Package weka.classifiers.meta

Class AbstainLeastMedianSq

  • All Implemented Interfaces:
    Serializable, Cloneable, AbstainingClassifier, weka.classifiers.Classifier, weka.core.BatchPredictor, weka.core.CapabilitiesHandler, weka.core.CapabilitiesIgnorer, weka.core.CommandlineRunnable, weka.core.OptionHandler, weka.core.RevisionHandler, weka.core.WeightedInstancesHandler
    public class AbstainLeastMedianSq
extends weka.classifiers.SingleClassifierEnhancer
implements weka.core.WeightedInstancesHandler, AbstainingClassifier
    Finds the base classifier with the best least median squared error.

    Valid options are: 

     -D
  If set, classifier is run in debug mode and
  may output additional info to the console
     -W
  Full name of base classifier.
  (default: weka.classifiers.rules.ZeroR)
     Options specific to classifier weka.classifiers.rules.ZeroR:
 
     -D
  If set, classifier is run in debug mode and
  may output additional info to the console
     -S <sint>
  Number of regressions
  (default: 10)
 
     -P <int>
  Percent sample size
  (default: 60)
 
     -E <int>
  Percent Error at
  (default: 50)
 
     -G <seed>
  Set the seed used to generate samples
  (default: 0)
    Version:
    $Revision$
    Author:
    Dale
    See Also:
    Serialized Form

    • Field Summary

      Fields 
      Modifier and Type Field Description
      protected weka.classifiers.Classifier m_bestClassifier  
      protected double m_bestMedian  
      protected weka.classifiers.Classifier[] m_cs  
      protected weka.classifiers.Classifier m_currentClassifier  
      protected weka.core.Instances m_Data  
      protected boolean m_debug  
      protected int m_errPct  
      protected int m_instancepct  
      protected double m_max  
      protected double m_min  
      protected int m_numreg  
      protected boolean m_ok  
      protected Random m_random  
      protected long m_randomseed  
      protected double[] m_Residuals  
      protected double m_Ridge  
      protected double m_scalefactor  
      protected double m_SSR  
      protected weka.core.Instances m_SubSample  
      protected double m_variance  
      protected double[] m_weight  

      • Fields inherited from class weka.classifiers.SingleClassifierEnhancer

        m_Classifier

      • Fields inherited from class weka.classifiers.AbstractClassifier

        BATCH_SIZE_DEFAULT, m_BatchSize, m_Debug, m_DoNotCheckCapabilities, m_numDecimalPlaces, NUM_DECIMAL_PLACES_DEFAULT

    • Method Summary

      All Methods Static Methods Instance Methods Concrete Methods 
      Modifier and Type Method Description
      void buildClassifier​(weka.core.Instances data)
      Builds the classifier.
      boolean canAbstain()
      Whether abstaining is possible, e.g., used in meta-classifiers.
      double classifyInstance​(weka.core.Instance inst)
      Returns the prediction.
      String errorTipText()  
      protected void findBestRegression()
      Finds the best regression generated from m_samples random samples from the training data.
      protected void findResiduals()
      Finds residuals (squared) for the current regression.
      protected void genRegression​(Random r)
      Generates a LinearRegression classifier from the current m_SubSample.
      double getAbstentionClassification​(weka.core.Instance inst)
      The prediction that made the classifier abstain.
      double[] getAbstentionDistribution​(weka.core.Instance inst)
      The class distribution that made the classifier abstain.
      weka.core.Capabilities getCapabilities()
      Returns default capabilities of the base classifier.
      boolean getDebug()
      Returns whether or not debugging output shouild be printed
      int getError()  
      protected void getErrorAtPct​(int pct)
      finds the median residual squared for the current regression.
      int getNumRegressions()
      gets number of samples
      String[] getOptions()
      Gets the current option settings for the OptionHandler.
      int getPct()  
      long getRandomSeed()
      get the seed for the random number generator
      String getRevision()
      Returns the revision string.
      double getVariance()  
      String globalInfo()
      Returns a string describing classifier.
      Enumeration listOptions()
      Returns an enumeration describing the available options.
      static void main​(String[] argv)
      Main method for running this class.
      String numRegressionsTipText()
      Returns the tip text for this property
      String pctTipText()  
      String randomSeedTipText()
      Returns the tip text for this property
      protected void selectSubSample​(weka.core.Instances data, Random r)
      Produces a random sample from m_Data in m_SubSample.
      void setDebug​(boolean debug)
      sets whether or not debugging output shouild be printed
      void setError​(int pct)  
      void setNumRegressions​(int samplesize)
      sets number of samples
      void setOptions​(String[] options)
      Sets the OptionHandler's options using the given list.
      void setPct​(int pct)  
      void setRandomSeed​(long randomseed)
      Set the seed for the random number generator
      void setVariance​(double var)  
      String toString()
      Returns description of classifier.
      String varianceTipText()  

