weka.distributed

Class CorrelationMatrixMapTask

java.lang.Object

weka.distributed.CorrelationMatrixMapTask

All Implemented Interfaces:

java.io.Serializable, weka.core.OptionHandler

public class CorrelationMatrixMapTask
extends java.lang.Object
implements java.io.Serializable, weka.core.OptionHandler

A map task that computes partial covariance sums for a covariance/correlation matrix from the data it gets via its processInstance() method. Expects to be initialized with a training header that includes summary meta attributes. Can replace missing values with means or ommit them from the updates.

Version:

$Revision: 11018 $

Author:

Mark Hall (mhall{[at]}pentaho{[dot]}com)

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
CorrelationMatrixMapTask()

Method Summary

Modifier and Type	Method and Description
java.lang.String	covarianceTipText() Tool tip text for this property.
int[][]	getCoOccurrenceCounts() The co-occurrence counts (will be null if missings are replaced by means)
boolean	getCovariance() Get whether to compute a covariance matrix rather than a correlation one
boolean	getIgnoreMissingValues() Get whether to ignore missing values
boolean	getKeepClassAttributeIfSet() Get whether to keep the class attribute as part of the correlation analysis
double[][]	getMatrix() Returns the matrix
java.lang.String[]	getOptions()
java.lang.String	ignoreMissingValuesTipText() Tool tip text for this property.
java.lang.String	keepClassAttributeIfSetTipText() Tool tip text for this property.
java.util.Enumeration<weka.core.Option>	listOptions()
static void	main(java.lang.String[] args) Main method for testing this class
void	processInstance(weka.core.Instance inst) Process an instance
void	setCovariance(boolean cov) Set whether to compute a covariance matrix rather than a correlation one
void	setIgnoreMissingValues(boolean ignore) Set whether to ignore missing values
void	setKeepClassAttributeIfSet(boolean keep) Set whether to keep the class attribute as part of the correlation analysis
void	setOptions(java.lang.String[] options)
void	setup(weka.core.Instances trainingHeader) Initialize the map task

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface weka.core.OptionHandler

makeCopy

Constructor Detail

CorrelationMatrixMapTask

public CorrelationMatrixMapTask()

Method Detail

listOptions

public java.util.Enumeration<weka.core.Option> listOptions()

Specified by:

listOptions in interface weka.core.OptionHandler

setOptions

public void setOptions(java.lang.String[] options)
                throws java.lang.Exception

Specified by:

setOptions in interface weka.core.OptionHandler

Throws:

java.lang.Exception

getOptions

public java.lang.String[] getOptions()

Specified by:

getOptions in interface weka.core.OptionHandler

ignoreMissingValuesTipText

public java.lang.String ignoreMissingValuesTipText()

Tool tip text for this property.

Returns:

a string describing this property

setIgnoreMissingValues

public void setIgnoreMissingValues(boolean ignore)

Set whether to ignore missing values

Parameters:

ignore - true if missing values are to be ignored

getIgnoreMissingValues

public boolean getIgnoreMissingValues()

Get whether to ignore missing values

Returns:

true if missing values are to be ignored

keepClassAttributeIfSetTipText

public java.lang.String keepClassAttributeIfSetTipText()

Tool tip text for this property.

Returns:

a string describing this property

setKeepClassAttributeIfSet

public void setKeepClassAttributeIfSet(boolean keep)

Set whether to keep the class attribute as part of the correlation analysis

Parameters:

keep - true if the class attribute is to be kept

getKeepClassAttributeIfSet

public boolean getKeepClassAttributeIfSet()

Get whether to keep the class attribute as part of the correlation analysis

Returns:

true if the class attribute is to be kept

covarianceTipText

public java.lang.String covarianceTipText()

Tool tip text for this property.

Returns:

a string describing this property

setCovariance

public void setCovariance(boolean cov)

Set whether to compute a covariance matrix rather than a correlation one

Parameters:

cov - true if a covariance matrix is to be computed rather than correlation

getCovariance

public boolean getCovariance()

Get whether to compute a covariance matrix rather than a correlation one

Returns:

true if a covariance matrix is to be computed rather than correlation

getMatrix

public double[][] getMatrix()

Returns the matrix

Returns:

the matrix

getCoOccurrenceCounts

public int[][] getCoOccurrenceCounts()

The co-occurrence counts (will be null if missings are replaced by means)

Returns:

the co-occurrence counts, or null if missings are being replaced by means

processInstance

public void processInstance(weka.core.Instance inst)
                     throws java.lang.Exception

Process an instance

Parameters:

inst - the instance to process

Throws:

java.lang.Exception - if a problem occurs

setup

public void setup(weka.core.Instances trainingHeader)
           throws DistributedWekaException

Initialize the map task

Parameters:

trainingHeader - the training header for the data (including summary meta attributes)

Throws:

DistributedWekaException - if a problem occurs

main

public static void main(java.lang.String[] args)

Main method for testing this class

Parameters:

args - command line arguments