Package weka.classifiers.meta

Class IterativeClassifierOptimizer

  • All Implemented Interfaces:
    java.io.Serializable, java.lang.Cloneable, Classifier, AdditionalMeasureProducer, BatchPredictor, CapabilitiesHandler, CapabilitiesIgnorer, CommandlineRunnable, OptionHandler, Randomizable, RevisionHandler
    public class IterativeClassifierOptimizer
extends RandomizableClassifier
implements AdditionalMeasureProducer
    Chooses the best number of iterations for an IterativeClassifier such as LogitBoost using cross-validation or a percentage split evaluation. Optimizes the number of iterations of the given iterative classifier using cross-validation or a percentage split evaluation.

    Valid options are: 

     -A
  If set, average estimate is used rather than one estimate from pooled predictions.
 
     -L <num>
  The number of iterations to look ahead for to find a better optimum.
  (default 50)
     -P <int>
  The size of the thread pool, for example, the number of cores in the CPU.
  (default 1)
     -E <int>
  The number of threads to use, which should be >= size of thread pool.
  (default 1)
     -I <num>
  Step size for the evaluation, if evaluation is time consuming.
  (default 1)
     -F <num>
  Number of folds for cross-validation.
  (default 10)
     -R <num>
  Number of runs for cross-validation.
  (default 1)
     -W
  Full name of base classifier.
  (default: weka.classifiers.meta.LogitBoost)
     -metric <name>
  Evaluation metric to optimise (default rmse). Available metrics:
  correct,incorrect,kappa,total cost,average cost,kb relative,kb information,
  correlation,complexity 0,complexity scheme,complexity improvement,
  mae,rmse,rae,rrse,coverage,region size,tp rate,fp rate,precision,recall,
  f-measure,mcc,roc area,prc area
     -class-value-index <0-based index>
  Class value index to optimise. Ignored for all but information-retrieval
  type metrics (such as roc area). If unspecified (or a negative value is supplied),
  and an information-retrieval metric is specified, then the class-weighted average
  metric used. (default -1)
     -S <num>
  Random number seed.
  (default 1)
     -output-debug-info
  If set, classifier is run in debug mode and
  may output additional info to the console
     -do-not-check-capabilities
  If set, classifier capabilities are not checked before classifier is built
  (use with caution).
     
 Options specific to classifier weka.classifiers.meta.LogitBoost:
 
     -Q
  Use resampling instead of reweighting for boosting.
     -P <percent>
  Percentage of weight mass to base training on.
  (default 100, reduce to around 90 speed up)
     -L <num>
  Threshold on the improvement of the likelihood.
  (default -Double.MAX_VALUE)
     -H <num>
  Shrinkage parameter.
  (default 1)
     -Z <num>
  Z max threshold for responses.
  (default 3)
     -O <int>
  The size of the thread pool, for example, the number of cores in the CPU. (default 1)
     -E <int>
  The number of threads to use for batch prediction, which should be >= size of thread pool.
  (default 1)
     -S <num>
  Random number seed.
  (default 1)
     -I <num>
  Number of iterations.
  (default 10)
     -percentage <num>
  The percentage of data to be used for training (if 0, k-fold cross-validation is used).
  (default 0)
     -order
  Whether to preserve order when a percentage split evaluation is performed.
  
     -W
  Full name of base classifier.
  (default: weka.classifiers.trees.DecisionStump)
     -output-debug-info
  If set, classifier is run in debug mode and
  may output additional info to the console
     -do-not-check-capabilities
  If set, classifier capabilities are not checked before classifier is built
  (use with caution).
     
 Options specific to classifier weka.classifiers.trees.DecisionStump:
 
     -output-debug-info
  If set, classifier is run in debug mode and
  may output additional info to the console
     -do-not-check-capabilities
  If set, classifier capabilities are not checked before classifier is built
  (use with caution).
    Version:
    $Revision: 10141 $
    Author:
    Eibe Frank (eibe@cs.waikato.ac.nz)
    See Also:
    Serialized Form

    • Field Detail

      • TAGS_EVAL

        public static Tag[] TAGS_EVAL

    • Constructor Detail

      • IterativeClassifierOptimizer

        public IterativeClassifierOptimizer()

    • Method Detail

      • globalInfo

        public java.lang.String globalInfo()
        Returns a string describing classifier
        Returns:
        a description suitable for displaying in the explorer/experimenter gui

      • useAverageTipText

        public java.lang.String useAverageTipText()
        Returns the tip text for this property
        Returns:
        tip text for this property suitable for displaying in the explorer/experimenter gui

      • getUseAverage

        public boolean getUseAverage()
        Get the value of UseAverage.
        Returns:
        Value of UseAverage.

