Class Evaluation

  • All Implemented Interfaces:
    RevisionHandler, Summarizable

    public class Evaluation
    extends java.lang.Object
    implements Summarizable, RevisionHandler
    Class for evaluating machine learning models.

    -------------------------------------------------------------------

    General options when evaluating a learning scheme from the command-line:

    -t filename
    Name of the file with the training data. (required)

    -T filename
    Name of the file with the test data. If missing a cross-validation is performed.

    -c index
    Index of the class attribute (1, 2, ...; default: last).

    -x number
    The number of folds for the cross-validation (default: 10).

    -no-cv
    No cross validation. If no test file is provided, no evaluation is done.

    -split-percentage percentage
    Sets the percentage for the train/test set split, e.g., 66.

    -preserve-order
    Preserves the order in the percentage split instead of randomizing the data first with the seed value ('-s').

    -s seed
    Random number seed for the cross-validation and percentage split (default: 1).

    -m filename
    The name of a file containing a cost matrix.

    -l filename
    Loads classifier from the given file. In case the filename ends with ".xml", a PMML file is loaded or, if that fails, options are loaded from XML.

    -d filename
    Saves classifier built from the training data into the given file. In case the filename ends with ".xml" the options are saved XML, not the model.

    -v
    Outputs no statistics for the training data.

    -o
    Outputs statistics only, not the classifier.

    -i
    Outputs information-retrieval statistics per class.

    -k
    Outputs information-theoretic statistics.

    -p range
    Outputs predictions for test instances (or the train instances if no test instances provided and -no-cv is used), along with the attributes in the specified range (and nothing else). Use '-p 0' if no attributes are desired.

    -distribution
    Outputs the distribution instead of only the prediction in conjunction with the '-p' option (only nominal classes).

    -r
    Outputs cumulative margin distribution (and nothing else).

    -g
    Only for classifiers that implement "Graphable." Outputs the graph representation of the classifier (and nothing else).

    -xml filename | xml-string
    Retrieves the options from the XML-data instead of the command line.

    -threshold-file file
    The file to save the threshold data to. The format is determined by the extensions, e.g., '.arff' for ARFF format or '.csv' for CSV.

    -threshold-label label
    The class label to determine the threshold data for (default is the first label)

    -------------------------------------------------------------------

    Example usage as the main of a classifier (called FunkyClassifier):

     public static void main(String [] args) {
       runClassifier(new FunkyClassifier(), args);
     }
     

    ------------------------------------------------------------------

    Example usage from within an application:

     Instances trainInstances = ... instances got from somewhere
     Instances testInstances = ... instances got from somewhere
     Classifier scheme = ... scheme got from somewhere
     
     Evaluation evaluation = new Evaluation(trainInstances);
     evaluation.evaluateModel(scheme, testInstances);
     System.out.println(evaluation.toSummaryString());
     
    Version:
    $Revision: 10974 $
    Author:
    Eibe Frank (eibe@cs.waikato.ac.nz), Len Trigg (trigg@cs.waikato.ac.nz)
    • Constructor Summary

      Constructors 
      Constructor Description
      Evaluation​(Instances data)
      Initializes all the counters for the evaluation.
      Evaluation​(Instances data, CostMatrix costMatrix)
      Initializes all the counters for the evaluation and also takes a cost matrix as parameter.
    • Method Summary

