regressionsplitevaluator.java

Java 编写的多种数据挖掘算法 包括聚类、分类、预处理等

  public Object [] getKey(){

    Object [] key = new Object[KEY_SIZE];
    key[0] = m_Template.getClass().getName();
    key[1] = m_ClassifierOptions;
    key[2] = m_ClassifierVersion;
    return key;
  }

  /**
   * Gets the data types of each of the result columns produced for a 
   * single run. The number of result fields must be constant
   * for a given SplitEvaluator.
   *
   * @return an array containing objects of the type of each result column. 
   * The objects should be Strings, or Doubles.
   */
  public Object [] getResultTypes() {
    int addm = (m_AdditionalMeasures != null) 
      ? m_AdditionalMeasures.length 
      : 0;
    Object [] resultTypes = new Object[RESULT_SIZE+addm];
    Double doub = new Double(0);
    int current = 0;
    resultTypes[current++] = doub;

    resultTypes[current++] = doub;
    resultTypes[current++] = doub;
    resultTypes[current++] = doub;
    resultTypes[current++] = doub;
    resultTypes[current++] = doub;

    resultTypes[current++] = doub;
    resultTypes[current++] = doub;
    resultTypes[current++] = doub;
    resultTypes[current++] = doub;
    resultTypes[current++] = doub;
    resultTypes[current++] = doub;

    // Timing stats
    resultTypes[current++] = doub;
    resultTypes[current++] = doub;
    resultTypes[current++] = doub;
    resultTypes[current++] = doub;

    resultTypes[current++] = "";

    // add any additional measures
    for (int i=0;i<addm;i++) {
      resultTypes[current++] = doub;
    }
    if (current != RESULT_SIZE+addm) {
      throw new Error("ResultTypes didn't fit RESULT_SIZE");
    }
    return resultTypes;
  }

  /**
   * Gets the names of each of the result columns produced for a single run.
   * The number of result fields must be constant
   * for a given SplitEvaluator.
   *
   * @return an array containing the name of each result column
   */
  public String [] getResultNames() {
    int addm = (m_AdditionalMeasures != null) 
      ? m_AdditionalMeasures.length 
      : 0;
    String [] resultNames = new String[RESULT_SIZE+addm];
    int current = 0;
    resultNames[current++] = "Number_of_instances";

    // Sensitive stats - certainty of predictions
    resultNames[current++] = "Mean_absolute_error";
    resultNames[current++] = "Root_mean_squared_error";
    resultNames[current++] = "Relative_absolute_error";
    resultNames[current++] = "Root_relative_squared_error";
    resultNames[current++] = "Correlation_coefficient";

    // SF stats
    resultNames[current++] = "SF_prior_entropy";
    resultNames[current++] = "SF_scheme_entropy";
    resultNames[current++] = "SF_entropy_gain";
    resultNames[current++] = "SF_mean_prior_entropy";
    resultNames[current++] = "SF_mean_scheme_entropy";
    resultNames[current++] = "SF_mean_entropy_gain";

    // Timing stats
    resultNames[current++] = "Elapsed_Time_training";
    resultNames[current++] = "Elapsed_Time_testing";
    resultNames[current++] = "UserCPU_Time_training";
    resultNames[current++] = "UserCPU_Time_testing";
    
    // Classifier defined extras
    resultNames[current++] = "Summary";
    // add any additional measures
    for (int i=0;i<addm;i++) {
      resultNames[current++] = m_AdditionalMeasures[i];
    }
    if (current != RESULT_SIZE+addm) {
      throw new Error("ResultNames didn't fit RESULT_SIZE");
    }
    return resultNames;
  }

  /**
   * Gets the results for the supplied train and test datasets. Now performs
   * a deep copy of the classifier before it is built and evaluated (just in case
   * the classifier is not initialized properly in buildClassifier()).
   *
   * @param train the training Instances.
   * @param test the testing Instances.
   * @return the results stored in an array. The objects stored in
   * the array may be Strings, Doubles, or null (for the missing value).
   * @throws Exception if a problem occurs while getting the results
   */
  public Object [] getResult(Instances train, Instances test) 
    throws Exception {

    if (train.classAttribute().type() != Attribute.NUMERIC) {
      throw new Exception("Class attribute is not numeric!");
    }
    if (m_Template == null) {
      throw new Exception("No classifier has been specified");
    }
    ThreadMXBean thMonitor = ManagementFactory.getThreadMXBean();
    boolean canMeasureCPUTime = thMonitor.isThreadCpuTimeSupported();
    if(!thMonitor.isThreadCpuTimeEnabled())
      thMonitor.setThreadCpuTimeEnabled(true);
    
    int addm = (m_AdditionalMeasures != null) ? m_AdditionalMeasures.length : 0;
    Object [] result = new Object[RESULT_SIZE+addm];
    long thID = Thread.currentThread().getId();
    long CPUStartTime=-1, trainCPUTimeElapsed=-1, testCPUTimeElapsed=-1,
         trainTimeStart, trainTimeElapsed, testTimeStart, testTimeElapsed;    
    Evaluation eval = new Evaluation(train);
    m_Classifier = Classifier.makeCopy(m_Template);

    trainTimeStart = System.currentTimeMillis();
    if(canMeasureCPUTime)
      CPUStartTime = thMonitor.getThreadUserTime(thID);
    m_Classifier.buildClassifier(train);
    if(canMeasureCPUTime)
      trainCPUTimeElapsed = thMonitor.getThreadUserTime(thID) - CPUStartTime;
    trainTimeElapsed = System.currentTimeMillis() - trainTimeStart;
    testTimeStart = System.currentTimeMillis();
    if(canMeasureCPUTime)
      CPUStartTime = thMonitor.getThreadUserTime(thID);
    eval.evaluateModel(m_Classifier, test);
    if(canMeasureCPUTime)
      testCPUTimeElapsed = thMonitor.getThreadUserTime(thID) - CPUStartTime;
    testTimeElapsed = System.currentTimeMillis() - testTimeStart;
    thMonitor = null;
    
