classifiersplitevaluator.java

一个数据挖掘软件ALPHAMINERR的整个过程的JAVA版源代码

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

    // IR stats
    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++] = "";

    // add any additional measures
    for (int i=0;i<addm;i++) {
      resultTypes[current++] = doub;
    }
    if (current != overall_length) {
      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;
    int overall_length = RESULT_SIZE+addm;
    overall_length += NUM_IR_STATISTICS;
    String [] resultNames = new String[overall_length];
    int current = 0;
    resultNames[current++] = "Number_of_training_instances";
    resultNames[current++] = "Number_of_testing_instances";

    // Basic performance stats - right vs wrong
    resultNames[current++] = "Number_correct";
    resultNames[current++] = "Number_incorrect";
    resultNames[current++] = "Number_unclassified";
    resultNames[current++] = "Percent_correct";
    resultNames[current++] = "Percent_incorrect";
    resultNames[current++] = "Percent_unclassified";
    resultNames[current++] = "Kappa_statistic";

    // 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";

    // 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";

    // K&B stats
    resultNames[current++] = "KB_information";
    resultNames[current++] = "KB_mean_information";
    resultNames[current++] = "KB_relative_information";

    // IR stats
    resultNames[current++] = "True_positive_rate";
    resultNames[current++] = "Num_true_positives";
    resultNames[current++] = "False_positive_rate";
    resultNames[current++] = "Num_false_positives";
    resultNames[current++] = "True_negative_rate";
    resultNames[current++] = "Num_true_negatives";
    resultNames[current++] = "False_negative_rate";
    resultNames[current++] = "Num_false_negatives";
    resultNames[current++] = "IR_precision";
    resultNames[current++] = "IR_recall";
    resultNames[current++] = "F_measure";

    // Timing stats
    resultNames[current++] = "Time_training";
    resultNames[current++] = "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 != overall_length) {
      throw new Error("ResultNames didn't fit RESULT_SIZE");
    }
    return resultNames;
  }

  /**
   * Gets the results for the supplied train and test datasets.
   *
   * @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).
   * @exception Exception if a problem occurs while getting the results
   */
  public Object [] getResult(Instances train, Instances test) 
    throws Exception {
    
    if (train.classAttribute().type() != Attribute.NOMINAL) {
      throw new Exception("Class attribute is not nominal!");
    }
    if (m_Classifier == null) {
      throw new Exception("No classifier has been specified");
    }
    int addm = (m_AdditionalMeasures != null) 
      ? m_AdditionalMeasures.length 
      : 0;
    int overall_length = RESULT_SIZE+addm;
    overall_length += NUM_IR_STATISTICS;

    Object [] result = new Object[overall_length];
    Evaluation eval = new Evaluation(train);
    long trainTimeStart = System.currentTimeMillis();
    m_Classifier.buildClassifier(train);
    long trainTimeElapsed = System.currentTimeMillis() - trainTimeStart;
    long testTimeStart = System.currentTimeMillis();
    eval.evaluateModel(m_Classifier, test);
    long testTimeElapsed = System.currentTimeMillis() - testTimeStart;
    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(train.numInstances());
    result[current++] = new Double(eval.numInstances());
    result[current++] = new Double(eval.correct());
    result[current++] = new Double(eval.incorrect());
    result[current++] = new Double(eval.unclassified());
    result[current++] = new Double(eval.pctCorrect());
    result[current++] = new Double(eval.pctIncorrect());
    result[current++] = new Double(eval.pctUnclassified());
    result[current++] = new Double(eval.kappa());

    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.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());

    // K&B stats
    result[current++] = new Double(eval.KBInformation());
    result[current++] = new Double(eval.KBMeanInformation());
    result[current++] = new Double(eval.KBRelativeInformation());

    // IR stats
    result[current++] = new Double(eval.truePositiveRate(m_IRclass));
    result[current++] = new Double(eval.numTruePositives(m_IRclass));
    result[current++] = new Double(eval.falsePositiveRate(m_IRclass));
    result[current++] = new Double(eval.numFalsePositives(m_IRclass));
    result[current++] = new Double(eval.trueNegativeRate(m_IRclass));
    result[current++] = new Double(eval.numTrueNegatives(m_IRclass));
    result[current++] = new Double(eval.falseNegativeRate(m_IRclass));
    result[current++] = new Double(eval.numFalseNegatives(m_IRclass));
    result[current++] = new Double(eval.precision(m_IRclass));
    result[current++] = new Double(eval.recall(m_IRclass));
    result[current++] = new Double(eval.fMeasure(m_IRclass));

    // Timing stats
    result[current++] = new Double(trainTimeElapsed / 1000.0);
    result[current++] = new Double(testTimeElapsed / 1000.0);

    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]);
	  Double value = new Double(dv);

	  result[current++] = value;
	} catch (Exception ex) {
	  System.err.println(ex);
	}
      } else {
	result[current++] = null;
      }
    }

    if (current != overall_length) {
      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_Classifier;
  }
  
  /**
   * Sets the classifier.
   *
   * @param newClassifier the new classifier to use.
   */
  public void setClassifier(Classifier newClassifier) {
    
    m_Classifier = newClassifier;
    updateOptions();
  }
  
  /**
   * Get the value of ClassForIRStatistics.
   * @return Value of ClassForIRStatistics.
   */
  public int getClassForIRStatistics() {
    
    return m_IRclass;
  }
  
  /**
   * Set the value of ClassForIRStatistics.
   * @param v  Value to assign to ClassForIRStatistics.
   */
  public void setClassForIRStatistics(int v) {
    
    m_IRclass = v;
  }
  
  /**
   * Updates the options that the current classifier is using.
   */
  protected void updateOptions() {
    
    if (m_Classifier instanceof OptionHandler) {
      m_ClassifierOptions = Utils.joinOptions(((OptionHandler)m_Classifier)
					      .getOptions());
    } else {
      m_ClassifierOptions = "";
    }
    if (m_Classifier instanceof Serializable) {
      ObjectStreamClass obs = ObjectStreamClass.lookup(m_Classifier
						       .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 newClassifier the Classifier class name.
   * @exception 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]);
	      Double value = new Double(dv);
	      
	      result.append(m_AdditionalMeasures[i]+" : "+value+'\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 = "ClassifierSplitEvaluator: ";
    if (m_Classifier == null) {
      return result + "<null> classifier";
    }
    return result + m_Classifier.getClass().getName() + " " 
      + m_ClassifierOptions + "(version " + m_ClassifierVersion + ")";
  }
} // ClassifierSplitEvaluator