      All Methods Static Methods Instance Methods Concrete Methods 
      Modifier and Type Method Description
      double areaUnderROC​(int classIndex)
      Returns the area under ROC for those predictions that have been collected in the evaluateClassifier(Classifier, Instances) method.
      double avgCost()
      Gets the average cost, that is, total cost of misclassifications (incorrect plus unclassified) over the total number of instances.
      double[][] confusionMatrix()
      Returns a copy of the confusion matrix.
      double correct()
      Gets the number of instances correctly classified (that is, for which a correct prediction was made).
      double correlationCoefficient()
      Returns the correlation coefficient if the class is numeric.
      void crossValidateModel​(java.lang.String classifierString, Instances data, int numFolds, java.lang.String[] options, java.util.Random random)
      Performs a (stratified if class is nominal) cross-validation for a classifier on a set of instances.
      void crossValidateModel​(Classifier classifier, Instances data, int numFolds, java.util.Random random, java.lang.Object... forPredictionsPrinting)
      Performs a (stratified if class is nominal) cross-validation for a classifier on a set of instances.
      boolean equals​(java.lang.Object obj)
      Tests whether the current evaluation object is equal to another evaluation object
      double errorRate()
      Returns the estimated error rate or the root mean squared error (if the class is numeric).
      static java.lang.String evaluateModel​(java.lang.String classifierString, java.lang.String[] options)
      Evaluates a classifier with the options given in an array of strings.
      static java.lang.String evaluateModel​(Classifier classifier, java.lang.String[] options)
      Evaluates a classifier with the options given in an array of strings.
      double[] evaluateModel​(Classifier classifier, Instances data, java.lang.Object... forPredictionsPrinting)
      Evaluates the classifier on a given set of instances.
      double evaluateModelOnce​(double[] dist, Instance instance)
      Evaluates the supplied distribution on a single instance.
      void evaluateModelOnce​(double prediction, Instance instance)
      Evaluates the supplied prediction on a single instance.
      double evaluateModelOnce​(Classifier classifier, Instance instance)
      Evaluates the classifier on a single instance.
      double evaluateModelOnceAndRecordPrediction​(double[] dist, Instance instance)
      Evaluates the supplied distribution on a single instance.
      double evaluateModelOnceAndRecordPrediction​(Classifier classifier, Instance instance)
      Evaluates the classifier on a single instance and records the prediction (if the class is nominal).
      double falseNegativeRate​(int classIndex)
      Calculate the false negative rate with respect to a particular class.
      double falsePositiveRate​(int classIndex)
      Calculate the false positive rate with respect to a particular class.
      double fMeasure​(int classIndex)
      Calculate the F-Measure with respect to a particular class.
      double[] getClassPriors()
      Get the current weighted class counts
      java.lang.String getRevision()
      Returns the revision string.
      double incorrect()
      Gets the number of instances incorrectly classified (that is, for which an incorrect prediction was made).
      double kappa()
      Returns value of kappa statistic if class is nominal.
      double KBInformation()
      Return the total Kononenko & Bratko Information score in bits
      double KBMeanInformation()
      Return the Kononenko & Bratko Information score in bits per instance.
      double KBRelativeInformation()
      Return the Kononenko & Bratko Relative Information score
      static void main​(java.lang.String[] args)
      A test method for this class.
      double meanAbsoluteError()
      Returns the mean absolute error.
      double meanPriorAbsoluteError()
      Returns the mean absolute error of the prior.
      double numFalseNegatives​(int classIndex)
      Calculate number of false negatives with respect to a particular class.
      double numFalsePositives​(int classIndex)
      Calculate number of false positives with respect to a particular class.
      double numInstances()
      Gets the number of test instances that had a known class value (actually the sum of the weights of test instances with known class value).
      double numTrueNegatives​(int classIndex)
      Calculate the number of true negatives with respect to a particular class.
      double numTruePositives​(int classIndex)
      Calculate the number of true positives with respect to a particular class.
      double pctCorrect()
      Gets the percentage of instances correctly classified (that is, for which a correct prediction was made).
      double pctIncorrect()
      Gets the percentage of instances incorrectly classified (that is, for which an incorrect prediction was made).
      double pctUnclassified()
      Gets the percentage of instances not classified (that is, for which no prediction was made by the classifier).
      double precision​(int classIndex)
      Calculate the precision with respect to a particular class.
      FastVector predictions()
      Returns the predictions that have been collected.
      static void printClassifications​(Classifier classifier, Instances train, ConverterUtils.DataSource testSource, int classIndex, Range attributesToOutput, boolean printDistribution, java.lang.StringBuffer text)
      Prints the predictions for the given dataset into a supplied StringBuffer
      static void printClassifications​(Classifier classifier, Instances train, ConverterUtils.DataSource testSource, int classIndex, Range attributesToOutput, java.lang.StringBuffer predsText)
      Prints the predictions for the given dataset into a String variable.
      double priorEntropy()
      Calculate the entropy of the prior distribution
      double recall​(int classIndex)
      Calculate the recall with respect to a particular class.
      double relativeAbsoluteError()
      Returns the relative absolute error.
      double rootMeanPriorSquaredError()
      Returns the root mean prior squared error.
      double rootMeanSquaredError()
      Returns the root mean squared error.
      double rootRelativeSquaredError()
      Returns the root relative squared error if the class is numeric.
      void setPriors​(Instances train)
      Sets the class prior probabilities
      double SFEntropyGain()
      Returns the total SF, which is the null model entropy minus the scheme entropy.
      double SFMeanEntropyGain()
      Returns the SF per instance, which is the null model entropy minus the scheme entropy, per instance.
      double SFMeanPriorEntropy()
      Returns the entropy per instance for the null model
      double SFMeanSchemeEntropy()
      Returns the entropy per instance for the scheme
      double SFPriorEntropy()
      Returns the total entropy for the null model
      double SFSchemeEntropy()
      Returns the total entropy for the scheme
      java.lang.String toClassDetailsString()
      Generates a breakdown of the accuracy for each class (with default title), incorporating various information-retrieval statistics, such as true/false positive rate, precision/recall/F-Measure.
      java.lang.String toClassDetailsString​(java.lang.String title)
      Generates a breakdown of the accuracy for each class, incorporating various information-retrieval statistics, such as true/false positive rate, precision/recall/F-Measure.
      java.lang.String toCumulativeMarginDistributionString()
      Output the cumulative margin distribution as a string suitable for input for gnuplot or similar package.
      java.lang.String toMatrixString()
      Calls toMatrixString() with a default title.
      java.lang.String toMatrixString​(java.lang.String title)
      Outputs the performance statistics as a classification confusion matrix.
      java.lang.String toSummaryString()
      Calls toSummaryString() with no title and no complexity stats
      java.lang.String toSummaryString​(boolean printComplexityStatistics)
      Calls toSummaryString() with a default title.
      java.lang.String toSummaryString​(java.lang.String title, boolean printComplexityStatistics)
      Outputs the performance statistics in summary form.
      double totalCost()
      Gets the total cost, that is, the cost of each prediction times the weight of the instance, summed over all instances.
      double trueNegativeRate​(int classIndex)
      Calculate the true negative rate with respect to a particular class.
      double truePositiveRate​(int classIndex)
      Calculate the true positive rate with respect to a particular class.
      double unclassified()
      Gets the number of instances not classified (that is, for which no prediction was made by the classifier).
      void updatePriors​(Instance instance)
      Updates the class prior probabilities (when incrementally training)
      void useNoPriors()
      disables the use of priors, e.g., in case of de-serialized schemes that have no access to the original training set, but are evaluated on a set set.
      double weightedAreaUnderROC()
      Calculates the weighted (by class size) AUC.
      double weightedFalseNegativeRate()
      Calculates the weighted (by class size) false negative rate.
      double weightedFalsePositiveRate()
      Calculates the weighted (by class size) false positive rate.
      double weightedFMeasure()
      Calculates the weighted (by class size) F-Measure.
      double weightedPrecision()
      Calculates the weighted (by class size) false precision.
      double weightedRecall()
      Calculates the weighted (by class size) recall.
      double weightedTrueNegativeRate()
      Calculates the weighted (by class size) true negative rate.
      double weightedTruePositiveRate()
      Calculates the weighted (by class size) true positive rate.
      static java.lang.String wekaStaticWrapper​(Sourcable classifier, java.lang.String className)
      Wraps a static classifier in enough source to test using the weka class libraries.
      • Methods inherited from class java.lang.Object

        getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
    • Constructor Detail

      • Evaluation

        public Evaluation​(Instances data)
                   throws java.lang.Exception
        Initializes all the counters for the evaluation. Use useNoPriors() if the dataset is the test set and you can't initialize with the priors from the training set via setPriors(Instances).
        Parameters:
        data - set of training instances, to get some header information and prior class distribution information
        Throws:
        java.lang.Exception - if the class is not defined
        See Also:
        useNoPriors(), setPriors(Instances)
      • Evaluation

        public Evaluation​(Instances data,
                          CostMatrix costMatrix)
                   throws java.lang.Exception
        Initializes all the counters for the evaluation and also takes a cost matrix as parameter. Use useNoPriors() if the dataset is the test set and you can't initialize with the priors from the training set via setPriors(Instances).
        Parameters:
        data - set of training instances, to get some header information and prior class distribution information
        costMatrix - the cost matrix---if null, default costs will be used
        Throws:
        java.lang.Exception - if cost matrix is not compatible with data, the class is not defined or the class is numeric
        See Also:
        useNoPriors(), setPriors(Instances)
    • Method Detail

      • areaUnderROC

        public double areaUnderROC​(int classIndex)
        Returns the area under ROC for those predictions that have been collected in the evaluateClassifier(Classifier, Instances) method. Returns Instance.missingValue() if the area is not available.
        Parameters:
        classIndex - the index of the class to consider as "positive"
        Returns:
        the area under the ROC curve or not a number
      • weightedAreaUnderROC

        public double weightedAreaUnderROC()
        Calculates the weighted (by class size) AUC.
        Returns:
        the weighted AUC.
      • confusionMatrix

        public double[][] confusionMatrix()
        Returns a copy of the confusion matrix.
        Returns:
        a copy of the confusion matrix as a two-dimensional array
      • crossValidateModel

        public void crossValidateModel​(Classifier classifier,
                                       Instances data,
                                       int numFolds,
                                       java.util.Random random,
                                       java.lang.Object... forPredictionsPrinting)
                                throws java.lang.Exception
        Performs a (stratified if class is nominal) cross-validation for a classifier on a set of instances. Now performs a deep copy of the classifier before each call to buildClassifier() (just in case the classifier is not initialized properly).
        Parameters:
        classifier - the classifier with any options set.
        data - the data on which the cross-validation is to be performed
        numFolds - the number of folds for the cross-validation
        random - random number generator for randomization
        forPredictionsString - varargs parameter that, if supplied, is expected to hold a StringBuffer to print predictions to, a Range of attributes to output and a Boolean (true if the distribution is to be printed)
        Throws:
        java.lang.Exception - if a classifier could not be generated successfully or the class is not defined
      • crossValidateModel

