evaluation.java

一个数据挖掘软件ALPHAMINERR的整个过程的JAVA版源代码

   */
  public final double SFSchemeEntropy() {

    return m_SumSchemeEntropy;
  }

  /**
   * Returns the entropy per instance for the scheme
   * 
   * @return the scheme entropy per instance
   */
  public final double SFMeanSchemeEntropy() {

    return m_SumSchemeEntropy / m_WithClass;
  }

  /**
   * Returns the total SF, which is the null model entropy minus
   * the scheme entropy.
   * 
   * @return the total SF
   */
  public final double SFEntropyGain() {

    return m_SumPriorEntropy - m_SumSchemeEntropy;
  }

  /**
   * Returns the SF per instance, which is the null model entropy
   * minus the scheme entropy, per instance.
   * 
   * @return the SF per instance
   */
  public final double SFMeanEntropyGain() {
    
    return (m_SumPriorEntropy - m_SumSchemeEntropy) / m_WithClass;
  }

  /**
   * Output the cumulative margin distribution as a string suitable
   * for input for gnuplot or similar package.
   *
   * @return the cumulative margin distribution
   * @exception Exception if the class attribute is nominal
   */
  public String toCumulativeMarginDistributionString() throws Exception {

    if (!m_ClassIsNominal) {
      throw new Exception("Class must be nominal for margin distributions");
    }
    String result = "";
    double cumulativeCount = 0;
    double margin;
    for(int i = 0; i <= k_MarginResolution; i++) {
      if (m_MarginCounts[i] != 0) {
	cumulativeCount += m_MarginCounts[i];
	margin = (double)i * 2.0 / k_MarginResolution - 1.0;
	result = result + Utils.doubleToString(margin, 7, 3) + ' ' 
	+ Utils.doubleToString(cumulativeCount * 100 
			       / m_WithClass, 7, 3) + '\n';
      } else if (i == 0) {
	result = Utils.doubleToString(-1.0, 7, 3) + ' ' 
	+ Utils.doubleToString(0, 7, 3) + '\n';
      }
    }
    return result;
  }


  /**
   * Calls toSummaryString() with no title and no complexity stats
   *
   * @return a summary description of the classifier evaluation
   */
  public String toSummaryString() {

    return toSummaryString("", false);
  }

  /**
   * Calls toSummaryString() with a default title.
   *
   * @param printComplexityStatistics if true, complexity statistics are
   * returned as well
   */
  public String toSummaryString(boolean printComplexityStatistics) {
    
    return toSummaryString("=== Summary ===\n", printComplexityStatistics);
  }

  /**
   * Outputs the performance statistics in summary form. Lists 
   * number (and percentage) of instances classified correctly, 
   * incorrectly and unclassified. Outputs the total number of 
   * instances classified, and the number of instances (if any) 
   * that had no class value provided. 
   *
   * @param title the title for the statistics
   * @param printComplexityStatistics if true, complexity statistics are
   * returned as well
   * @return the summary as a String
   */
  public String toSummaryString(String title, 
				boolean printComplexityStatistics) { 
    
    double mae, mad = 0;
    StringBuffer text = new StringBuffer();

    text.append(title + "\n");
    try {
      if (m_WithClass > 0) {
	if (m_ClassIsNominal) {

	  text.append("Correctly Classified Instances     ");
	  text.append(Utils.doubleToString(correct(), 12, 4) + "     " +
		      Utils.doubleToString(pctCorrect(),
					   12, 4) + " %\n");
	  text.append("Incorrectly Classified Instances   ");
	  text.append(Utils.doubleToString(incorrect(), 12, 4) + "     " +
		      Utils.doubleToString(pctIncorrect(),
					   12, 4) + " %\n");
	  text.append("Kappa statistic                    ");
	  text.append(Utils.doubleToString(kappa(), 12, 4) + "\n");
	  
