weka.classifiers.mi
Class MISMO

java.lang.Object
  extended by weka.classifiers.Classifier
      extended by weka.classifiers.mi.MISMO
All Implemented Interfaces:
java.io.Serializable, java.lang.Cloneable, CapabilitiesHandler, MultiInstanceCapabilitiesHandler, OptionHandler, TechnicalInformationHandler, WeightedInstancesHandler

public class MISMO
extends Classifier
implements WeightedInstancesHandler, MultiInstanceCapabilitiesHandler, TechnicalInformationHandler

Implements John Platt's sequential minimal optimization algorithm for training a support vector classifier.

This implementation globally replaces all missing values and transforms nominal attributes into binary ones. It also normalizes all attributes by default. (In that case the coefficients in the output are based on the normalized data, not the original data --- this is important for interpreting the classifier.)

Multi-class problems are solved using pairwise classification.

To obtain proper probability estimates, use the option that fits logistic regression models to the outputs of the support vector machine. In the multi-class case the predicted probabilities are coupled using Hastie and Tibshirani's pairwise coupling method.

Note: for improved speed normalization should be turned off when operating on SparseInstances.

For more information on the SMO algorithm, see

J. Platt: Machines using Sequential Minimal Optimization. In B. Schoelkopf and C. Burges and A. Smola, editors, Advances in Kernel Methods - Support Vector Learning, 1998.

S.S. Keerthi, S.K. Shevade, C. Bhattacharyya, K.R.K. Murthy (2001). Improvements to Platt's SMO Algorithm for SVM Classifier Design. Neural Computation. 13(3):637-649.

BibTeX:

 @incollection{Platt1998,
    author = {J. Platt},
    booktitle = {Advances in Kernel Methods - Support Vector Learning},
    editor = {B. Schoelkopf and C. Burges and A. Smola},
    publisher = {MIT Press},
    title = {Machines using Sequential Minimal Optimization},
    year = {1998}
 }
 
 @article{Keerthi2001,
    author = {S.S. Keerthi and S.K. Shevade and C. Bhattacharyya and K.R.K. Murthy},
    journal = {Neural Computation},
    number = {3},
    pages = {637-649},
    title = {Improvements to Platt's SMO Algorithm for SVM Classifier Design},
    volume = {13},
    year = {2001}
 }
 

Valid options are:

 -D
  If set, classifier is run in debug mode and
  may output additional info to the console
 -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)
 -C <double>
  The complexity constant C. (default 1)
 -N
  Whether to 0=normalize/1=standardize/2=neither.
  (default 0=normalize)
 -I
  Use MIminimax feature space. 
 -L <double>
  The tolerance parameter. (default 1.0e-3)
 -P <double>
  The epsilon for round-off error. (default 1.0e-12)
 -M
  Fit logistic models to SVM outputs. 
 -V <double>
  The number of folds for the internal cross-validation. 
  (default -1, use training data)
 -W <double>
  The random number seed. (default 1)
 -K <classname and parameters>
  The Kernel to use.
  (default: weka.classifiers.functions.supportVector.PolyKernel)
 
 Options specific to kernel weka.classifiers.mi.supportVector.MIPolyKernel:
 
 -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)

Version:
$Revision: 1.5 $
Author:
Eibe Frank (eibe@cs.waikato.ac.nz), Shane Legg (shane@intelligenesis.net) (sparse vector code), Stuart Inglis (stuart@reeltwo.com) (sparse vector code), Lin Dong (ld21@cs.waikato.ac.nz) (code for adapting to MI data)
See Also:
Serialized Form

Field Summary
static int FILTER_NONE
          No normalization/standardization
static int FILTER_NORMALIZE
          Normalize training data
static int FILTER_STANDARDIZE
          Standardize training data
static Tag[] TAGS_FILTER
          The filter to apply to the training data
 
Constructor Summary
MISMO()
           