        public void crossValidateModel​(java.lang.String classifierString,
                                       Instances data,
                                       int numFolds,
                                       java.lang.String[] options,
                                       java.util.Random random)
                                throws java.lang.Exception
        Performs a (stratified if class is nominal) cross-validation for a classifier on a set of instances.
        Parameters:
        classifierString - a string naming the class of the classifier
        data - the data on which the cross-validation is to be performed
        numFolds - the number of folds for the cross-validation
        options - the options to the classifier. Any options
        random - the random number generator for randomizing the data accepted by the classifier will be removed from this array.
        Throws:
        java.lang.Exception - if a classifier could not be generated successfully or the class is not defined
      • evaluateModel

        public static java.lang.String evaluateModel​(java.lang.String classifierString,
                                                     java.lang.String[] options)
                                              throws java.lang.Exception
        Evaluates a classifier with the options given in an array of strings.

        Valid options are:

        -t filename
        Name of the file with the training data. (required)

        -T filename
        Name of the file with the test data. If missing a cross-validation is performed.

        -c index
        Index of the class attribute (1, 2, ...; default: last).

        -x number
        The number of folds for the cross-validation (default: 10).

        -no-cv
        No cross validation. If no test file is provided, no evaluation is done.

        -split-percentage percentage
        Sets the percentage for the train/test set split, e.g., 66.

        -preserve-order
        Preserves the order in the percentage split instead of randomizing the data first with the seed value ('-s').

        -s seed
        Random number seed for the cross-validation and percentage split (default: 1).

        -m filename
        The name of a file containing a cost matrix.

        -l filename
        Loads classifier from the given file. In case the filename ends with ".xml",a PMML file is loaded or, if that fails, options are loaded from XML.

        -d filename
        Saves classifier built from the training data into the given file. In case the filename ends with ".xml" the options are saved XML, not the model.

        -v
        Outputs no statistics for the training data.

        -o
        Outputs statistics only, not the classifier.

        -i
        Outputs detailed information-retrieval statistics per class.

        -k
        Outputs information-theoretic statistics.

        -p range
        Outputs predictions for test instances (or the train instances if no test instances provided and -no-cv is used), along with the attributes in the specified range (and nothing else). Use '-p 0' if no attributes are desired.

        -distribution
        Outputs the distribution instead of only the prediction in conjunction with the '-p' option (only nominal classes).

        -r
        Outputs cumulative margin distribution (and nothing else).

        -g
        Only for classifiers that implement "Graphable." Outputs the graph representation of the classifier (and nothing else).

        -xml filename | xml-string
        Retrieves the options from the XML-data instead of the command line.

        -threshold-file file
        The file to save the threshold data to. The format is determined by the extensions, e.g., '.arff' for ARFF format or '.csv' for CSV.

        -threshold-label label
        The class label to determine the threshold data for (default is the first label)

        Parameters:
        classifierString - class of machine learning classifier as a string
        options - the array of string containing the options
        Returns:
        a string describing the results
        Throws:
        java.lang.Exception - if model could not be evaluated successfully
      • main

        public static void main​(java.lang.String[] args)
        A test method for this class. Just extracts the first command line argument as a classifier class name and calls evaluateModel.
        Parameters:
        args - an array of command line arguments, the first of which must be the class name of a classifier.
      • evaluateModel

        public static java.lang.String evaluateModel​(Classifier classifier,
                                                     java.lang.String[] options)
                                              throws java.lang.Exception
        Evaluates a classifier with the options given in an array of strings.

        Valid options are:

        -t name of training file
        Name of the file with the training data. (required)

        -T name of test file
        Name of the file with the test data. If missing a cross-validation is performed.

        -c class index
        Index of the class attribute (1, 2, ...; default: last).

        -x number of folds
        The number of folds for the cross-validation (default: 10).

        -no-cv
        No cross validation. If no test file is provided, no evaluation is done.

        -split-percentage percentage
        Sets the percentage for the train/test set split, e.g., 66.

        -preserve-order
        Preserves the order in the percentage split instead of randomizing the data first with the seed value ('-s').

        -s seed
        Random number seed for the cross-validation and percentage split (default: 1).

        -m file with cost matrix
        The name of a file containing a cost matrix.

        -l filename
        Loads classifier from the given file. In case the filename ends with ".xml",a PMML file is loaded or, if that fails, options are loaded from XML.

        -d filename
        Saves classifier built from the training data into the given file. In case the filename ends with ".xml" the options are saved XML, not the model.

        -v
        Outputs no statistics for the training data.

        -o
        Outputs statistics only, not the classifier.

        -i
        Outputs detailed information-retrieval statistics per class.

