Package weka.filters.unsupervised.attribute

Class KernelFilter

  • All Implemented Interfaces:
    java.io.Serializable, CapabilitiesHandler, OptionHandler, RevisionHandler, TechnicalInformationHandler, UnsupervisedFilter
    public class KernelFilter
extends SimpleBatchFilter
implements UnsupervisedFilter, TechnicalInformationHandler
    Converts the given set of predictor variables into a kernel matrix. The class value remains unchangedm, as long as the preprocessing filter doesn't change it.
    By default, the data is preprocessed with the Center filter, but the user can choose any filter (NB: one must be careful that the filter does not alter the class attribute unintentionally). With weka.filters.AllFilter the preprocessing gets disabled.

    For more information regarding preprocessing the data, see:

    K.P. Bennett, M.J. Embrechts: An Optimization Perspective on Kernel Partial Least Squares Regression. In: Advances in Learning Theory: Methods, Models and Applications, 227-249, 2003.

    BibTeX: 

     @inproceedings{Bennett2003,
    author = {K.P. Bennett and M.J. Embrechts},
    booktitle = {Advances in Learning Theory: Methods, Models and Applications},
    editor = {J. Suykens et al.},
    pages = {227-249},
    publisher = {IOS Press, Amsterdam, The Netherlands},
    series = {NATO Science Series, Series III: Computer and System Sciences},
    title = {An Optimization Perspective on Kernel Partial Least Squares Regression},
    volume = {190},
    year = {2003}
 }

    Valid options are: 

     -D
  Turns on output of debugging information.
     -no-checks
  Turns off all checks - use with caution!
  Turning them off assumes that data is purely numeric, doesn't
  contain any missing values, and has a nominal class. Turning them
  off also means that no header information will be stored if the
  machine is linear. Finally, it also assumes that no instance has
  a weight equal to 0.
  (default: checks on)
     -F <filename>
  The file to initialize the filter with (optional).
     -C <num>
  The class index for the file to initialize with,
  First and last are valid (optional, default: last).
     -K <classname and parameters>
  The Kernel to use.
  (default: weka.classifiers.functions.supportVector.PolyKernel)
     -kernel-factor
  Defines a factor for the kernel.
   - RBFKernel: a factor for gamma
    Standardize: 1/(2*N)
    Normalize..: 6/N
  Available parameters are:
   N for # of instances, A for # of attributes
  (default: 1)
     -P <classname and parameters>
  The Filter used for preprocessing (use weka.filters.AllFilter
  to disable preprocessing).
  (default: weka.filters.unsupervised.attribute.Center)
     
 Options specific to kernel weka.classifiers.functions.supportVector.PolyKernel:
 
     -D
  Enables debugging output (if available) to be printed.
  (default: off)
     -no-checks
  Turns off all checks - use with caution!
  (default: checks on)
     -C <num>
  The size of the cache (a prime number), 0 for full cache and 
  -1 to turn it off.
  (default: 250007)
     -E <num>
  The Exponent to use.
  (default: 1.0)
     -L
  Use lower-order terms.
  (default: no)
     
 Options specific to preprocessing filter weka.filters.unsupervised.attribute.Center:
 
     -unset-class-temporarily
  Unsets the class index temporarily before the filter is
  applied to the data.
  (default: no)
    Version:
    $Revision: 9570 $
    Author:
    Jonathan Miles (jdm18@cs.waikato.ac.nz), FracPete (fracpete at waikato dot ac dot nz)
    See Also:
    Serialized Form

    • Constructor Detail

      • KernelFilter

        public KernelFilter()

    • Method Detail

      • globalInfo

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

      • getTechnicalInformation

        public TechnicalInformation getTechnicalInformation()
        Returns an instance of a TechnicalInformation object, containing detailed information about the technical background of this class, e.g., paper reference or book this class is based on.
        Specified by:
        getTechnicalInformation in interface TechnicalInformationHandler
        Returns:
        the technical information about this class

      • listOptions

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

      • getOptions

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

      • setOptions

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

        Valid options are: 

