All Packages  Class Hierarchy  This Package  Previous  Next  Index  WEKA's home

Class weka.clusterers.EM

java.lang.Object
   |
   +----weka.clusterers.Clusterer
           |
           +----weka.clusterers.DistributionClusterer
                   |
                   +----weka.clusterers.EM

public class EM

extends DistributionClusterer

implements OptionHandler

EM assigns a probability distribution to each instance which indicates the probability of it belonging to each of the clusters. EM can decide how many clusters to create by cross validation, or you may specify apriori how many clusters to generate.

Valid options are:

-V
Verbose.

-N
Specify the number of clusters to generate. If omitted, EM will use cross validation to select the number of clusters automatically.

-I
Terminate after this many iterations if EM has not converged.

-S
Specify random number seed.

-M
Set the minimum allowable standard deviation for normal density calculation.

Author:

Mark Hall (mhall@cs.waikato.ac.nz)

EM()

Constructor.

buildClusterer(Instances)

Generates a clusterer.

densityForInstance(Instance)

Computes the density for a given instance.

distributionForInstance(Instance)

Predicts the cluster memberships for a given instance.

getDebug()

Get debug mode

getMaxIterations()

Get the maximum number of iterations

getMinStdDev()

Get the minimum allowable standard deviation.

getNumClusters()

Get the number of clusters

getOptions()

Gets the current settings of EM.

getSeed()

Get the random number seed

globalInfo()

Returns a string describing this clusterer

listOptions()

Returns an enumeration describing the available options.

main(String[])

Main method for testing this class.

maxIterationsTipText()

Returns the tip text for this property

minStdDevTipText()

Returns the tip text for this property

numberOfClusters()

Returns the number of clusters.

numClustersTipText()

Returns the tip text for this property

seedTipText()

Returns the tip text for this property

setDebug(boolean)

Set debug mode - verbose output

setMaxIterations(int)

Set the maximum number of iterations to perform

setMinStdDev(double)

Set the minimum value for standard deviation when calculating normal density.

setNumClusters(int)

Set the number of clusters (-1 to select by CV).

setOptions(String[])

Parses a given list of options.

setSeed(int)

Set the random number seed

toString()

Outputs the generated clusters into a string.

 public EM()

Constructor.

 public String globalInfo()

Returns a string describing this clusterer

Returns:

a description of the evaluator suitable for displaying in the explorer/experimenter gui

 public Enumeration listOptions()

Returns an enumeration describing the available options.

Valid options are:

-V
Verbose.

-N
Specify the number of clusters to generate. If omitted, EM will use cross validation to select the number of clusters automatically.

-I
Terminate after this many iterations if EM has not converged.

-S
Specify random number seed.

-M
Set the minimum allowable standard deviation for normal density calculation.

Returns:

an enumeration of all the available options

 public void setOptions(String options[]) throws Exception

Parses a given list of options.

Parameters:

options - the list of options as an array of strings

Throws: Exception

if an option is not supported

 public String minStdDevTipText()

Returns the tip text for this property

Returns:

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

 public void setMinStdDev(double m)

Set the minimum value for standard deviation when calculating normal density. Reducing this value can help prevent arithmetic overflow resulting from multiplying large densities (arising from small standard deviations) when there are many singleton or near singleton values.

Parameters:

m - minimum value for standard deviation

 public double getMinStdDev()

Get the minimum allowable standard deviation.

Returns:

the minumum allowable standard deviation

 public String seedTipText()

Returns the tip text for this property

Returns:

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

 public void setSeed(int s)

Set the random number seed

Parameters:

s - the seed

 public int getSeed()

Get the random number seed

Returns:

the seed

 public String numClustersTipText()

Returns the tip text for this property

Returns:

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

 public void setNumClusters(int n) throws Exception

Set the number of clusters (-1 to select by CV).

Parameters:

n - the number of clusters

Throws: Exception

if n is 0

 public int getNumClusters()

Get the number of clusters

Returns:

the number of clusters.

 public String maxIterationsTipText()

Returns the tip text for this property

Returns:

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

 public void setMaxIterations(int i) throws Exception

Set the maximum number of iterations to perform

Parameters:

i - the number of iterations

Throws: Exception

if i is less than 1

 public int getMaxIterations()

Get the maximum number of iterations

Returns:

the number of iterations

 public void setDebug(boolean v)

Set debug mode - verbose output

Parameters:

v - true for verbose output

 public boolean getDebug()

Get debug mode

Returns:

true if debug mode is set

 public String[] getOptions()

Gets the current settings of EM.

Returns:

an array of strings suitable for passing to setOptions()

 public String toString()

Outputs the generated clusters into a string.

Overrides:

toString in class Object

 public int numberOfClusters() throws Exception

Returns the number of clusters.

Returns:

the number of clusters generated for a training dataset.

Throws: Exception

if number of clusters could not be returned successfully

Overrides:

numberOfClusters in class Clusterer

 public void buildClusterer(Instances data) throws Exception

Generates a clusterer. Has to initialize all fields of the clusterer that are not being set via options.

Parameters:

data - set of instances serving as training data

Throws: Exception

if the clusterer has not been generated successfully

Overrides:

buildClusterer in class Clusterer

 public double densityForInstance(Instance inst) throws Exception

Computes the density for a given instance.

Parameters:

inst - the instance to compute the density for

Returns:

the density.

Throws: Exception

if the density could not be computed successfully

Overrides:

densityForInstance in class DistributionClusterer

 public double[] distributionForInstance(Instance inst) throws Exception

Predicts the cluster memberships for a given instance.

Parameters:

data - set of test instances

instance - the instance to be assigned a cluster.

Returns:

an array containing the estimated membership probabilities of the test instance in each cluster (this should sum to at most 1)

Throws: Exception

if distribution could not be computed successfully

Overrides:

distributionForInstance in class DistributionClusterer

 public static void main(String argv[])

Main method for testing this class.

Parameters:

argv - should contain the following arguments:

-t training file [-T test file] [-N number of clusters] [-S random seed]

All Packages  Class Hierarchy  This Package  Previous  Next  Index  WEKA's home