moa.classifiers.lazy.neighboursearch

Class LinearNNSearch

java.lang.Object

moa.classifiers.lazy.neighboursearch.NearestNeighbourSearch

moa.classifiers.lazy.neighboursearch.LinearNNSearch

All Implemented Interfaces:

Serializable

public class LinearNNSearch
extends NearestNeighbourSearch

Class implementing the brute force search algorithm for nearest neighbour search.

Valid options are:

 -S
  Skip identical instances (distances equal to zero).
 

Version:

$Revision: 8034 $

Author:

Ashraf M. Kibriya (amk14[at-the-rate]cs[dot]waikato[dot]ac[dot]nz)

See Also:

Serialized Form

Nested Class Summary

Nested classes/interfaces inherited from class moa.classifiers.lazy.neighboursearch.NearestNeighbourSearch

NearestNeighbourSearch.MyHeap, NearestNeighbourSearch.MyHeapElement, NearestNeighbourSearch.NeighborList, NearestNeighbourSearch.NeighborNode

Field Summary

Fields

Modifier and Type	Field and Description
protected double[]	m_Distances Array holding the distances of the nearest neighbours.
protected boolean	m_SkipIdentical Whether to skip instances from the neighbours that are identical to the query instance.

Fields inherited from class moa.classifiers.lazy.neighboursearch.NearestNeighbourSearch

m_DistanceFunction, m_Instances, m_kNN, m_MeasurePerformance

Constructor Summary

Constructors

Constructor and Description
LinearNNSearch() Constructor.
LinearNNSearch(weka.core.Instances insts) Constructor that uses the supplied set of instances.

Method Summary

Methods

Modifier and Type	Method and Description
void	addInstanceInfo(weka.core.Instance ins) Adds the given instance info.
double[]	getDistances() Returns the distances of the k nearest neighbours.
boolean	getSkipIdentical() Gets whether if identical instances are skipped from the neighbourhood.
String	globalInfo() Returns a string describing this nearest neighbour search algorithm.
weka.core.Instances	kNearestNeighbours(weka.core.Instance target, int kNN) Returns k nearest instances in the current neighbourhood to the supplied instance.
weka.core.Instance	nearestNeighbour(weka.core.Instance target) Returns the nearest instance in the current neighbourhood to the supplied instance.
void	setInstances(weka.core.Instances insts) Sets the instances comprising the current neighbourhood.
void	setSkipIdentical(boolean skip) Sets the property to skip identical instances (with distance zero from the target) from the set of neighbours returned.
String	skipIdenticalTipText() Returns the tip text for this property.
void	update(weka.core.Instance ins) Updates the LinearNNSearch to cater for the new added instance.

Methods inherited from class moa.classifiers.lazy.neighboursearch.NearestNeighbourSearch

combSort11, distanceFunctionTipText, getDistanceFunction, getInstances, getMeasurePerformance, measurePerformanceTipText, partition, quickSort, setDistanceFunction

Methods inherited from class java.lang.Object

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

Field Detail

m_Distances

protected double[] m_Distances

Array holding the distances of the nearest neighbours. It is filled up both by nearestNeighbour() and kNearestNeighbours().

m_SkipIdentical

protected boolean m_SkipIdentical

Whether to skip instances from the neighbours that are identical to the query instance.

Constructor Detail

LinearNNSearch

public LinearNNSearch()

Constructor. Needs setInstances(Instances) to be called before the class is usable.

LinearNNSearch

public LinearNNSearch(weka.core.Instances insts)

Constructor that uses the supplied set of instances.

Parameters:

insts - the instances to use

Method Detail

globalInfo

public String globalInfo()

Returns a string describing this nearest neighbour search algorithm.

Overrides:

globalInfo in class NearestNeighbourSearch

Returns:

a description of the algorithm for displaying in the explorer/experimenter gui

skipIdenticalTipText

public String skipIdenticalTipText()

Returns the tip text for this property.

Returns:

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

setSkipIdentical

public void setSkipIdentical(boolean skip)

Sets the property to skip identical instances (with distance zero from the target) from the set of neighbours returned.

Parameters:

skip - if true, identical intances are skipped

getSkipIdentical

public boolean getSkipIdentical()

Gets whether if identical instances are skipped from the neighbourhood.

Returns:

true if identical instances are skipped

nearestNeighbour

public weka.core.Instance nearestNeighbour(weka.core.Instance target)
                                    throws Exception

Returns the nearest instance in the current neighbourhood to the supplied instance.

Specified by:

nearestNeighbour in class NearestNeighbourSearch

Parameters:

target - The instance to find the nearest neighbour for.

Returns:

the nearest instance

Throws:

Exception - if the nearest neighbour could not be found.

kNearestNeighbours

public weka.core.Instances kNearestNeighbours(weka.core.Instance target,
                                     int kNN)
                                       throws Exception

Returns k nearest instances in the current neighbourhood to the supplied instance.

Specified by:

kNearestNeighbours in class NearestNeighbourSearch

Parameters:

target - The instance to find the k nearest neighbours for.

kNN - The number of nearest neighbours to find.

Returns:

the k nearest neighbors

Throws:

Exception - if the neighbours could not be found.

getDistances

public double[] getDistances()
                      throws Exception

Returns the distances of the k nearest neighbours. The kNearestNeighbours or nearestNeighbour must always be called before calling this function. If this function is called before calling either the kNearestNeighbours or the nearestNeighbour, then it throws an exception. If, however, if either of the nearestNeighbour functions are called at any point in the past then no exception is thrown and the distances of the training set from the last supplied target instance (to either one of the nearestNeighbour functions) is/are returned.

Specified by:

getDistances in class NearestNeighbourSearch

Returns:

array containing the distances of the nearestNeighbours. The length and ordering of the array is the same as that of the instances returned by nearestNeighbour functions.

Throws:

Exception - if called before calling kNearestNeighbours or nearestNeighbours.

setInstances

public void setInstances(weka.core.Instances insts)
                  throws Exception

Sets the instances comprising the current neighbourhood.

Overrides:

setInstances in class NearestNeighbourSearch

Parameters:

insts - The set of instances on which the nearest neighbour search is carried out. Usually this set is the training set.

Throws:

Exception - if setting of instances fails

update

public void update(weka.core.Instance ins)
            throws Exception

Updates the LinearNNSearch to cater for the new added instance. This implementation only updates the ranges of the DistanceFunction class, since our set of instances is passed by reference and should already have the newly added instance.

Specified by:

update in class NearestNeighbourSearch

Parameters:

ins - The instance to add. Usually this is the instance that is added to our neighbourhood i.e. the training instances.

Throws:

Exception - if the given instances are null

addInstanceInfo

public void addInstanceInfo(weka.core.Instance ins)

Adds the given instance info. This implementation updates the range datastructures of the DistanceFunction class.

Overrides:

addInstanceInfo in class NearestNeighbourSearch

Parameters:

ins - The instance to add the information of. Usually this is the test instance supplied to update the range of attributes in the distance function.