      • setUseAverage

        public void setUseAverage​(boolean newUseAverage)
        Set the value of UseAverage.
        Parameters:
        newUseAverage - Value to assign to UseAverage.

      • numThreadsTipText

        public java.lang.String numThreadsTipText()
        Returns:
        a string to describe the option

      • getNumThreads

        public int getNumThreads()
        Gets the number of threads.

      • setNumThreads

        public void setNumThreads​(int nT)
        Sets the number of threads

      • poolSizeTipText

        public java.lang.String poolSizeTipText()
        Returns:
        a string to describe the option

      • getPoolSize

        public int getPoolSize()
        Gets the number of threads.

      • setPoolSize

        public void setPoolSize​(int nT)
        Sets the number of threads

      • stepSizeTipText

        public java.lang.String stepSizeTipText()
        Returns the tip text for this property
        Returns:
        tip text for this property suitable for displaying in the explorer/experimenter gui

      • getStepSize

        public int getStepSize()
        Get the value of StepSize.
        Returns:
        Value of StepSize.

      • setStepSize

        public void setStepSize​(int newStepSize)
        Set the value of StepSize.
        Parameters:
        newStepSize - Value to assign to StepSize.

      • numRunsTipText

        public java.lang.String numRunsTipText()
        Returns the tip text for this property
        Returns:
        tip text for this property suitable for displaying in the explorer/experimenter gui

      • getNumRuns

        public int getNumRuns()
        Get the value of NumRuns.
        Returns:
        Value of NumRuns.

      • setNumRuns

        public void setNumRuns​(int newNumRuns)
        Set the value of NumRuns.
        Parameters:
        newNumRuns - Value to assign to NumRuns.

      • numFoldsTipText

        public java.lang.String numFoldsTipText()
        Returns the tip text for this property
        Returns:
        tip text for this property suitable for displaying in the explorer/experimenter gui

      • getNumFolds

        public int getNumFolds()
        Get the value of NumFolds.
        Returns:
        Value of NumFolds.

      • setNumFolds

        public void setNumFolds​(int newNumFolds)
        Set the value of NumFolds.
        Parameters:
        newNumFolds - Value to assign to NumFolds.

      • lookAheadIterationsTipText

        public java.lang.String lookAheadIterationsTipText()
        Returns the tip text for this property
        Returns:
        tip text for this property suitable for displaying in the explorer/experimenter gui

      • getLookAheadIterations

        public int getLookAheadIterations()
        Get the value of LookAheadIterations.
        Returns:
        Value of LookAheadIterations.

      • setLookAheadIterations

        public void setLookAheadIterations​(int newLookAheadIterations)
        Set the value of LookAheadIterations.
        Parameters:
        newLookAheadIterations - Value to assign to LookAheadIterations.

      • splitPercentageTipText

        public java.lang.String splitPercentageTipText()
        Returns the tip text for this property
        Returns:
        tip text for this property suitable for displaying in the explorer/experimenter gui

      • getSplitPercentage

        public double getSplitPercentage()
        Get the value of SplitPercentage.
        Returns:
        Value of SplitPercentage.

      • setSplitPercentage

        public void setSplitPercentage​(double newSplitPercentage)
        Set the value of SplitPercentage.
        Parameters:
        newSplitPercentage - Value to assign to SplitPercentage.

      • preserveOrderInPercentageSplitEvaluationTipText

        public java.lang.String preserveOrderInPercentageSplitEvaluationTipText()
        Returns the tip text for this property
        Returns:
        tip text for this property suitable for displaying in the explorer/experimenter gui

      • getPreserveOrderInPercentageSplitEvaluation

        public boolean getPreserveOrderInPercentageSplitEvaluation()
        Get the value of PreserveOrderInPercentageSplitEvaluation.
        Returns:
        Value of PreserveOrderInPercentageSplitEvaluation.