        -k
        Outputs information-theoretic statistics.

        -p range
        Outputs predictions for test instances (or the train instances if no test instances provided and -no-cv is used), along with the attributes in the specified range (and nothing else). Use '-p 0' if no attributes are desired.

        -distribution
        Outputs the distribution instead of only the prediction in conjunction with the '-p' option (only nominal classes).

        -r
        Outputs cumulative margin distribution (and nothing else).

        -g
        Only for classifiers that implement "Graphable." Outputs the graph representation of the classifier (and nothing else).

        -xml filename | xml-string
        Retrieves the options from the XML-data instead of the command line.

        Parameters:
        classifier - machine learning classifier
        options - the array of string containing the options
        Returns:
        a string describing the results
        Throws:
        java.lang.Exception - if model could not be evaluated successfully
      • evaluateModel

        public double[] evaluateModel​(Classifier classifier,
                                      Instances data,
                                      java.lang.Object... forPredictionsPrinting)
                               throws java.lang.Exception
        Evaluates the classifier on a given set of instances. Note that the data must have exactly the same format (e.g. order of attributes) as the data used to train the classifier! Otherwise the results will generally be meaningless.
        Parameters:
        classifier - machine learning classifier
        data - set of test instances for evaluation
        forPredictionsString - varargs parameter that, if supplied, is expected to hold a StringBuffer to print predictions to, a Range of attributes to output and a Boolean (true if the distribution is to be printed)
        Returns:
        the predictions
        Throws:
        java.lang.Exception - if model could not be evaluated successfully
      • evaluateModelOnceAndRecordPrediction

        public double evaluateModelOnceAndRecordPrediction​(Classifier classifier,
                                                           Instance instance)
                                                    throws java.lang.Exception
        Evaluates the classifier on a single instance and records the prediction (if the class is nominal).
        Parameters:
        classifier - machine learning classifier
        instance - the test instance to be classified
        Returns:
        the prediction made by the clasifier
        Throws:
        java.lang.Exception - if model could not be evaluated successfully or the data contains string attributes
      • evaluateModelOnce

        public double evaluateModelOnce​(Classifier classifier,
                                        Instance instance)
                                 throws java.lang.Exception
        Evaluates the classifier on a single instance.
        Parameters:
        classifier - machine learning classifier
        instance - the test instance to be classified
        Returns:
        the prediction made by the clasifier
        Throws:
        java.lang.Exception - if model could not be evaluated successfully or the data contains string attributes
      • evaluateModelOnce

        public double evaluateModelOnce​(double[] dist,
                                        Instance instance)
                                 throws java.lang.Exception
        Evaluates the supplied distribution on a single instance.
        Parameters:
        dist - the supplied distribution
        instance - the test instance to be classified
        Returns:
        the prediction
        Throws:
        java.lang.Exception - if model could not be evaluated successfully
      • evaluateModelOnceAndRecordPrediction

        public double evaluateModelOnceAndRecordPrediction​(double[] dist,
                                                           Instance instance)
                                                    throws java.lang.Exception
        Evaluates the supplied distribution on a single instance.
        Parameters:
        dist - the supplied distribution
        instance - the test instance to be classified
        Returns:
        the prediction
        Throws:
        java.lang.Exception - if model could not be evaluated successfully
      • evaluateModelOnce

        public void evaluateModelOnce​(double prediction,
                                      Instance instance)
                               throws java.lang.Exception
        Evaluates the supplied prediction on a single instance.
        Parameters:
        prediction - the supplied prediction
        instance - the test instance to be classified
        Throws:
        java.lang.Exception - if model could not be evaluated successfully
      • predictions

        public FastVector predictions()
        Returns the predictions that have been collected.
        Returns:
        a reference to the FastVector containing the predictions that have been collected. This should be null if no predictions have been collected (e.g. if the class is numeric).
      • wekaStaticWrapper

        public static java.lang.String wekaStaticWrapper​(Sourcable classifier,
                                                         java.lang.String className)
                                                  throws java.lang.Exception
        Wraps a static classifier in enough source to test using the weka class libraries.
        Parameters:
        classifier - a Sourcable Classifier
        className - the name to give to the source code class
        Returns:
        the source for a static classifier that can be tested with weka libraries.
        Throws:
        java.lang.Exception - if code-generation fails
      • numInstances

        public final double numInstances()
        Gets the number of test instances that had a known class value (actually the sum of the weights of test instances with known class value).
        Returns:
        the number of test instances with known class
      • incorrect

        public final double incorrect()
        Gets the number of instances incorrectly classified (that is, for which an incorrect prediction was made). (Actually the sum of the weights of these instances)
        Returns:
        the number of incorrectly classified instances
      • pctIncorrect

        public final double pctIncorrect()
        Gets the percentage of instances incorrectly classified (that is, for which an incorrect prediction was made).
        Returns:
        the percent of incorrectly classified instances (between 0 and 100)
      • totalCost

