : 0, 
                              numClasses, 
                              classType,
                              multiInstance);
      if (missingLevel > 0)
        addMissing(train, missingLevel, predictorMissing, classMissing);
      search = ASSearch.makeCopies(getSearch(), 1)[0];
      evaluation = ASEvaluation.makeCopies(getEvaluator(), 1)[0];
      trainCopy = new Instances(train);
    } catch (Exception ex) {
      throw new Error("Error setting up for tests: " + ex.getMessage());
    }
    try {
      search(search, evaluation, trainCopy);
      compareDatasets(train, trainCopy);
      
      println("yes");
      result[0] = true;
    } catch (Exception ex) {
      println("no");
      result[0] = false;
      
      if (m_Debug) {
        println("\n=== Full Report ===");
        print("Problem during training");
        println(": " + ex.getMessage() + "\n");
        println("Here are the datasets:\n");
        println("=== Train Dataset (original) ===\n"
            + trainCopy.toString() + "\n");
        println("=== Train Dataset ===\n"
            + train.toString() + "\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 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 numClasses,
      FastVector accepts) {
    
    return runBasicTest(
		nominalPredictor, 
		numericPredictor,
		stringPredictor,
		datePredictor,
		relationalPredictor,
		multiInstance,
		classType, 
		TestInstances.CLASS_IS_LAST,
		missingLevel,
		predictorMissing,
		classMissing,
		numTrain,
		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 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 numClasses,
      FastVector accepts) {
    
    boolean[] result = new boolean[2];
    Instances train = null;
    ASSearch search = null;
    ASEvaluation evaluation = null;
    try {
      train = makeTestDataset(42, numTrain, 
                              nominalPredictor    ? getNumNominal()    : 0,
                              numericPredictor    ? getNumNumeric()    : 0, 
                              stringPredictor     ? getNumString()     : 0,
                              datePredictor       ? getNumDate()       : 0,
                              relationalPredictor ? getNumRelational() : 0,
                              numClasses, 
                              classType,
                              classIndex,
                              multiInstance);
      if (missingLevel > 0)
        addMissing(train, missingLevel, predictorMissing, classMissing);
      search = ASSearch.makeCopies(getSearch(), 1)[0];
      evaluation = ASEvaluation.makeCopies(getEvaluator(), 1)[0];
    } catch (Exception ex) {
      ex.printStackTrace();
      throw new Error("Error setting up for tests: " + ex.getMessage());
    }
    try {
      search(search, evaluation, train);
      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;
      for (int i = 0; i < accepts.size(); i++) {
	if (msg.indexOf((String)accepts.elementAt(i)) >= 0) {
	  acceptable = true;
	}
      }
      
      println("no" + (acceptable ? " (OK error message)" : ""));
      result[1] = acceptable;
      
      if (m_Debug) {
        println("\n=== Full Report ===");
        print("Problem during training");
        println(": " + ex.getMessage() + "\n");
        if (!acceptable) {
          if (accepts.size() > 0) {
            print("Error message doesn't mention ");
            for (int i = 0; i < accepts.size(); i++) {
              if (i != 0) {
                print(" or ");
              }
              print('"' + (String)accepts.elementAt(i) + '"');
            }
          }
          println("here is the dataset:\n");
          println("=== Train Dataset ===\n"
              + train.toString() + "\n");
        }
      }
    }
    
    return result;
  }
  
  /**
   * Make a simple set of instances, which can later be modified
   * for use in specific tests.
   *
   * @param seed the random number seed
   * @param numInstances the number of instances to generate
   * @param numNominal the number of nominal attributes
   * @param numNumeric the number of numeric attributes
   * @param numString the number of string attributes
   * @param numDate the number of date attributes
   * @param numRelational the number of relational attributes
   * @param numClasses the number of classes (if nominal class)
   * @param classType the class type (NUMERIC, NOMINAL, etc.)
   * @param multiInstance whether the dataset should a multi-instance dataset
   * @return the test dataset
   * @throws Exception if the dataset couldn't be generated
   * @see #process(Instances)
   */
  protected Instances makeTestDataset(int seed, int numInstances, 
                                      int numNominal, int numNumeric, 
                                      int numString, int numDate,
                                      int numRelational,
                                      int numClasses, int classType,
                                      boolean multiInstance)
    throws Exception {
    
    return makeTestDataset(
		seed, 
		numInstances,
		numNominal,
		numNumeric,
		numString,
		numDate, 
		numRelational,
		numClasses, 
		classType,
		TestInstances.CLASS_IS_LAST,
		multiInstance);
  }
  