 
Method Summary
 java.lang.String[][][] attributeNames()
          Returns the attribute names.
 double[][] bias()
          Returns the bias of each binary SMO.
 void buildClassifier(Instances insts)
          Method for building the classifier.
 java.lang.String buildLogisticModelsTipText()
          Returns the tip text for this property
 java.lang.String checksTurnedOffTipText()
          Returns the tip text for this property
 java.lang.String[] classAttributeNames()
          Returns the names of the class attributes.
 java.lang.String cTipText()
          Returns the tip text for this property
 double[] distributionForInstance(Instance inst)
          Estimates class probabilities for given instance.
 java.lang.String epsilonTipText()
          Returns the tip text for this property
 java.lang.String filterTypeTipText()
          Returns the tip text for this property
 boolean getBuildLogisticModels()
          Get the value of buildLogisticModels.
 double getC()
          Get the value of C.
 Capabilities getCapabilities()
          Returns default capabilities of the classifier.
 boolean getChecksTurnedOff()
          Returns whether the checks are turned off or not.
 double getEpsilon()
          Get the value of epsilon.
 SelectedTag getFilterType()
          Gets how the training data will be transformed.
 Kernel getKernel()
          Gets the kernel to use.
 boolean getMinimax()
          Check if the MIMinimax feature space is to be used.
 Capabilities getMultiInstanceCapabilities()
          Returns the capabilities of this multi-instance classifier for the relational data.
 int getNumFolds()
          Get the value of numFolds.
 java.lang.String[] getOptions()
          Gets the current settings of the classifier.
 int getRandomSeed()
          Get the value of randomSeed.
 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.
 double getToleranceParameter()
          Get the value of tolerance parameter.
 java.lang.String globalInfo()
          Returns a string describing classifier
 java.lang.String kernelTipText()
          Returns the tip text for this property
 java.util.Enumeration listOptions()
          Returns an enumeration describing the available options.
static void main(java.lang.String[] argv)
          Main method for testing this class.
 java.lang.String minimaxTipText()
          Returns the tip text for this property
 int numClassAttributeValues()
          Returns the number of values of the class attribute.
 java.lang.String numFoldsTipText()
          Returns the tip text for this property
 double[] pairwiseCoupling(double[][] n, double[][] r)
          Implements pairwise coupling.
 java.lang.String randomSeedTipText()
          Returns the tip text for this property
 void setBuildLogisticModels(boolean newbuildLogisticModels)
          Set the value of buildLogisticModels.
 void setC(double v)
          Set the value of C.
 void setChecksTurnedOff(boolean value)
          Disables or enables the checks (which could be time-consuming).
 void setEpsilon(double v)
          Set the value of epsilon.
 void setFilterType(SelectedTag newType)
          Sets how the training data will be transformed.
 void setKernel(Kernel value)
          Sets the kernel to use.
 void setMinimax(boolean v)
          Set if the MIMinimax feature space is to be used.
 void setNumFolds(int newnumFolds)
          Set the value of numFolds.
 void setOptions(java.lang.String[] options)
          Parses a given list of options.
 void setRandomSeed(int newrandomSeed)
          Set the value of randomSeed.
 void setToleranceParameter(double v)
          Set the value of tolerance parameter.
 int[][][] sparseIndices()
          Returns the indices in sparse format.
 double[][][] sparseWeights()
          Returns the weights in sparse format.
 java.lang.String toleranceParameterTipText()
          Returns the tip text for this property
 java.lang.String toString()
          Prints out the classifier.
 void turnChecksOff()
          Turns off checks for missing values, etc.
 void turnChecksOn()
          Turns on checks for missing values, etc.
 
Methods inherited from class weka.classifiers.Classifier
classifyInstance, debugTipText, forName, getDebug, makeCopies, makeCopy, setDebug
 
Methods inherited from class java.lang.Object
equals, getClass, hashCode, notify, notifyAll, wait, wait, wait
 

Field Detail

FILTER_NORMALIZE

public static final int FILTER_NORMALIZE
Normalize training data

See Also:
Constant Field Values

FILTER_STANDARDIZE

public static final int FILTER_STANDARDIZE
Standardize training data

See Also:
Constant Field Values

FILTER_NONE

public static final int FILTER_NONE
No normalization/standardization

See Also:
Constant Field Values

TAGS_FILTER

public static final Tag[] TAGS_FILTER
The filter to apply to the training data

Constructor Detail

MISMO

public MISMO()
Method Detail

globalInfo

public java.lang.String globalInfo()
Returns a string describing classifier

Returns:
a description 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

turnChecksOff

public void turnChecksOff()
Turns off checks for missing values, etc. Use with caution.


turnChecksOn

public void turnChecksOn()
Turns on checks for missing values, etc.


getCapabilities

public Capabilities getCapabilities()
Returns default capabilities of the classifier.

Specified by:
getCapabilities in interface CapabilitiesHandler
Overrides:
getCapabilities in class Classifier
Returns:
the capabilities of this classifier
See Also:
Capabilities

getMultiInstanceCapabilities

public Capabilities getMultiInstanceCapabilities()
Returns the capabilities of this multi-instance classifier for the relational data.

Specified by:
getMultiInstanceCapabilities in interface MultiInstanceCapabilitiesHandler
Returns:
the capabilities of this object
See Also:
Capabilities

buildClassifier

public void buildClassifier(Instances insts)
                     throws java.lang.Exception
Method for building the classifier. Implements a one-against-one wrapper for multi-class problems.

Specified by:
buildClassifier in class Classifier
Parameters:
insts - the set of training instances
Throws:
java.lang.Exception - if the classifier can't be built successfully

distributionForInstance

public double[] distributionForInstance(Instance inst)
                                 throws java.lang.Exception
Estimates class probabilities for given instance.

Overrides:
distributionForInstance in class Classifier
Parameters:
inst - the instance to compute the distribution for
Returns:
the class probabilities
Throws:
java.lang.Exception - if computation fails

pairwiseCoupling

public double[] pairwiseCoupling(double[][] n,
                                 double[][] r)
Implements pairwise coupling.

Parameters:
n - the sum of weights used to train each model
r - the probability estimate from each model
Returns:
the coupled estimates

sparseWeights

public double[][][] sparseWeights()
Returns the weights in sparse format.

Returns:
the weights in sparse format

sparseIndices

public int[][][] sparseIndices()
Returns the indices in sparse format.

