weka.core
Class WeightedEuclideanDistance

java.lang.Object
  weka.core.NormalizableDistance
      weka.core.WeightedEuclideanDistance

All Implemented Interfaces:

Serializable, Cloneable, weka.core.DistanceFunction, weka.core.OptionHandler, weka.core.RevisionHandler, weka.core.TechnicalInformationHandler

public class WeightedEuclideanDistance
extends weka.core.NormalizableDistance
implements Cloneable, weka.core.TechnicalInformationHandler

Implementing Euclidean distance (or similarity) function.

One object defines not one distance but the data model in which the distances between objects of that data model can be computed.

Attention: For efficiency reasons the use of consistency checks (like are the data models of the two instances exactly the same), is low.

For more information, see:

Wikipedia. Euclidean distance. URL http://en.wikipedia.org/wiki/Euclidean_distance.

BibTeX:

 @misc{missing_id,
    author = {Wikipedia},
    title = {Euclidean distance},
    URL = {http://en.wikipedia.org/wiki/Euclidean_distance}
 }
 

Valid options are:

 -D
  Turns off the normalization of attribute 
  values in distance calculation.

 -R <col1,col2-col4,...>
  Specifies list of columns to used in the calculation of the 
  distance. 'first' and 'last' are valid indices.
  (default: first-last)

 -V
  Invert matching sense of column indices.

Version:

$Revision: 4584 $

Author:

dale (dale at waikato dot ac dot nz)

See Also:

Serialized Form

Field Summary

protected double[]	m_Coefficients Array for storing coefficients of linear regression.
protected weka.classifiers.functions.LinearRegression	m_LR
protected weka.filters.unsupervised.attribute.Normalize	m_norm

Fields inherited from class weka.core.NormalizableDistance

m_ActiveIndices, m_AttributeIndices, m_Data, m_DontNormalize, m_Ranges, m_Validated, R_MAX, R_MIN, R_WIDTH

Constructor Summary

WeightedEuclideanDistance()
Constructs an Euclidean Distance object, Instances must be still set.

WeightedEuclideanDistance(weka.core.Instances data)
Constructs an Euclidean Distance object and automatically initializes the ranges.

Method Summary

protected double	difference(int index, double val1, double val2) Computes the difference between two given attribute values.
double	distance(weka.core.Instance first, weka.core.Instance second) Calculates the distance between two instances.
double	distance(weka.core.Instance first, weka.core.Instance second, double cutOffValue, weka.core.neighboursearch.PerformanceStats stats)
double	distance(weka.core.Instance first, weka.core.Instance second, weka.core.neighboursearch.PerformanceStats stats) Calculates the distance (or similarity) between two instances.
double	getMiddle(double[] ranges) Returns value in the middle of the two parameter values.
String	getRevision() Returns the revision string.
weka.core.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.
String	globalInfo() Returns a string describing this object.
protected void	initialize() initializes the ranges and the attributes being used.
void	postProcessDistances(double[] distances) Does post processing of the distances (if necessary) returned by distance(distance(Instance first, Instance second, double cutOffValue).
double	sqDifference(int index, double val1, double val2) Returns the squared difference of two values of an attribute.
protected weka.core.Instance	transform(weka.core.Instance i)
protected double	updateDistance(double currDist, double diff) Updates the current distance calculated so far with the new difference between two attributes.
boolean	valueIsSmallerEqual(weka.core.Instance instance, int dim, double value) Returns true if the value of the given dimension is smaller or equal the value to be compared with.

Methods inherited from class weka.core.NormalizableDistance

attributeIndicesTipText, distance, dontNormalizeTipText, getAttributeIndices, getDontNormalize, getInstances, getInvertSelection, getOptions, getRanges, initializeAttributeIndices, initializeRanges, initializeRanges, initializeRanges, initializeRangesEmpty, inRanges, invalidate, invertSelectionTipText, listOptions, norm, rangesSet, setAttributeIndices, setDontNormalize, setInstances, setInvertSelection, setOptions, toString, update, updateRanges, updateRanges, updateRanges, updateRangesFirst, validate

Methods inherited from class java.lang.Object

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

Field Detail

m_Coefficients

protected double[] m_Coefficients

Array for storing coefficients of linear regression.

m_LR

protected weka.classifiers.functions.LinearRegression m_LR

m_norm

protected weka.filters.unsupervised.attribute.Normalize m_norm

Constructor Detail

WeightedEuclideanDistance

public WeightedEuclideanDistance()

Constructs an Euclidean Distance object, Instances must be still set.

