Class Resample

  • All Implemented Interfaces:
    java.io.Serializable, CapabilitiesHandler, OptionHandler, RevisionHandler, SupervisedFilter

    public class Resample
    extends Filter
    implements SupervisedFilter, OptionHandler
    Produces a random subsample of a dataset using either sampling with replacement or without replacement.
    The original dataset must fit entirely in memory. The number of instances in the generated dataset may be specified. The dataset must have a nominal class attribute. If not, use the unsupervised version. The filter can be made to maintain the class distribution in the subsample, or to bias the class distribution toward a uniform distribution. When used in batch mode (i.e. in the FilteredClassifier), subsequent batches are NOT resampled.

    Valid options are:

     -S <num>
      Specify the random number seed (default 1)
     -Z <num>
      The size of the output dataset, as a percentage of
      the input dataset (default 100)
     -B <num>
      Bias factor towards uniform class distribution.
      0 = distribution in input data -- 1 = uniform distribution.
      (default 0)
     -no-replacement
      Disables replacement of instances
      (default: with replacement)
     -V
      Inverts the selection - only available with '-no-replacement'.
    Version:
    $Revision: 5542 $
    Author:
    Len Trigg (len@reeltwo.com), FracPete (fracpete at waikato dot ac dot nz)
    See Also:
    Serialized Form
    • Constructor Detail

      • Resample

        public Resample()
    • Method Detail

      • globalInfo

        public java.lang.String globalInfo()
        Returns a string describing this filter.
        Returns:
        a description of the filter suitable for displaying in the explorer/experimenter gui
      • listOptions

        public java.util.Enumeration listOptions()
        Returns an enumeration describing the available options.
        Specified by:
        listOptions in interface OptionHandler
        Returns:
        an enumeration of all the available options.
      • setOptions

        public void setOptions​(java.lang.String[] options)
                        throws java.lang.Exception
        Parses a given list of options.

        Valid options are:

         -S <num>
          Specify the random number seed (default 1)
         -Z <num>
          The size of the output dataset, as a percentage of
          the input dataset (default 100)
         -B <num>
          Bias factor towards uniform class distribution.
          0 = distribution in input data -- 1 = uniform distribution.
          (default 0)
         -no-replacement
          Disables replacement of instances
          (default: with replacement)
         -V
          Inverts the selection - only available with '-no-replacement'.
        Specified by:
        setOptions in interface OptionHandler
        Parameters:
        options - the list of options as an array of strings
        Throws:
        java.lang.Exception - if an option is not supported
      • getOptions

        public java.lang.String[] getOptions()
        Gets the current settings of the filter.
        Specified by:
        getOptions in interface OptionHandler
        Returns:
        an array of strings suitable for passing to setOptions
      • biasToUniformClassTipText

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

        public double getBiasToUniformClass()
        Gets the bias towards a uniform class. A value of 0 leaves the class distribution as-is, a value of 1 ensures the class distributions are uniform in the output data.
        Returns:
        the current bias
      • setBiasToUniformClass

        public void setBiasToUniformClass​(double newBiasToUniformClass)
        Sets the bias towards a uniform class. A value of 0 leaves the class distribution as-is, a value of 1 ensures the class distributions are uniform in the output data.
        Parameters:
        newBiasToUniformClass - the new bias value, between 0 and 1.
      • randomSeedTipText

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

        public int getRandomSeed()
        Gets the random number seed.
        Returns:
        the random number seed.
      • setRandomSeed

        public void setRandomSeed​(int newSeed)
        Sets the random number seed.
        Parameters:
        newSeed - the new random number seed.
      • sampleSizePercentTipText

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

        public double getSampleSizePercent()
        Gets the subsample size as a percentage of the original set.
        Returns:
        the subsample size
      • setSampleSizePercent

        public void setSampleSizePercent​(double newSampleSizePercent)
        Sets the size of the subsample, as a percentage of the original set.
        Parameters:
        newSampleSizePercent - the subsample set size, between 0 and 100.
      • noReplacementTipText

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

        public boolean getNoReplacement()
        Gets whether instances are drawn with or without replacement.
        Returns:
        true if the replacement is disabled
      • setNoReplacement

        public void setNoReplacement​(boolean value)
        Sets whether instances are drawn with or with out replacement.
        Parameters:
        value - if true then the replacement of instances is disabled
      • invertSelectionTipText

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

        public boolean getInvertSelection()
        Gets whether selection is inverted (only if instances are drawn WIHTOUT replacement).
        Returns:
        true if the replacement is disabled
        See Also:
        m_NoReplacement
      • setInvertSelection

        public void setInvertSelection​(boolean value)
        Sets whether the selection is inverted (only if instances are drawn WIHTOUT replacement).
        Parameters:
        value - if true then selection is inverted
      • setInputFormat

        public boolean setInputFormat​(Instances instanceInfo)
                               throws java.lang.Exception
        Sets the format of the input instances.
        Overrides:
        setInputFormat in class Filter
        Parameters:
        instanceInfo - an Instances object containing the input instance structure (any instances contained in the object are ignored - only the structure is required).
        Returns:
        true if the outputFormat may be collected immediately
        Throws:
        java.lang.Exception - if the input format can't be set successfully
      • input

        public boolean input​(Instance instance)
        Input an instance for filtering. Filter requires all training instances be read before producing output.
        Overrides:
        input in class Filter
        Parameters:
        instance - the input instance
        Returns:
        true if the filtered instance may now be collected with output().
        Throws:
        java.lang.IllegalStateException - if no input structure has been defined
      • batchFinished

        public boolean batchFinished()
        Signify that this batch of input to the filter is finished. If the filter requires all instances prior to filtering, output() may now be called to retrieve the filtered instances.
        Overrides:
        batchFinished in class Filter
        Returns:
        true if there are instances pending output
        Throws:
        java.lang.IllegalStateException - if no input structure has been defined
      • createSubsampleWithReplacement

        public void createSubsampleWithReplacement​(java.util.Random random,
                                                   int origSize,
                                                   int sampleSize,
                                                   int actualClasses,
                                                   int[] classIndices)
        creates the subsample with replacement.
        Parameters:
        random - the random number generator to use
        origSize - the original size of the dataset
        sampleSize - the size to generate
        actualClasses - the number of classes found in the data
        classIndices - the indices where classes start
      • createSubsampleWithoutReplacement

        public void createSubsampleWithoutReplacement​(java.util.Random random,
                                                      int origSize,
                                                      int sampleSize,
                                                      int actualClasses,
                                                      int[] classIndices)
        creates the subsample without replacement.
        Parameters:
        random - the random number generator to use
        origSize - the original size of the dataset
        sampleSize - the size to generate
        actualClasses - the number of classes found in the data
        classIndices - the indices where classes start
      • main

        public static void main​(java.lang.String[] argv)
        Main method for testing this class.
        Parameters:
        argv - should contain arguments to the filter: use -h for help