        public final double totalCost()
        Gets the total cost, that is, the cost of each prediction times the weight of the instance, summed over all instances.
        Returns:
        the total cost
      • avgCost

        public final double avgCost()
        Gets the average cost, that is, total cost of misclassifications (incorrect plus unclassified) over the total number of instances.
        Returns:
        the average cost.
      • correct

        public final double correct()
        Gets the number of instances correctly classified (that is, for which a correct prediction was made). (Actually the sum of the weights of these instances)
        Returns:
        the number of correctly classified instances
      • pctCorrect

        public final double pctCorrect()
        Gets the percentage of instances correctly classified (that is, for which a correct prediction was made).
        Returns:
        the percent of correctly classified instances (between 0 and 100)
      • unclassified

        public final double unclassified()
        Gets the number of instances not classified (that is, for which no prediction was made by the classifier). (Actually the sum of the weights of these instances)
        Returns:
        the number of unclassified instances
      • pctUnclassified

        public final double pctUnclassified()
        Gets the percentage of instances not classified (that is, for which no prediction was made by the classifier).
        Returns:
        the percent of unclassified instances (between 0 and 100)
      • errorRate

        public final double errorRate()
        Returns the estimated error rate or the root mean squared error (if the class is numeric). If a cost matrix was given this error rate gives the average cost.
        Returns:
        the estimated error rate (between 0 and 1, or between 0 and maximum cost)
      • kappa

        public final double kappa()
        Returns value of kappa statistic if class is nominal.
        Returns:
        the value of the kappa statistic
      • correlationCoefficient

        public final double correlationCoefficient()
                                            throws java.lang.Exception
        Returns the correlation coefficient if the class is numeric.
        Returns:
        the correlation coefficient
        Throws:
        java.lang.Exception - if class is not numeric
      • meanAbsoluteError

        public final double meanAbsoluteError()
        Returns the mean absolute error. Refers to the error of the predicted values for numeric classes, and the error of the predicted probability distribution for nominal classes.
        Returns:
        the mean absolute error
      • meanPriorAbsoluteError

        public final double meanPriorAbsoluteError()
        Returns the mean absolute error of the prior.
        Returns:
        the mean absolute error
      • relativeAbsoluteError

        public final double relativeAbsoluteError()
                                           throws java.lang.Exception
        Returns the relative absolute error.
        Returns:
        the relative absolute error
        Throws:
        java.lang.Exception - if it can't be computed
      • rootMeanSquaredError

        public final double rootMeanSquaredError()
        Returns the root mean squared error.
        Returns:
        the root mean squared error
      • rootMeanPriorSquaredError

        public final double rootMeanPriorSquaredError()
        Returns the root mean prior squared error.
        Returns:
        the root mean prior squared error
      • rootRelativeSquaredError

        public final double rootRelativeSquaredError()
        Returns the root relative squared error if the class is numeric.
        Returns:
        the root relative squared error
      • priorEntropy

        public final double priorEntropy()
                                  throws java.lang.Exception
        Calculate the entropy of the prior distribution
        Returns:
        the entropy of the prior distribution
        Throws:
        java.lang.Exception - if the class is not nominal
      • KBInformation

        public final double KBInformation()
                                   throws java.lang.Exception
        Return the total Kononenko & Bratko Information score in bits
        Returns:
        the K&B information score
        Throws:
        java.lang.Exception - if the class is not nominal
      • KBMeanInformation

        public final double KBMeanInformation()
                                       throws java.lang.Exception
        Return the Kononenko & Bratko Information score in bits per instance.
        Returns:
        the K&B information score
        Throws:
        java.lang.Exception - if the class is not nominal
      • KBRelativeInformation

        public final double KBRelativeInformation()
                                           throws java.lang.Exception
        Return the Kononenko & Bratko Relative Information score
        Returns:
        the K&B relative information score
        Throws:
        java.lang.Exception - if the class is not nominal
      • SFPriorEntropy

        public final double SFPriorEntropy()
        Returns the total entropy for the null model
        Returns:
        the total null model entropy
      • SFMeanPriorEntropy

        public final double SFMeanPriorEntropy()
        Returns the entropy per instance for the null model
        Returns:
        the null model entropy per instance
      • SFSchemeEntropy

        public final double SFSchemeEntropy()
        Returns the total entropy for the scheme
        Returns:
        the total scheme entropy
      • SFMeanSchemeEntropy

        public final double SFMeanSchemeEntropy()
        Returns the entropy per instance for the scheme
        Returns:
        the scheme entropy per instance
      • SFEntropyGain

        public final double SFEntropyGain()
        Returns the total SF, which is the null model entropy minus the scheme entropy.
        Returns:
        the total SF
      • SFMeanEntropyGain