Returns:
the indices in sparse format

bias

public double[][] bias()
Returns the bias of each binary SMO.

Returns:
the bias of each binary SMO

numClassAttributeValues

public int numClassAttributeValues()
Returns the number of values of the class attribute.

Returns:
the number values of the class attribute

classAttributeNames

public java.lang.String[] classAttributeNames()
Returns the names of the class attributes.

Returns:
the names of the class attributes

attributeNames

public java.lang.String[][][] attributeNames()
Returns the attribute names.

Returns:
the attribute names

listOptions

public java.util.Enumeration listOptions()
Returns an enumeration describing the available options.

Specified by:
listOptions in interface OptionHandler
Overrides:
listOptions in class Classifier
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:

 -D
  If set, classifier is run in debug mode and
  may output additional info to the console
 -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)
 -C <double>
  The complexity constant C. (default 1)
 -N
  Whether to 0=normalize/1=standardize/2=neither.
  (default 0=normalize)
 -I
  Use MIminimax feature space. 
 -L <double>
  The tolerance parameter. (default 1.0e-3)
 -P <double>
  The epsilon for round-off error. (default 1.0e-12)
 -M
  Fit logistic models to SVM outputs. 
 -V <double>
  The number of folds for the internal cross-validation. 
  (default -1, use training data)
 -W <double>
  The random number seed. (default 1)
 -K <classname and parameters>
  The Kernel to use.
  (default: weka.classifiers.functions.supportVector.PolyKernel)
 
 Options specific to kernel weka.classifiers.mi.supportVector.MIPolyKernel:
 
 -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)

Specified by:
setOptions in interface OptionHandler
Overrides:
setOptions in class Classifier
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 classifier.

Specified by:
getOptions in interface OptionHandler
Overrides:
getOptions in class Classifier
Returns:
an array of strings suitable for passing to setOptions

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

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

cTipText

public java.lang.String cTipText()
Returns the tip text for this property

Returns:
tip text for this property suitable for displaying in the explorer/experimenter gui

getC

public double getC()
Get the value of C.

Returns:
Value of C.

setC

public void setC(double v)
Set the value of C.

Parameters:
v - Value to assign to C.

toleranceParameterTipText

public java.lang.String toleranceParameterTipText()
Returns the tip text for this property

Returns:
tip text for this property suitable for displaying in the explorer/experimenter gui

getToleranceParameter

public double getToleranceParameter()
Get the value of tolerance parameter.

Returns:
Value of tolerance parameter.

setToleranceParameter

public void setToleranceParameter(double v)
Set the value of tolerance parameter.

Parameters:
v - Value to assign to tolerance parameter.

epsilonTipText

public java.lang.String epsilonTipText()
Returns the tip text for this property

Returns:
tip text for this property suitable for displaying in the explorer/experimenter gui

getEpsilon

public double getEpsilon()
Get the value of epsilon.

Returns:
Value of epsilon.

setEpsilon

public void setEpsilon(double v)
Set the value of epsilon.

Parameters:
v - Value to assign to epsilon.

filterTypeTipText

public java.lang.String filterTypeTipText()
Returns the tip text for this property

Returns:
tip text for this property suitable for displaying in the explorer/experimenter gui

getFilterType

public SelectedTag getFilterType()
Gets how the training data will be transformed. Will be one of FILTER_NORMALIZE, FILTER_STANDARDIZE, FILTER_NONE.

Returns:
the filtering mode

setFilterType

public void setFilterType(SelectedTag newType)
Sets how the training data will be transformed. Should be one of FILTER_NORMALIZE, FILTER_STANDARDIZE, FILTER_NONE.

Parameters:
newType - the new filtering mode

minimaxTipText

public java.lang.String minimaxTipText()
Returns the tip text for this property

Returns:
tip text for this property suitable for displaying in the explorer/experimenter gui

getMinimax

public boolean getMinimax()
Check if the MIMinimax feature space is to be used.

Returns:
true if minimax

setMinimax

public void setMinimax(boolean v)
Set if the MIMinimax feature space is to be used.

Parameters:
v - true if RBF

buildLogisticModelsTipText

public java.lang.String buildLogisticModelsTipText()
Returns the tip text for this property

Returns:
tip text for this property suitable for displaying in the explorer/experimenter gui

getBuildLogisticModels

public boolean getBuildLogisticModels()
Get the value of buildLogisticModels.

Returns:
Value of buildLogisticModels.

setBuildLogisticModels

public void setBuildLogisticModels(boolean newbuildLogisticModels)
Set the value of buildLogisticModels.

Parameters:
newbuildLogisticModels - Value to assign to buildLogisticModels.

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.

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()
Get the value of randomSeed.

Returns:
Value of randomSeed.

setRandomSeed

public void setRandomSeed(int newrandomSeed)
Set the value of randomSeed.

Parameters:
newrandomSeed - Value to assign to randomSeed.

toString

public java.lang.String toString()
Prints out the classifier.

Overrides:
toString in class java.lang.Object
Returns:
a description of the classifier as a string

main

public static void main(java.lang.String[] argv)
Main method for testing this class.

Parameters:
argv - the commandline parameters