      • setPreserveOrderInPercentageSplitEvaluation

        public void setPreserveOrderInPercentageSplitEvaluation​(boolean newPreserveOrderInPercentageSplitEvaluation)
        Set the value of PreserveOrderInPercentageSplitEvaluation.
        Parameters:
        newPreserveOrderInPercentageSplitEvaluation - Value to assign to PreserveOrderInPercentageSplitEvaluation.

      • buildClassifier

        public void buildClassifier​(Instances data)
                     throws java.lang.Exception
        Builds the classifier.
        Specified by:
        buildClassifier in interface Classifier
        Parameters:
        data - set of instances serving as training data
        Throws:
        java.lang.Exception - if the classifier has not been generated successfully

      • distributionForInstance

        public double[] distributionForInstance​(Instance inst)
                                 throws java.lang.Exception
        Returns the class distribution for an instance.
        Specified by:
        distributionForInstance in interface Classifier
        Overrides:
        distributionForInstance in class AbstractClassifier
        Parameters:
        inst - the instance to be classified
        Returns:
        an array containing the estimated membership probabilities of the test instance in each class or the numeric prediction
        Throws:
        java.lang.Exception - if distribution could not be computed successfully

      • toString

        public java.lang.String toString()
        Returns a string describing the classifier.
        Overrides:
        toString in class java.lang.Object

      • setOptions

        public void setOptions​(java.lang.String[] options)
                throws java.lang.Exception
        Parses a given list of options. Options after -- are passed to the designated classifier.
        Specified by:
        setOptions in interface OptionHandler
        Overrides:
        setOptions in class RandomizableClassifier
        Parameters:
        options - the list of options as an array of strings
        Throws:
        java.lang.Exception - if an option is not supported

      • evaluationMetricTipText

        public java.lang.String evaluationMetricTipText()
        Returns the tip text for this property
        Returns:
        tip text for this property suitable for displaying in the explorer/experimenter gui

      • setEvaluationMetric

        public void setEvaluationMetric​(SelectedTag metric)
        Set the evaluation metric to use
        Parameters:
        metric - the metric to use

      • getEvaluationMetric

        public SelectedTag getEvaluationMetric()
        Get the evaluation metric to use
        Returns:
        the evaluation metric to use

      • classValueIndexTipText

        public java.lang.String classValueIndexTipText()
        Returns the tip text for this property
        Returns:
        tip text for this property suitable for displaying in the explorer/experimenter gui

      • setClassValueIndex

        public void setClassValueIndex​(int i)
        Set the class value index to use
        Parameters:
        i - the class value index to use

      • getClassValueIndex

        public int getClassValueIndex()
        Get the class value index to use
        Returns:
        the class value index to use

      • iterativeClassifierTipText

        public java.lang.String iterativeClassifierTipText()
        Returns the tip text for this property
        Returns:
        tip text for this property suitable for displaying in the explorer/experimenter gui

      • setIterativeClassifier

        public void setIterativeClassifier​(IterativeClassifier newIterativeClassifier)
        Set the base learner.
        Parameters:
        newIterativeClassifier - the classifier to use.

      • getIterativeClassifier

        public IterativeClassifier getIterativeClassifier()
        Get the classifier used as the base learner.
        Returns:
        the classifier used as the classifier

      • measureBestNumIts

        public double measureBestNumIts()
        Returns the best number of iterations
        Returns:
        the best number of iterations

      • measureBestVal

        public double measureBestVal()
        Returns the measure for the best model
        Returns:
        the number of leaves

      • enumerateMeasures

        public java.util.Enumeration<java.lang.String> enumerateMeasures()
        Returns an enumeration of the additional measure names
        Specified by:
        enumerateMeasures in interface AdditionalMeasureProducer
        Returns:
        an enumeration of the measure names

      • getMeasure

        public double getMeasure​(java.lang.String additionalMeasureName)
        Returns the value of the named measure
        Specified by:
        getMeasure in interface AdditionalMeasureProducer
        Parameters:
        additionalMeasureName - the name of the measure to query for its value
        Returns:
        the value of the named measure
        Throws:
        java.lang.IllegalArgumentException - if the named measure is not supported

      • main

        public static void main​(java.lang.String[] argv)
        Main method for testing this class.
        Parameters:
        argv - the options