         -D
  Turns on output of debugging information.
         -no-checks
  Turns off all checks - use with caution!
  Turning them off assumes that data is purely numeric, doesn't
  contain any missing values, and has a nominal class. Turning them
  off also means that no header information will be stored if the
  machine is linear. Finally, it also assumes that no instance has
  a weight equal to 0.
  (default: checks on)
         -F <filename>
  The file to initialize the filter with (optional).
         -C <num>
  The class index for the file to initialize with,
  First and last are valid (optional, default: last).
         -K <classname and parameters>
  The Kernel to use.
  (default: weka.classifiers.functions.supportVector.PolyKernel)
         -kernel-factor
  Defines a factor for the kernel.
   - RBFKernel: a factor for gamma
    Standardize: 1/(2*N)
    Normalize..: 6/N
  Available parameters are:
   N for # of instances, A for # of attributes
  (default: 1)
         -P <classname and parameters>
  The Filter used for preprocessing (use weka.filters.AllFilter
  to disable preprocessing).
  (default: weka.filters.unsupervised.attribute.Center)
         
 Options specific to kernel weka.classifiers.functions.supportVector.PolyKernel:
 
         -D
  Enables debugging output (if available) to be printed.
  (default: off)
         -no-checks
  Turns off all checks - use with caution!
  (default: checks on)
         -C <num>
  The size of the cache (a prime number), 0 for full cache and 
  -1 to turn it off.
  (default: 250007)
         -E <num>
  The Exponent to use.
  (default: 1.0)
         -L
  Use lower-order terms.
  (default: no)
         
 Options specific to preprocessing filter weka.filters.unsupervised.attribute.Center:
 
         -unset-class-temporarily
  Unsets the class index temporarily before the filter is
  applied to the data.
  (default: no)
        Specified by:
        setOptions in interface OptionHandler
        Overrides:
        setOptions in class SimpleFilter
        Parameters:
        options - the list of options as an array of strings
        Throws:
        java.lang.Exception - if an option is not supported
        See Also:
        SimpleFilter.reset()

      • initFileTipText

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

      • getInitFile

        public java.io.File getInitFile()
        Gets the file to initialize the filter with, can be null.
        Returns:
        the file

      • setInitFile

        public void setInitFile​(java.io.File value)
        Sets the file to initialize the filter with, can be null.
        Parameters:
        value - the file

      • initFileClassIndexTipText

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

      • getInitFileClassIndex

        public java.lang.String getInitFileClassIndex()
        Gets the class index of the file to initialize the filter with.
        Returns:
        the class index

      • setInitFileClassIndex

        public void setInitFileClassIndex​(java.lang.String value)
        Sets class index of the file to initialize the filter with.
        Parameters:
        value - the class index

      • kernelTipText

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

      • getKernel

        public Kernel getKernel()
        Gets the kernel to use.
        Returns:
        the kernel

      • setKernel

        public void setKernel​(Kernel value)
        Sets the kernel to use.
        Parameters:
        value - the kernel

      • setChecksTurnedOff

        public void setChecksTurnedOff​(boolean value)
        Disables or enables the checks (which could be time-consuming). Use with caution!
        Parameters:
        value - if true turns off all checks

      • getChecksTurnedOff

        public boolean getChecksTurnedOff()
        Returns whether the checks are turned off or not.
        Returns:
        true if the checks are turned off

      • checksTurnedOffTipText

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

      • kernelFactorExpressionTipText

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

      • getKernelFactorExpression

        public java.lang.String getKernelFactorExpression()
        Gets the expression for the kernel.
        Returns:
        the expression

      • setKernelFactorExpression

        public void setKernelFactorExpression​(java.lang.String value)
        Sets the expression for the kernel.
        Parameters:
        value - the file

      • preprocessingTipText

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

      • setPreprocessing

        public void setPreprocessing​(Filter value)
        Sets the filter to use for preprocessing (use the AllFilter for no preprocessing)
        Parameters:
        value - the preprocessing filter

      • getPreprocessing

        public Filter getPreprocessing()
        Gets the filter used for preprocessing
        Returns:
        the current preprocessing filter.

      • initFilter

        public void initFilter​(Instances instances)
                throws java.lang.Exception
        initializes the filter with the given dataset, i.e., the kernel gets built. Needs to be called before the first call of Filter.useFilter or batchFinished(), if not the -F option (or setInitFile(File) is used).
        Parameters:
        instances - the data to initialize with
        Throws:
        java.lang.Exception - if building of kernel fails

      • main

        public static void main​(java.lang.String[] args)
        runs the filter with the given arguments
        Parameters:
        args - the commandline arguments