      • Methods inherited from class weka.classifiers.SingleClassifierEnhancer

        classifierTipText, defaultClassifierOptions, defaultClassifierString, getClassifier, getClassifierSpec, postExecution, preExecution, setClassifier

      • Methods inherited from class weka.classifiers.AbstractClassifier

        batchSizeTipText, debugTipText, distributionForInstance, distributionsForInstances, doNotCheckCapabilitiesTipText, forName, getBatchSize, getDoNotCheckCapabilities, getNumDecimalPlaces, implementsMoreEfficientBatchPrediction, makeCopies, makeCopy, numDecimalPlacesTipText, run, runClassifier, setBatchSize, setDoNotCheckCapabilities, setNumDecimalPlaces

      • Methods inherited from interface weka.classifiers.Classifier

        distributionForInstance

    • Field Detail

      • m_Residuals

        protected double[] m_Residuals

      • m_weight

        protected double[] m_weight

      • m_SSR

        protected double m_SSR

      • m_scalefactor

        protected double m_scalefactor

      • m_bestMedian

        protected double m_bestMedian

      • m_Ridge

        protected double m_Ridge

      • m_currentClassifier

        protected weka.classifiers.Classifier m_currentClassifier

      • m_bestClassifier

        protected weka.classifiers.Classifier m_bestClassifier

      • m_Data

        protected weka.core.Instances m_Data

      • m_SubSample

        protected weka.core.Instances m_SubSample

      • m_numreg

        protected int m_numreg

      • m_instancepct

        protected int m_instancepct

      • m_errPct

        protected int m_errPct

      • m_debug

        protected boolean m_debug

      • m_random

        protected Random m_random

      • m_randomseed

        protected long m_randomseed

      • m_variance

        protected double m_variance

      • m_ok

        protected boolean m_ok

      • m_min

        protected double m_min

      • m_max

        protected double m_max

      • m_cs

        protected weka.classifiers.Classifier[] m_cs

    • Constructor Detail

      • AbstainLeastMedianSq

        public AbstainLeastMedianSq()

    • Method Detail

      • globalInfo

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

      • listOptions

        public Enumeration listOptions()
        Returns an enumeration describing the available options.
        Specified by:
        listOptions in interface weka.core.OptionHandler
        Overrides:
        listOptions in class weka.classifiers.SingleClassifierEnhancer
        Returns:
        an enumeration of all the available options.

      • setOptions

        public void setOptions​(String[] options)
                throws Exception
        Sets the OptionHandler's options using the given list. All options will be set (or reset) during this call (i.e. incremental setting of options is not possible). Valid options are: 

         -D
  If set, classifier is run in debug mode and
  may output additional info to the console
         -W
  Full name of base classifier.
  (default: weka.classifiers.rules.ZeroR)
         Options specific to classifier weka.classifiers.rules.ZeroR:
 
         -D
  If set, classifier is run in debug mode and
  may output additional info to the console
         -S <sint>
  Number of regressions
  (default: 10)
 
         -P <int>
  Percent sample size
  (default: 60)
 
         -E <int>
  Percent Error at
  (default: 50)
 
         -G <seed>
  Set the seed used to generate samples
  (default: 0)
        Specified by:
        setOptions in interface weka.core.OptionHandler
        Overrides:
        setOptions in class weka.classifiers.SingleClassifierEnhancer
        Parameters:
        options - the list of options as an array of strings
        Throws:
        Exception - if an option is not supported

      • getOptions

        public String[] getOptions()
        Gets the current option settings for the OptionHandler.
        Specified by:
        getOptions in interface weka.core.OptionHandler
        Overrides:
        getOptions in class weka.classifiers.SingleClassifierEnhancer
        Returns:
        the list of current option settings as an array of strings

      • findResiduals

        protected void findResiduals()
                      throws Exception
        Finds residuals (squared) for the current regression.
        Throws:
        Exception - if an error occurs

      • getErrorAtPct

        protected void getErrorAtPct​(int pct)
                      throws Exception
        finds the median residual squared for the current regression.
        Throws:
        Exception - if an error occurs

      • findBestRegression

        protected void findBestRegression()
                           throws Exception
        Finds the best regression generated from m_samples random samples from the training data.
        Throws:
        Exception - if an error occurs