	  if (m_CostMatrix != null) {
	    text.append("Total Cost                         ");
	    text.append(Utils.doubleToString(totalCost(), 12, 4) + "\n");
	    text.append("Average Cost                       ");
	    text.append(Utils.doubleToString(avgCost(), 12, 4) + "\n");
	  }
	  if (printComplexityStatistics) {
	    text.append("K&B Relative Info Score            ");
	    text.append(Utils.doubleToString(KBRelativeInformation(), 12, 4) 
			+ " %\n");
	    text.append("K&B Information Score              ");
	    text.append(Utils.doubleToString(KBInformation(), 12, 4) 
			+ " bits");
	    text.append(Utils.doubleToString(KBMeanInformation(), 12, 4) 
			+ " bits/instance\n");
	  }
	} else {        
	  text.append("Correlation coefficient            ");
	  text.append(Utils.doubleToString(correlationCoefficient(), 12 , 4) +
		      "\n");
	}
	if (printComplexityStatistics) {
	  text.append("Class complexity | order 0         ");
	  text.append(Utils.doubleToString(SFPriorEntropy(), 12, 4) 
		      + " bits");
	  text.append(Utils.doubleToString(SFMeanPriorEntropy(), 12, 4) 
		      + " bits/instance\n");
	  text.append("Class complexity | scheme          ");
	  text.append(Utils.doubleToString(SFSchemeEntropy(), 12, 4) 
		      + " bits");
	  text.append(Utils.doubleToString(SFMeanSchemeEntropy(), 12, 4) 
		      + " bits/instance\n");
	  text.append("Complexity improvement     (Sf)    ");
	  text.append(Utils.doubleToString(SFEntropyGain(), 12, 4) + " bits");
	  text.append(Utils.doubleToString(SFMeanEntropyGain(), 12, 4) 
		      + " bits/instance\n");
	}

	text.append("Mean absolute error                ");
	text.append(Utils.doubleToString(meanAbsoluteError(), 12, 4) 
		    + "\n");
	text.append("Root mean squared error            ");
	text.append(Utils.
		    doubleToString(rootMeanSquaredError(), 12, 4) 
		    + "\n");
	text.append("Relative absolute error            ");
	text.append(Utils.doubleToString(relativeAbsoluteError(), 
					 12, 4) + " %\n");
	text.append("Root relative squared error        ");
	text.append(Utils.doubleToString(rootRelativeSquaredError(), 
					 12, 4) + " %\n");
      }
      if (Utils.gr(unclassified(), 0)) {
	text.append("UnClassified Instances             ");
	text.append(Utils.doubleToString(unclassified(), 12,4) +  "     " +
		    Utils.doubleToString(pctUnclassified(),
					 12, 4) + " %\n");
      }
      text.append("Total Number of Instances          ");
      text.append(Utils.doubleToString(m_WithClass, 12, 4) + "\n");
      if (m_MissingClass > 0) {
	text.append("Ignored Class Unknown Instances            ");
	text.append(Utils.doubleToString(m_MissingClass, 12, 4) + "\n");
      }
    } catch (Exception ex) {
      // Should never occur since the class is known to be nominal 
      // here
      System.err.println("Arggh - Must be a bug in Evaluation class");
    }
   
    return text.toString(); 
  }
  
  /**
   * Calls toMatrixString() with a default title.
   *
   * @return the confusion matrix as a string
   * @exception Exception if the class is numeric
   */
  public String toMatrixString() throws Exception {

    return toMatrixString("=== Confusion Matrix ===\n");
  }

  /**
   * Outputs the performance statistics as a classification confusion
   * matrix. For each class value, shows the distribution of 
   * predicted class values.
   *
   * @param title the title for the confusion matrix
   * @return the confusion matrix as a String
   * @exception Exception if the class is numeric
   */
  public String toMatrixString(String title) throws Exception {

    StringBuffer text = new StringBuffer();
    char [] IDChars = {'a','b','c','d','e','f','g','h','i','j',
		       'k','l','m','n','o','p','q','r','s','t',
		       'u','v','w','x','y','z'};
    int IDWidth;
    boolean fractional = false;

    if (!m_ClassIsNominal) {
      throw new Exception("Evaluation: No confusion matrix possible!");
    }

    // Find the maximum value in the matrix
    // and check for fractional display requirement 
    double maxval = 0;
    for(int i = 0; i < m_NumClasses; i++) {
      for(int j = 0; j < m_NumClasses; j++) {
	double current = m_ConfusionMatrix[i][j];
        if (current < 0) {
          current *= -10;
        }
	if (current > maxval) {
	  maxval = current;
	}
	double fract = current - Math.rint(current);
	if (!fractional
	    && ((Math.log(fract) / Math.log(10)) >= -2)) {
	  fractional = true;
	}
      }
    }