        public final double SFMeanEntropyGain()
        Returns the SF per instance, which is the null model entropy minus the scheme entropy, per instance.
        Returns:
        the SF per instance
      • toCumulativeMarginDistributionString

        public java.lang.String toCumulativeMarginDistributionString()
                                                              throws java.lang.Exception
        Output the cumulative margin distribution as a string suitable for input for gnuplot or similar package.
        Returns:
        the cumulative margin distribution
        Throws:
        java.lang.Exception - if the class attribute is nominal
      • toSummaryString

        public java.lang.String toSummaryString()
        Calls toSummaryString() with no title and no complexity stats
        Specified by:
        toSummaryString in interface Summarizable
        Returns:
        a summary description of the classifier evaluation
      • toSummaryString

        public java.lang.String toSummaryString​(boolean printComplexityStatistics)
        Calls toSummaryString() with a default title.
        Parameters:
        printComplexityStatistics - if true, complexity statistics are returned as well
        Returns:
        the summary string
      • toSummaryString

        public java.lang.String toSummaryString​(java.lang.String title,
                                                boolean 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.
        Parameters:
        title - the title for the statistics
        printComplexityStatistics - if true, complexity statistics are returned as well
        Returns:
        the summary as a String
      • toMatrixString

        public java.lang.String toMatrixString()
                                        throws java.lang.Exception
        Calls toMatrixString() with a default title.
        Returns:
        the confusion matrix as a string
        Throws:
        java.lang.Exception - if the class is numeric
      • toMatrixString

        public java.lang.String toMatrixString​(java.lang.String title)
                                        throws java.lang.Exception
        Outputs the performance statistics as a classification confusion matrix. For each class value, shows the distribution of predicted class values.
        Parameters:
        title - the title for the confusion matrix
        Returns:
        the confusion matrix as a String
        Throws:
        java.lang.Exception - if the class is numeric
      • toClassDetailsString

        public java.lang.String toClassDetailsString()
                                              throws java.lang.Exception
        Generates a breakdown of the accuracy for each class (with default title), incorporating various information-retrieval statistics, such as true/false positive rate, precision/recall/F-Measure. Should be useful for ROC curves, recall/precision curves.
        Returns:
        the statistics presented as a string
        Throws:
        java.lang.Exception - if class is not nominal
      • toClassDetailsString

        public java.lang.String toClassDetailsString​(java.lang.String title)
                                              throws java.lang.Exception
        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.
        Parameters:
        title - the title to prepend the stats string with
        Returns:
        the statistics presented as a string
        Throws:
        java.lang.Exception - if class is not nominal
      • numTruePositives

        public double numTruePositives​(int classIndex)
        Calculate the number of true positives with respect to a particular class. This is defined as

         correctly classified positives
         
        Parameters:
        classIndex - the index of the class to consider as "positive"
        Returns:
        the true positive rate
      • truePositiveRate

        public double truePositiveRate​(int classIndex)
        Calculate the true positive rate with respect to a particular class. This is defined as

         correctly classified positives
         ------------------------------
               total positives
         
        Parameters:
        classIndex - the index of the class to consider as "positive"
        Returns:
        the true positive rate
      • weightedTruePositiveRate

        public double weightedTruePositiveRate()
        Calculates the weighted (by class size) true positive rate.
        Returns:
        the weighted true positive rate.
      • numTrueNegatives

        public double numTrueNegatives​(int classIndex)
        Calculate the number of true negatives with respect to a particular class. This is defined as

         correctly classified negatives
         
        Parameters:
        classIndex - the index of the class to consider as "positive"
        Returns:
        the true positive rate
      • trueNegativeRate

        public double trueNegativeRate​(int classIndex)
        Calculate the true negative rate with respect to a particular class. This is defined as

         correctly classified negatives
         ------------------------------
               total negatives
         
        Parameters:
        classIndex - the index of the class to consider as "positive"
        Returns:
        the true positive rate
      • weightedTrueNegativeRate

        public double weightedTrueNegativeRate()
        Calculates the weighted (by class size) true negative rate.
        Returns:
        the weighted true negative rate.
      • numFalsePositives

        public double numFalsePositives​(int classIndex)
        Calculate number of false positives with respect to a particular class. This is defined as

         incorrectly classified negatives
         
        Parameters:
        classIndex - the index of the class to consider as "positive"
        Returns:
        the false positive rate
      • falsePositiveRate

        public double falsePositiveRate​(int classIndex)
        Calculate the false positive rate with respect to a particular class. This is defined as

         incorrectly classified negatives
         --------------------------------
                total negatives
         