  /**
   * Make a simple set of instances with variable position of the class 
   * attribute, which can later be modified for use in specific tests.
   *
   * @param seed the random number seed
   * @param numInstances the number of instances to generate
   * @param numNominal the number of nominal attributes
   * @param numNumeric the number of numeric attributes
   * @param numString the number of string attributes
   * @param numDate the number of date attributes
   * @param numRelational the number of relational attributes
   * @param numClasses the number of classes (if nominal class)
   * @param classType the class type (NUMERIC, NOMINAL, etc.)
   * @param classIndex the index of the class (0-based, -1 as last)
   * @param multiInstance whether the dataset should a multi-instance dataset
   * @return the test dataset
   * @throws Exception if the dataset couldn't be generated
   * @see TestInstances#CLASS_IS_LAST
   * @see #process(Instances)
   */
  protected Instances makeTestDataset(int seed, int numInstances, 
                                      int numNominal, int numNumeric, 
                                      int numString, int numDate,
                                      int numRelational,
                                      int numClasses, int classType,
                                      int classIndex,
                                      boolean multiInstance)
  throws Exception {
    
    TestInstances dataset = new TestInstances();
    
    dataset.setSeed(seed);
    dataset.setNumInstances(numInstances);
    dataset.setNumNominal(numNominal);
    dataset.setNumNumeric(numNumeric);
    dataset.setNumString(numString);
    dataset.setNumDate(numDate);
    dataset.setNumRelational(numRelational);
    dataset.setNumClasses(numClasses);
    dataset.setClassType(classType);
    dataset.setClassIndex(classIndex);
    dataset.setNumClasses(numClasses);
    dataset.setMultiInstance(multiInstance);
    dataset.setWords(getWords());
    dataset.setWordSeparators(getWordSeparators());
    
    return process(dataset.generate());
  }
  
  /**
   * Print out a short summary string for the dataset characteristics
   *
   * @param nominalPredictor true if nominal predictor attributes are present
   * @param numericPredictor true if numeric predictor attributes are present
   * @param stringPredictor true if string predictor attributes are present
   * @param datePredictor true if date predictor attributes are present
   * @param relationalPredictor true if relational predictor attributes are present
   * @param multiInstance whether multi-instance is needed
   * @param classType the class type (NUMERIC, NOMINAL, etc.)
   */
  protected void printAttributeSummary(boolean nominalPredictor, 
                                       boolean numericPredictor, 
                                       boolean stringPredictor, 
                                       boolean datePredictor, 
                                       boolean relationalPredictor, 
                                       boolean multiInstance,
                                       int classType) {
    
    String str = "";

    if (numericPredictor)
      str += " numeric";
    
    if (nominalPredictor) {
      if (str.length() > 0)
        str += " &";
      str += " nominal";
    }
    
    if (stringPredictor) {
      if (str.length() > 0)
        str += " &";
      str += " string";
    }
    
    if (datePredictor) {
      if (str.length() > 0)
        str += " &";
      str += " date";
    }
    
    if (relationalPredictor) {
      if (str.length() > 0)
        str += " &";
      str += " relational";
    }
    
    str += " predictors)";
    
    switch (classType) {
      case Attribute.NUMERIC:
        str = " (numeric class," + str;
        break;
      case Attribute.NOMINAL:
        str = " (nominal class," + str;
        break;
      case Attribute.STRING:
        str = " (string class," + str;
        break;
      case Attribute.DATE:
        str = " (date class," + str;
        break;
      case Attribute.RELATIONAL:
        str = " (relational class," + str;
        break;
    }
    
    print(str);
  }
  
  /**
   * Test method for this class
   * 
   * @param args the commandline parameters
   */
  public static void main(String [] args) {
    runCheck(new CheckAttributeSelection(), args);
  }
}