    IDWidth = 1 + Math.max((int)(Math.log(maxval) / Math.log(10) 
				 + (fractional ? 3 : 0)),
			     (int)(Math.log(m_NumClasses) / 
				   Math.log(IDChars.length)));
    text.append(title).append("\n");
    for(int i = 0; i < m_NumClasses; i++) {
      if (fractional) {
	text.append(" ").append(num2ShortID(i,IDChars,IDWidth - 3))
          .append("   ");
      } else {
	text.append(" ").append(num2ShortID(i,IDChars,IDWidth));
      }
    }
    text.append("   <-- classified as\n");
    for(int i = 0; i< m_NumClasses; i++) { 
      for(int j = 0; j < m_NumClasses; j++) {
	text.append(" ").append(
		    Utils.doubleToString(m_ConfusionMatrix[i][j],
					 IDWidth,
					 (fractional ? 2 : 0)));
      }
      text.append(" | ").append(num2ShortID(i,IDChars,IDWidth))
        .append(" = ").append(m_ClassNames[i]).append("\n");
    }
    return text.toString();
  }

  public String toClassDetailsString() throws Exception {

    return toClassDetailsString("=== Detailed Accuracy By Class ===\n");
  }

  /**
   * Generates a breakdown of the accuracy for each class,
   * incorporating various information-retrieval statistics, such as
   * true/false positive rate, precision/recall/F-Measure.  Should be
   * useful for ROC curves, recall/precision curves.  
   * 
   * @param title the title to prepend the stats string with 
   * @return the statistics presented as a string
   */
  public String toClassDetailsString(String title) throws Exception {

    if (!m_ClassIsNominal) {
      throw new Exception("Evaluation: No confusion matrix possible!");
    }
    StringBuffer text = new StringBuffer(title 
					 + "\nTP Rate   FP Rate"
                                         + "   Precision   Recall"
                                         + "  F-Measure   Class\n");
    for(int i = 0; i < m_NumClasses; i++) {
      text.append(Utils.doubleToString(truePositiveRate(i), 7, 3))
        .append("   ");
      text.append(Utils.doubleToString(falsePositiveRate(i), 7, 3))
        .append("    ");
      text.append(Utils.doubleToString(precision(i), 7, 3))
        .append("   ");
      text.append(Utils.doubleToString(recall(i), 7, 3))
        .append("   ");
      text.append(Utils.doubleToString(fMeasure(i), 7, 3))
        .append("    ");
      text.append(m_ClassNames[i]).append('\n');
    }
    return text.toString();
  }

  /**
   * Calculate the number of true positives with respect to a particular class. 
   * This is defined as<p>
   * <pre>
   * correctly classified positives
   * </pre>
   *
   * @param classIndex the index of the class to consider as "positive"
   * @return the true positive rate
   */
  public double numTruePositives(int classIndex) {

    double correct = 0;
    for (int j = 0; j < m_NumClasses; j++) {
      if (j == classIndex) {
	correct += m_ConfusionMatrix[classIndex][j];
      }
    }
    return correct;
  }

  /**
   * Calculate the true positive rate with respect to a particular class. 
   * This is defined as<p>
   * <pre>
   * correctly classified positives
   * ------------------------------
   *       total positives
   * </pre>
   *
   * @param classIndex the index of the class to consider as "positive"
   * @return the true positive rate
   */
  public double truePositiveRate(int classIndex) {

    double correct = 0, total = 0;
    for (int j = 0; j < m_NumClasses; j++) {
      if (j == classIndex) {
	correct += m_ConfusionMatrix[classIndex][j];
      }
      total += m_ConfusionMatrix[classIndex][j];
    }
    if (total == 0) {
      return 0;
    }
    return correct / total;
  }

  /**
   * Calculate the number of true negatives with respect to a particular class. 
   * This is defined as<p>
   * <pre>
   * correctly classified negatives
   * </pre>
   *
   * @param classIndex the index of the class to consider as "positive"
   * @return the true positive rate
   */
  public double numTrueNegatives(int classIndex) {

    double correct = 0;
    for (int i = 0; i < m_NumClasses; i++) {
      if (i != classIndex) {
	for (int j = 0; j < m_NumClasses; j++) {
	  if (j != classIndex) {
	    correct += m_ConfusionMatrix[i][j];
	  }
	}
      }
    }
    return correct;
  }

  /**
   * Calculate the true negative rate with respect to a particular class. 
   * This is defined as<p>
   * <pre>
   * correctly classified negatives
   * ------------------------------
   *       total negatives
   * </pre>
   *
   * @param classIndex the index of the class to consider as "positive"
   * @return the true positive rate
   */