Package elki.clustering.trivial

Class ByLabelClustering

java.lang.Object

elki.clustering.trivial.ByLabelClustering

All Implemented Interfaces:

Algorithm, ClusteringAlgorithm<Clustering<Model>>

Direct Known Subclasses:

ByLabelOrAllInOneClustering

@Title("Clustering by label")
@Description("Cluster points by a (pre-assigned!) label. For comparing results with a reference clustering.")
@Priority(-100)
public class ByLabelClustering
extends java.lang.Object
implements ClusteringAlgorithm<Clustering<Model>>

Pseudo clustering using labels.

This "algorithm" puts elements into the same cluster when they agree in their labels. I.e. it just uses a predefined clustering, and is mostly useful for testing and evaluation (e.g., comparing the result of a real algorithm to a reference result / golden standard).

If an assignment of an object to multiple clusters is desired, the labels of the object indicating the clusters need to be separated by blanks and the flag ByLabelClustering.Par.MULTIPLE_ID needs to be set.

TODO: handling of data sets with no labels?

Since:

0.2

Author:

Erich Schubert

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	ByLabelClustering.Par	Parameterization class.

Nested classes/interfaces inherited from interface elki.Algorithm

Algorithm.Utils

Field Summary

Fields

Modifier and Type	Field	Description
private boolean	multiple	Allow multiple cluster assignment.
private java.util.regex.Pattern	noisepattern	Pattern to recognize noise clusters by.

Constructor Summary

Constructors

Constructor	Description
ByLabelClustering()	Constructor without parameters
ByLabelClustering(boolean multiple, java.util.regex.Pattern noisepattern)	Constructor.

Method Summary

Modifier and Type	Method	Description
private void	assign(java.util.HashMap<java.lang.String,DBIDs> labelMap, java.lang.String label, DBIDRef id)	Assigns the specified id to the labelMap according to its label
Clustering<Model>	autorun(Database database)	Try to auto-run the algorithm on a database by calling a method called run, with an optional Database first, and with data relations as specified by Algorithm.getInputTypeRestriction().
TypeInformation[]	getInputTypeRestriction()	Get the input type restriction used for negotiating the data query.
private java.util.HashMap<java.lang.String,DBIDs>	multipleAssignment(Relation<?> data)	Assigns the objects of the database to multiple clusters according to their labels.
Clustering<Model>	run(Relation<?> relation)	Run the actual clustering algorithm.
private java.util.HashMap<java.lang.String,DBIDs>	singleAssignment(Relation<?> data)	Assigns the objects of the database to single clusters according to their labels.

Methods inherited from class java.lang.Object

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

Field Detail

multiple

private boolean multiple

Allow multiple cluster assignment.

noisepattern

private java.util.regex.Pattern noisepattern

Pattern to recognize noise clusters by.

Constructor Detail

ByLabelClustering

public ByLabelClustering(boolean multiple,
                         java.util.regex.Pattern noisepattern)

Constructor.

Parameters:

multiple - Allow multiple cluster assignments

noisepattern - Noise pattern

ByLabelClustering

public ByLabelClustering()

Constructor without parameters

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

autorun

public Clustering<Model> autorun(Database database)

Description copied from interface: Algorithm

Try to auto-run the algorithm on a database by calling a method called run, with an optional Database first, and with data relations as specified by Algorithm.getInputTypeRestriction().

Specified by:

autorun in interface Algorithm

Specified by:

autorun in interface ClusteringAlgorithm<Clustering<Model>>

Parameters:

database - the database to run the algorithm on

Returns:

the Result computed by this algorithm

run

public Clustering<Model> run(Relation<?> relation)

Run the actual clustering algorithm.

Parameters:

relation - The data input we use

singleAssignment

private java.util.HashMap<java.lang.String,DBIDs> singleAssignment(Relation<?> data)

Assigns the objects of the database to single clusters according to their labels.

Parameters:

data - the database storing the objects

Returns:

a mapping of labels to ids

multipleAssignment

private java.util.HashMap<java.lang.String,DBIDs> multipleAssignment(Relation<?> data)

Assigns the objects of the database to multiple clusters according to their labels.

Parameters:

data - the database storing the objects

Returns:

a mapping of labels to ids

assign

private void assign(java.util.HashMap<java.lang.String,DBIDs> labelMap,
                    java.lang.String label,
                    DBIDRef id)

Assigns the specified id to the labelMap according to its label

Parameters:

labelMap - the mapping of label to ids

label - the label of the object to be assigned

id - the id of the object to be assigned