checkclassifier.java

Java 编写的多种数据挖掘算法 包括聚类、分类、预处理等

   * returns the current PostProcessor, can be null
   * 
   * @return		the current PostProcessor
   */
  public PostProcessor getPostProcessor() {
    return m_PostProcessor;
  }
  
  /**
   * returns TRUE if the classifier returned a "not in classpath" Exception
   * 
   * @return	true if CLASSPATH problems occurred
   */
  public boolean hasClasspathProblems() {
    return m_ClasspathProblems;
  }
  
  /**
   * Begin the tests, reporting results to System.out
   */
  public void doTests() {
    
    if (getClassifier() == null) {
      println("\n=== No classifier set ===");
      return;
    }
    println("\n=== Check on Classifier: "
        + getClassifier().getClass().getName()
        + " ===\n");
    
    // Start tests
    m_ClasspathProblems = false;
    println("--> Checking for interfaces");
    canTakeOptions();
    boolean updateableClassifier = updateableClassifier()[0];
    boolean weightedInstancesHandler = weightedInstancesHandler()[0];
    boolean multiInstanceHandler = multiInstanceHandler()[0];
    println("--> Classifier tests");
    testsPerClassType(Attribute.NOMINAL,    updateableClassifier, weightedInstancesHandler, multiInstanceHandler);
    testsPerClassType(Attribute.NUMERIC,    updateableClassifier, weightedInstancesHandler, multiInstanceHandler);
    testsPerClassType(Attribute.DATE,       updateableClassifier, weightedInstancesHandler, multiInstanceHandler);
    testsPerClassType(Attribute.STRING,     updateableClassifier, weightedInstancesHandler, multiInstanceHandler);
    testsPerClassType(Attribute.RELATIONAL, updateableClassifier, weightedInstancesHandler, multiInstanceHandler);
  }
  
  /**
   * Set debugging mode
   *
   * @param debug true if debug output should be printed
   */
  public void setDebug(boolean debug) {
    m_Debug = debug;
    // disable silent mode, if necessary
    if (getDebug())
      setSilent(false);
  }
  
  /**
   * Get whether debugging is turned on
   *
   * @return true if debugging output is on
   */
  public boolean getDebug() {
    return m_Debug;
  }
  
  /**
   * Set slient mode, i.e., no output at all to stdout
   *
   * @param value whether silent mode is active or not
   */
  public void setSilent(boolean value) {
    m_Silent = value;
  }
  
  /**
   * Get whether silent mode is turned on
   *
   * @return true if silent mode is on
   */
  public boolean getSilent() {
    return m_Silent;
  }
  
  /**
   * Sets the number of instances to use in the datasets (some classifiers
   * might require more instances).
   *
   * @param value the number of instances to use
   */
  public void setNumInstances(int value) {
    m_NumInstances = value;
  }
  
  /**
   * Gets the current number of instances to use for the datasets.
   *
   * @return the number of instances
   */
  public int getNumInstances() {
    return m_NumInstances;
  }
  
  /**
   * Set the classifier for boosting. 
   *
   * @param newClassifier the Classifier to use.
   */
  public void setClassifier(Classifier newClassifier) {
    m_Classifier = newClassifier;
  }
  
  /**
   * Get the classifier used as the classifier
   *
   * @return the classifier used as the classifier
   */
  public Classifier getClassifier() {
    return m_Classifier;
  }

  /**
   * turns the comma-separated list into an array
   * 
   * @param value	the list to process
   * @return		the list as array
   */
  protected static String[] listToArray(String value) {
    StringTokenizer	tok;
    Vector		list;
    
    list = new Vector();
    tok = new StringTokenizer(value, ",");
    while (tok.hasMoreTokens())
      list.add(tok.nextToken());
    
    return (String[]) list.toArray(new String[list.size()]);
  }
  
  /**
   * turns the array into a comma-separated list
   * 
   * @param value	the array to process
   * @return		the array as list
   */
  protected static String arrayToList(String[] value) {
    String	result;
    int		i;
    
    result = "";
    
    for (i = 0; i < value.length; i++) {
      if (i > 0)
	result += ",";
      result += value[i];
    }
    
    return result;
  }
  
  /**
   * Sets the comma-separated list of words to use for generating strings. The
   * list must contain at least 2 words, otherwise an exception will be thrown.
   * 
   * @param value			the list of words
   * @throws IllegalArgumentException	if not at least 2 words are provided
   */
  public void setWords(String value) {
    if (listToArray(value).length < 2)
      throw new IllegalArgumentException("At least 2 words must be provided!");
    
    m_Words = listToArray(value);
  }
  
  /**
   * returns the words used for assembling strings in a comma-separated list.
   * 
   * @return		the words as comma-separated list
   */
  public String getWords() {
    return arrayToList(m_Words);
  }

  /**
   * sets the word separators (chars) to use for assembling strings.
   * 
   * @param value	the characters to use as separators
   */
  public void setWordSeparators(String value) {
    m_WordSeparators = value;
  }
  
  /**
   * returns the word separators (chars) to use for assembling strings.
   * 
   * @return		the current separators
   */
  public String getWordSeparators() {
    return m_WordSeparators;
  }
  
  /**
   * prints the given message to stdout, if not silent mode
   * 
   * @param msg         the text to print to stdout
   */
  protected void print(Object msg) {
    if (!getSilent())
      System.out.print(msg);
  }
  
  /**
   * prints the given message (+ LF) to stdout, if not silent mode
   * 
   * @param msg         the message to println to stdout
   */
  protected void println(Object msg) {
    print(msg + "\n");
  }
  
  /**
   * prints a LF to stdout, if not silent mode
   */
  protected void println() {
    print("\n");
  }
  
  /**
   * Run a battery of tests for a given class attribute type
   *
   * @param classType true if the class attribute should be numeric
   * @param updateable true if the classifier is updateable
   * @param weighted true if the classifier says it handles weights
   * @param multiInstance true if the classifier is a multi-instance classifier
   */
  protected void testsPerClassType(int classType, 
                                   boolean updateable,
                                   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);
      doesntUseTestClassVal(PNom, PNum, PStr, PDat, PRel, multiInstance, classType);
      if (updateable)
        updatingEquality(PNom, PNum, PStr, PDat, PRel, multiInstance, classType);
    }
  }
  
  /**
   * Checks whether the scheme can take command line options.
   *
   * @return index 0 is true if the classifier can take options
   */
  protected boolean[] canTakeOptions() {
    
    boolean[] result = new boolean[2];
    
    print("options...");
    if (m_Classifier instanceof OptionHandler) {
      println("yes");
      if (m_Debug) {
        println("\n=== Full report ===");
        Enumeration enu = ((OptionHandler)m_Classifier).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 can build models incrementally.
   *
   * @return index 0 is true if the classifier can train incrementally
   */
  protected boolean[] updateableClassifier() {
    
    boolean[] result = new boolean[2];
    
    print("updateable classifier...");
    if (m_Classifier instanceof UpdateableClassifier) {
      println("yes");
      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 classifier handles instance weights
   */
  protected boolean[] weightedInstancesHandler() {
    
    boolean[] result = new boolean[2];
    
    print("weighted instances classifier...");
    if (m_Classifier 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 classifier handles multi-instance data
   */
  protected boolean[] multiInstanceHandler() {
    boolean[] result = new boolean[2];
    
    print("multi-instance classifier...");
    if (m_Classifier instanceof MultiInstanceCapabilitiesHandler) {