weka.classifiers.kstar
Class KStarNumericAttribute

java.lang.Object
  |
  +--weka.classifiers.kstar.KStarNumericAttribute

All Implemented Interfaces:

KStarConstants

public class KStarNumericAttribute

extends java.lang.Object

implements KStarConstants

A custom class which provides the environment for computing the transformation probability of a specified test instance numeric attribute to a specified train instance numeric attribute.

Author:

Len Trigg (len@intelligenesis.net), Abdelaziz Mahoui (am14@cs.waikato.ac.nz)

Field Summary

protected int	m_ActualCount The number of train instances with no missing attribute values
protected int	m_AttrIndex The index of the attribute in the test and train instances
protected double	m_AverageProb Average probability of test attribute transforming into train attribute
protected int	m_BlendFactor default sphere of influence blend setting
protected int	m_BlendMethod 0 = use specified blend, 1 = entropic blend setting
protected KStarCache	m_Cache A cache for storing attribute values and their corresponding scale parameters
protected int	m_ClassType The class attribute type
protected double[]	m_Distances The set of disctances from the test attribute to the set of train attributes
protected int	m_MissingMode missing value treatment
protected double	m_MissingProb Probability of test attribute transforming into train attribute with missing value
protected int	m_NumAttributes The number of attributes
protected int	m_NumClasses The number of class values
protected int	m_NumInstances The number of instances in the dataset
protected int[][]	m_RandClassCols Set of colomns: each colomn representing a randomised version of the train dataset class colomn
protected double	m_Scale The scale parameter
protected double	m_SmallestProb Smallest probability of test attribute transforming into train attribute
protected Instance	m_Test The test instance
protected Instance	m_Train The train instance
protected Instances	m_TrainSet The training instances used for classification.

Fields inherited from interface weka.classifiers.kstar.KStarConstants

B_ENTROPY, B_SPHERE, EPSILON, FLOOR, FLOOR1, INITIAL_STEP, LOG2, M_AVERAGE, M_DELETE, M_MAXDIFF, M_NORMAL, NUM_RAND_COLS, OFF, ON, ROOT_FINDER_ACCURACY, ROOT_FINDER_MAX_ITER

Constructor Summary

KStarNumericAttribute(Instance test, Instance train, int attrIndex, Instances trainSet, int[][] randClassCols, KStarCache cache)
Constructor

Method Summary

void	setBlendFactor(int factor) Set the blending factor
void	setBlendMethod(int method) Set the blending method
void	setMissingMode(int mode) Set the missing value mode.
void	setOptions(int missingmode, int blendmethod, int blendfactor) Set options.
double	transProb() Calculates the transformation probability of the attribute indexed "m_AttrIndex" in test instance "m_Test" to the same attribute in the train instance "m_Train".

Methods inherited from class java.lang.Object

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

Field Detail

m_TrainSet

protected Instances m_TrainSet

The training instances used for classification.

m_Test

protected Instance m_Test

The test instance

m_Train

protected Instance m_Train

The train instance

m_AttrIndex

protected int m_AttrIndex

The index of the attribute in the test and train instances

m_Scale

protected double m_Scale

The scale parameter

m_MissingProb

protected double m_MissingProb

Probability of test attribute transforming into train attribute with missing value

m_AverageProb

protected double m_AverageProb

Average probability of test attribute transforming into train attribute

m_SmallestProb

protected double m_SmallestProb

Smallest probability of test attribute transforming into train attribute

m_Distances

protected double[] m_Distances

The set of disctances from the test attribute to the set of train attributes

m_RandClassCols

protected int[][] m_RandClassCols

Set of colomns: each colomn representing a randomised version of the train dataset class colomn

m_ActualCount

protected int m_ActualCount

The number of train instances with no missing attribute values

m_Cache

protected KStarCache m_Cache

A cache for storing attribute values and their corresponding scale parameters

m_NumInstances

protected int m_NumInstances

The number of instances in the dataset

m_NumClasses

protected int m_NumClasses

The number of class values

m_NumAttributes

protected int m_NumAttributes

The number of attributes

m_ClassType

protected int m_ClassType

The class attribute type

m_MissingMode

protected int m_MissingMode

missing value treatment

m_BlendMethod

protected int m_BlendMethod

0 = use specified blend, 1 = entropic blend setting

m_BlendFactor

protected int m_BlendFactor

default sphere of influence blend setting

Constructor Detail

KStarNumericAttribute

public KStarNumericAttribute(Instance test,
                             Instance train,
                             int attrIndex,
                             Instances trainSet,
                             int[][] randClassCols,
                             KStarCache cache)

Constructor

Method Detail

transProb

public double transProb()

Calculates the transformation probability of the attribute indexed "m_AttrIndex" in test instance "m_Test" to the same attribute in the train instance "m_Train".

Returns:

the probability value

setOptions

public void setOptions(int missingmode,
                       int blendmethod,
                       int blendfactor)

Set options.

Parameters:

missingmode - the missing value treatment to use

blendmethod - the blending method to use

blendfactor - the level of blending to use

setMissingMode

public void setMissingMode(int mode)

Set the missing value mode.

Parameters:

mode - the type of missing value treatment to use

setBlendMethod

public void setBlendMethod(int method)

Set the blending method

Parameters:

method - the blending method to use

setBlendFactor

public void setBlendFactor(int factor)

Set the blending factor

Parameters:

factor - the level of blending to use