      • selectSubSample

        protected void selectSubSample​(weka.core.Instances data,
                               Random r)
                        throws Exception
        Produces a random sample from m_Data in m_SubSample.
        Parameters:
        data - data from which to take sample
        Throws:
        Exception - if an error occurs

      • genRegression

        protected void genRegression​(Random r)
                      throws Exception
        Generates a LinearRegression classifier from the current m_SubSample.
        Throws:
        Exception - if an error occurs

      • getCapabilities

        public weka.core.Capabilities getCapabilities()
        Returns default capabilities of the base classifier.
        Specified by:
        getCapabilities in interface weka.core.CapabilitiesHandler
        Specified by:
        getCapabilities in interface weka.classifiers.Classifier
        Overrides:
        getCapabilities in class weka.classifiers.SingleClassifierEnhancer
        Returns:
        the capabilities of the base classifier

      • buildClassifier

        public void buildClassifier​(weka.core.Instances data)
                     throws Exception
        Builds the classifier.
        Specified by:
        buildClassifier in interface weka.classifiers.Classifier
        Parameters:
        data - the training data
        Throws:
        Exception - if something goes wrong

      • classifyInstance

        public double classifyInstance​(weka.core.Instance inst)
                        throws Exception
        Returns the prediction.
        Specified by:
        classifyInstance in interface weka.classifiers.Classifier
        Overrides:
        classifyInstance in class weka.classifiers.AbstractClassifier
        Throws:
        Exception

      • canAbstain

        public boolean canAbstain()
        Whether abstaining is possible, e.g., used in meta-classifiers.
        Specified by:
        canAbstain in interface AbstainingClassifier
        Returns:
        true if abstaining is possible

      • getAbstentionClassification

        public double getAbstentionClassification​(weka.core.Instance inst)
                                   throws Exception
        The prediction that made the classifier abstain.
        Specified by:
        getAbstentionClassification in interface AbstainingClassifier
        Parameters:
        inst - the instance to get the prediction for
        Returns:
        the prediction
        Throws:
        Exception - if fails to make prediction

      • getAbstentionDistribution

        public double[] getAbstentionDistribution​(weka.core.Instance inst)
                                   throws Exception
        The class distribution that made the classifier abstain.
        Specified by:
        getAbstentionDistribution in interface AbstainingClassifier
        Parameters:
        inst - the instance to get the prediction for
        Returns:
        the class distribution
        Throws:
        Exception - if fails to make prediction

      • toString

        public String toString()
        Returns description of classifier.
        Overrides:
        toString in class Object

      • getRevision

        public String getRevision()
        Returns the revision string.
        Specified by:
        getRevision in interface weka.core.RevisionHandler
        Overrides:
        getRevision in class weka.classifiers.AbstractClassifier
        Returns:
        the revision

      • numRegressionsTipText

        public String numRegressionsTipText()
        Returns the tip text for this property
        Returns:
        tip text for this property suitable for displaying in the explorer/experimenter gui

      • setVariance

        public void setVariance​(double var)

      • getVariance

        public double getVariance()

      • varianceTipText

        public String varianceTipText()

      • setPct

        public void setPct​(int pct)

      • getPct

        public int getPct()

      • pctTipText

        public String pctTipText()

      • setError

        public void setError​(int pct)

      • getError

        public int getError()

      • errorTipText

        public String errorTipText()

      • setNumRegressions

        public void setNumRegressions​(int samplesize)
        sets number of samples
        Parameters:
        samplesize - value

      • getNumRegressions

        public int getNumRegressions()
        gets number of samples
        Returns:
        value

      • randomSeedTipText

        public String randomSeedTipText()
        Returns the tip text for this property
        Returns:
        tip text for this property suitable for displaying in the explorer/experimenter gui

      • setRandomSeed

        public void setRandomSeed​(long randomseed)
        Set the seed for the random number generator
        Parameters:
        randomseed - the seed

      • getRandomSeed

        public long getRandomSeed()
        get the seed for the random number generator
        Returns:
        the seed value

      • setDebug

        public void setDebug​(boolean debug)
        sets whether or not debugging output shouild be printed
        Overrides:
        setDebug in class weka.classifiers.AbstractClassifier
        Parameters:
        debug - true if debugging output selected

      • getDebug

        public boolean getDebug()
        Returns whether or not debugging output shouild be printed
        Overrides:
        getDebug in class weka.classifiers.AbstractClassifier
        Returns:
        true if debuging output selected

      • main

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