Package elki.classification

Class KNNClassifier<O>

java.lang.Object

elki.classification.KNNClassifier<O>

Type Parameters:

O - the type of objects handled by this algorithm

All Implemented Interfaces:

Algorithm, Classifier<O>

@Title("kNN-classifier")
@Description("Lazy classifier classifies a given instance to the majority class of the k-nearest neighbors.")
@Priority(100)
public class KNNClassifier<O>
extends java.lang.Object
implements Classifier<O>

KNNClassifier classifies instances based on the class distribution among the k nearest neighbors in a database.

Since:

0.7.0

Author:

Arthur Zimek

Nested Class Summary

Nested classes/interfaces inherited from interface elki.Algorithm

Algorithm.Utils

Field Summary

Fields

Modifier and Type	Field	Description
protected Distance<? super O>	distance	Distance function
protected int	k	Holds the value of @link #K_PARAM}.
protected KNNSearcher<O>	knnq	kNN query class.
protected Relation<? extends ClassLabel>	labelrep	Class label representation.

Constructor Summary

Constructors

Constructor	Description
KNNClassifier(Distance<? super O> distance, int k)	Constructor.

Method Summary

Modifier and Type	Method	Description
void	buildClassifier(Database database, Relation<? extends ClassLabel> labels)	Performs the training.
ClassLabel	classify(O instance)	Classify a single instance.
double[]	classProbabilities(O instance, java.util.ArrayList<ClassLabel> labels)
Distance<? super O>	getDistance()	Returns the distance.
TypeInformation[]	getInputTypeRestriction()	Get the input type restriction used for negotiating the data query.
java.lang.String	model()	Produce a String representation of the classification model.

Methods inherited from class java.lang.Object

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

Methods inherited from interface elki.Algorithm

autorun

Field Detail

k

protected int k

Holds the value of @link #K_PARAM}.

knnq

protected KNNSearcher<O> knnq

kNN query class.

labelrep

protected Relation<? extends ClassLabel> labelrep

Class label representation.

distance

protected Distance<? super O> distance

Distance function

Constructor Detail

KNNClassifier

public KNNClassifier(Distance<? super O> distance,
                     int k)

Constructor.

Parameters:

distance - Distance function

k - Number of nearest neighbors to access.

Method Detail

getInputTypeRestriction

public TypeInformation[] getInputTypeRestriction()

Description copied from interface: Algorithm

Get the input type restriction used for negotiating the data query.

Specified by:

getInputTypeRestriction in interface Algorithm

Returns:

Type restriction

buildClassifier

public void buildClassifier(Database database,
                            Relation<? extends ClassLabel> labels)

Description copied from interface: Classifier

Performs the training. Sets available labels.

Specified by:

buildClassifier in interface Classifier<O>

Parameters:

database - the database to build the model on

labels - the classes to be learned

classify

public ClassLabel classify(O instance)

Description copied from interface: Classifier

Classify a single instance.

Specified by:

classify in interface Classifier<O>

Parameters:

instance - an instance to classify

Returns:

predicted class label of the given instance

classProbabilities

public double[] classProbabilities(O instance,
                                   java.util.ArrayList<ClassLabel> labels)

model

public java.lang.String model()

Description copied from interface: Classifier

Produce a String representation of the classification model.

Specified by:

model in interface Classifier<O>

Returns:

a String representation of the classification model

getDistance

public Distance<? super O> getDistance()

Returns the distance.

Returns:

the distance