        Parameters:
        classIndex - the index of the class to consider as "positive"
        Returns:
        the false positive rate
      • weightedFalsePositiveRate

        public double weightedFalsePositiveRate()
        Calculates the weighted (by class size) false positive rate.
        Returns:
        the weighted false positive rate.
      • numFalseNegatives

        public double numFalseNegatives​(int classIndex)
        Calculate number of false negatives with respect to a particular class. This is defined as

         incorrectly classified positives
         
        Parameters:
        classIndex - the index of the class to consider as "positive"
        Returns:
        the false positive rate
      • falseNegativeRate

        public double falseNegativeRate​(int classIndex)
        Calculate the false negative rate with respect to a particular class. This is defined as

         incorrectly classified positives
         --------------------------------
                total positives
         
        Parameters:
        classIndex - the index of the class to consider as "positive"
        Returns:
        the false positive rate
      • weightedFalseNegativeRate

        public double weightedFalseNegativeRate()
        Calculates the weighted (by class size) false negative rate.
        Returns:
        the weighted false negative rate.
      • recall

        public double recall​(int classIndex)
        Calculate the recall with respect to a particular class. This is defined as

         correctly classified positives
         ------------------------------
               total positives
         

        (Which is also the same as the truePositiveRate.)

        Parameters:
        classIndex - the index of the class to consider as "positive"
        Returns:
        the recall
      • weightedRecall

        public double weightedRecall()
        Calculates the weighted (by class size) recall.
        Returns:
        the weighted recall.
      • precision

        public double precision​(int classIndex)
        Calculate the precision with respect to a particular class. This is defined as

         correctly classified positives
         ------------------------------
          total predicted as positive
         
        Parameters:
        classIndex - the index of the class to consider as "positive"
        Returns:
        the precision
      • weightedPrecision

        public double weightedPrecision()
        Calculates the weighted (by class size) false precision.
        Returns:
        the weighted precision.
      • fMeasure

        public double fMeasure​(int classIndex)
        Calculate the F-Measure with respect to a particular class. This is defined as

         2 * recall * precision
         ----------------------
           recall + precision
         
        Parameters:
        classIndex - the index of the class to consider as "positive"
        Returns:
        the F-Measure
      • weightedFMeasure

        public double weightedFMeasure()
        Calculates the weighted (by class size) F-Measure.
        Returns:
        the weighted F-Measure.
      • setPriors

        public void setPriors​(Instances train)
                       throws java.lang.Exception
        Sets the class prior probabilities
        Parameters:
        train - the training instances used to determine the prior probabilities
        Throws:
        java.lang.Exception - if the class attribute of the instances is not set
      • getClassPriors

        public double[] getClassPriors()
        Get the current weighted class counts
        Returns:
        the weighted class counts
      • updatePriors

        public void updatePriors​(Instance instance)
                          throws java.lang.Exception
        Updates the class prior probabilities (when incrementally training)
        Parameters:
        instance - the new training instance seen
        Throws:
        java.lang.Exception - if the class of the instance is not set
      • useNoPriors

        public void useNoPriors()
        disables the use of priors, e.g., in case of de-serialized schemes that have no access to the original training set, but are evaluated on a set set.
      • equals

        public boolean equals​(java.lang.Object obj)
        Tests whether the current evaluation object is equal to another evaluation object
        Overrides:
        equals in class java.lang.Object
        Parameters:
        obj - the object to compare against
        Returns:
        true if the two objects are equal
      • printClassifications

        public static void printClassifications​(Classifier classifier,
                                                Instances train,
                                                ConverterUtils.DataSource testSource,
                                                int classIndex,
                                                Range attributesToOutput,
                                                java.lang.StringBuffer predsText)
                                         throws java.lang.Exception
        Prints the predictions for the given dataset into a String variable.
        Parameters:
        classifier - the classifier to use
        train - the training data
        testSource - the test set
        classIndex - the class index (1-based), if -1 ot does not override the class index is stored in the data file (by using the last attribute)
        attributesToOutput - the indices of the attributes to output
        Throws:
        java.lang.Exception - if test file cannot be opened
      • printClassifications

        public static void printClassifications​(Classifier classifier,
                                                Instances train,
                                                ConverterUtils.DataSource testSource,
                                                int classIndex,
                                                Range attributesToOutput,
                                                boolean printDistribution,
                                                java.lang.StringBuffer text)
                                         throws java.lang.Exception
        Prints the predictions for the given dataset into a supplied StringBuffer
        Parameters:
        classifier - the classifier to use
        train - the training data
        testSource - the test set
        classIndex - the class index (1-based), if -1 ot does not override the class index is stored in the data file (by using the last attribute)
        attributesToOutput - the indices of the attributes to output
        printDistribution - prints the complete distribution for nominal classes, not just the predicted value
        text - StringBuffer to hold the printed predictions
        Throws:
        java.lang.Exception - if test file cannot be opened
      • getRevision

        public java.lang.String getRevision()
        Returns the revision string.
        Specified by:
        getRevision in interface RevisionHandler
        Returns:
        the revision