WeightedEuclideanDistance

public WeightedEuclideanDistance(weka.core.Instances data)

Constructs an Euclidean Distance object and automatically initializes the ranges.

Parameters:

data - the instances the distance function should work on

Method Detail

initialize

protected void initialize()

initializes the ranges and the attributes being used.

Overrides:

initialize in class weka.core.NormalizableDistance

globalInfo

public String globalInfo()

Returns a string describing this object.

Specified by:

globalInfo in class weka.core.NormalizableDistance

Returns:

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

getTechnicalInformation

public weka.core.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 weka.core.TechnicalInformationHandler

Returns:

the technical information about this class

distance

public double distance(weka.core.Instance first,
                       weka.core.Instance second)

Calculates the distance between two instances.

Specified by:

distance in interface weka.core.DistanceFunction

Overrides:

distance in class weka.core.NormalizableDistance

Parameters:

first - the first instance

second - the second instance

Returns:

the distance between the two given instances

distance

public double distance(weka.core.Instance first,
                       weka.core.Instance second,
                       weka.core.neighboursearch.PerformanceStats stats)

Calculates the distance (or similarity) between two instances. Need to pass this returned distance later on to postprocess method to set it on correct scale.
P.S.: Please don't mix the use of this function with distance(Instance first, Instance second), as that already does post processing. Please consider passing Double.POSITIVE_INFINITY as the cutOffValue to this function and then later on do the post processing on all the distances.

Specified by:

distance in interface weka.core.DistanceFunction

Overrides:

distance in class weka.core.NormalizableDistance

Parameters:

first - the first instance

second - the second instance

stats - the structure for storing performance statistics.

Returns:

the distance between the two given instances or Double.POSITIVE_INFINITY.

updateDistance

protected double updateDistance(double currDist,
                                double diff)

Updates the current distance calculated so far with the new difference between two attributes. The difference between the attributes was calculated with the difference(int,double,double) method.

Specified by:

updateDistance in class weka.core.NormalizableDistance

Parameters:

currDist - the current distance calculated so far

diff - the difference between two new attributes

Returns:

the update distance

See Also:

difference(int, double, double)

distance

public double distance(weka.core.Instance first,
                       weka.core.Instance second,
                       double cutOffValue,
                       weka.core.neighboursearch.PerformanceStats stats)

Specified by:

distance in interface weka.core.DistanceFunction

Overrides:

distance in class weka.core.NormalizableDistance

difference

protected double difference(int index,
                            double val1,
                            double val2)

Computes the difference between two given attribute values.

Overrides:

difference in class weka.core.NormalizableDistance

Parameters:

index - the attribute index

val1 - the first value

val2 - the second value

Returns:

the difference

postProcessDistances

public void postProcessDistances(double[] distances)

Does post processing of the distances (if necessary) returned by distance(distance(Instance first, Instance second, double cutOffValue). It is necessary to do so to get the correct distances if distance(distance(Instance first, Instance second, double cutOffValue) is used. This is because that function actually returns the squared distance to avoid inaccuracies arising from floating point comparison.

Specified by:

postProcessDistances in interface weka.core.DistanceFunction

Overrides:

postProcessDistances in class weka.core.NormalizableDistance

Parameters:

distances - the distances to post-process

sqDifference

public double sqDifference(int index,
                           double val1,
                           double val2)

Returns the squared difference of two values of an attribute.

Parameters:

index - the attribute index

val1 - the first value

val2 - the second value

Returns:

the squared difference

getMiddle

public double getMiddle(double[] ranges)

Returns value in the middle of the two parameter values.

Parameters:

ranges - the ranges to this dimension

Returns:

the middle value

transform

protected weka.core.Instance transform(weka.core.Instance i)

valueIsSmallerEqual

public boolean valueIsSmallerEqual(weka.core.Instance instance,
                                   int dim,
                                   double value)

Returns true if the value of the given dimension is smaller or equal the value to be compared with.

Parameters:

instance - the instance where the value should be taken of

dim - the dimension of the value

value - the value to compare with

Returns:

true if value of instance is smaller or equal value

getRevision

public String getRevision()

Returns the revision string.

Specified by:

getRevision in interface weka.core.RevisionHandler

Returns:

the revision