    m_result = eval.toSummaryString();
    // The results stored are all per instance -- can be multiplied by the
    // number of instances to get absolute numbers
    int current = 0;
    result[current++] = new Double(eval.numInstances());

    result[current++] = new Double(eval.meanAbsoluteError());
    result[current++] = new Double(eval.rootMeanSquaredError());
    result[current++] = new Double(eval.relativeAbsoluteError());
    result[current++] = new Double(eval.rootRelativeSquaredError());
    result[current++] = new Double(eval.correlationCoefficient());

    result[current++] = new Double(eval.SFPriorEntropy());
    result[current++] = new Double(eval.SFSchemeEntropy());
    result[current++] = new Double(eval.SFEntropyGain());
    result[current++] = new Double(eval.SFMeanPriorEntropy());
    result[current++] = new Double(eval.SFMeanSchemeEntropy());
    result[current++] = new Double(eval.SFMeanEntropyGain());
    
    // Timing stats
    result[current++] = new Double(trainTimeElapsed / 1000.0);
    result[current++] = new Double(testTimeElapsed / 1000.0);
    if(canMeasureCPUTime) {
      result[current++] = new Double((trainCPUTimeElapsed/1000000.0) / 1000.0);
      result[current++] = new Double((testCPUTimeElapsed /1000000.0) / 1000.0);
    }
    else {
      result[current++] = new Double(Instance.missingValue());
      result[current++] = new Double(Instance.missingValue());
    }
    
    if (m_Classifier instanceof Summarizable) {
      result[current++] = ((Summarizable)m_Classifier).toSummaryString();
    } else {
      result[current++] = null;
    }
    
    for (int i=0;i<addm;i++) {
      if (m_doesProduce[i]) {
        try {
          double dv = ((AdditionalMeasureProducer)m_Classifier).
          getMeasure(m_AdditionalMeasures[i]);
          if (!Instance.isMissingValue(dv)) {
            Double value = new Double(dv);
            result[current++] = value;
          } else {
            result[current++] = null;
          }
        } catch (Exception ex) {
          System.err.println(ex);
        }
      } else {
        result[current++] = null;
      }
    }
    
    if (current != RESULT_SIZE+addm) {
      throw new Error("Results didn't fit RESULT_SIZE");
    }
    return result;
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String classifierTipText() {
    return "The classifier to use.";
  }

  /**
   * Get the value of Classifier.
   *
   * @return Value of Classifier.
   */
  public Classifier getClassifier() {
    
    return m_Template;
  }
  
  /**
   * Sets the classifier.
   *
   * @param newClassifier the new classifier to use.
   */
  public void setClassifier(Classifier newClassifier) {
    
    m_Template = newClassifier;
    updateOptions();

    System.err.println("RegressionSplitEvaluator: In set classifier");
  }

  /**
   * Updates the options that the current classifier is using.
   */
  protected void updateOptions() {
    
    if (m_Template instanceof OptionHandler) {
      m_ClassifierOptions = Utils.joinOptions(((OptionHandler)m_Template)
					      .getOptions());
    } else {
      m_ClassifierOptions = "";
    }
    if (m_Template instanceof Serializable) {
      ObjectStreamClass obs = ObjectStreamClass.lookup(m_Template
						       .getClass());
      m_ClassifierVersion = "" + obs.getSerialVersionUID();
    } else {
      m_ClassifierVersion = "";
    }
  }

  /**
   * Set the Classifier to use, given it's class name. A new classifier will be
   * instantiated.
   *
   * @param newClassifierName the Classifier class name.
   * @throws Exception if the class name is invalid.
   */
  public void setClassifierName(String newClassifierName) throws Exception {

    try {
      setClassifier((Classifier)Class.forName(newClassifierName)
		    .newInstance());
    } catch (Exception ex) {
      throw new Exception("Can't find Classifier with class name: "
			  + newClassifierName);
    }
  }

  /**
   * Gets the raw output from the classifier
   * @return the raw output from the classifier
   */
  public String getRawResultOutput() {
    StringBuffer result = new StringBuffer();

    if (m_Classifier == null) {
      return "<null> classifier";
    }
    result.append(toString());
    result.append("Classifier model: \n"+m_Classifier.toString()+'\n');

    // append the performance statistics
    if (m_result != null) {
      result.append(m_result);
      
      if (m_doesProduce != null) {
	for (int i=0;i<m_doesProduce.length;i++) {
	  if (m_doesProduce[i]) {
	    try {
	      double dv = ((AdditionalMeasureProducer)m_Classifier).
		getMeasure(m_AdditionalMeasures[i]);
	      if (!Instance.isMissingValue(dv)) {
		Double value = new Double(dv);
		result.append(m_AdditionalMeasures[i]+" : "+value+'\n');
	      } else {
		result.append(m_AdditionalMeasures[i]+" : "+'?'+'\n');
	      }
	    } catch (Exception ex) {
	      System.err.println(ex);
	    }
	  } 
	}
      }
    }
    return result.toString();
  }

  /**
   * Returns a text description of the split evaluator.
   *
   * @return a text description of the split evaluator.
   */
  public String toString() {

    String result = "RegressionSplitEvaluator: ";
    if (m_Template == null) {
      return result + "<null> classifier";
    }
    return result + m_Template.getClass().getName() + " " 
      + m_ClassifierOptions + "(version " + m_ClassifierVersion + ")";
  }
} // RegressionSplitEvaluator