de.lmu.ifi.dbs.elki.algorithm.clustering
Class ByLabelClustering<O extends DatabaseObject>

java.lang.Object
  de.lmu.ifi.dbs.elki.logging.AbstractLoggable
      de.lmu.ifi.dbs.elki.algorithm.AbstractAlgorithm<O,Clustering<Model>>
          de.lmu.ifi.dbs.elki.algorithm.clustering.ByLabelClustering<O>

Type Parameters:

O - Object type

All Implemented Interfaces:

Algorithm<O,Clustering<Model>>, ClusteringAlgorithm<Clustering<Model>,O>, Parameterizable

@Title(value="Clustering by label")
@Description(value="Cluster points by a (pre-assigned!) label. For comparing results with a reference clustering.")
public class ByLabelClustering<O extends DatabaseObject>
extends AbstractAlgorithm<O,Clustering<Model>>
implements ClusteringAlgorithm<Clustering<Model>,O>

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 MULTIPLE_FLAG needs to be set. TODO: handling of data sets with no labels? TODO: Noise handling (e.g. allow the user to specify a noise label pattern?)

Author:

Erich Schubert

Field Summary

private boolean	multiple Holds the value of MULTIPLE_FLAG.
private Flag	MULTIPLE_FLAG Flag to indicate that multiple cluster assignment is possible.
static OptionID	MULTIPLE_ID OptionID for MULTIPLE_FLAG

Fields inherited from class de.lmu.ifi.dbs.elki.logging.AbstractLoggable

debug, logger

Constructor Summary

ByLabelClustering()
Constructor without parameters

ByLabelClustering(Parameterization config)
Constructor, adhering to Parameterizable

Method Summary

private void	assign(HashMap<String,Collection<Integer>> labelMap, String label, Integer id) Assigns the specified id to the labelMap according to its label
private HashMap<String,Collection<Integer>>	multipleAssignment(Database<O> database) Assigns the objects of the database to multiple clusters according to their labels.
protected Clustering<Model>	runInTime(Database<O> database) Run the actual clustering algorithm.
void	setMultiple(boolean multiple) Sets the multiple flag to indicate that a multiple cluster assignment is possible.
private HashMap<String,Collection<Integer>>	singleAssignment(Database<O> database) Assigns the objects of the database to single clusters according to their labels.

Methods inherited from class de.lmu.ifi.dbs.elki.algorithm.AbstractAlgorithm

isTime, isVerbose, run, setTime, setVerbose

Methods inherited from class de.lmu.ifi.dbs.elki.logging.AbstractLoggable

debugFine, debugFiner, debugFinest, exception, progress, verbose, warning

Methods inherited from class java.lang.Object

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

Methods inherited from interface de.lmu.ifi.dbs.elki.algorithm.clustering.ClusteringAlgorithm

run

Methods inherited from interface de.lmu.ifi.dbs.elki.algorithm.Algorithm

setTime, setVerbose

Field Detail

MULTIPLE_ID

public static final OptionID MULTIPLE_ID

OptionID for MULTIPLE_FLAG

MULTIPLE_FLAG

private final Flag MULTIPLE_FLAG

Flag to indicate that multiple cluster assignment is possible. If an assignment to multiple clusters is desired, the labels indicating the clusters need to be separated by blanks.

Key: -clique.prune

multiple

private boolean multiple

Holds the value of MULTIPLE_FLAG.

Constructor Detail

ByLabelClustering

public ByLabelClustering(Parameterization config)

Constructor, adhering to Parameterizable

Parameters:

config - Parameterization

ByLabelClustering

public ByLabelClustering()

Constructor without parameters

Method Detail

runInTime

protected Clustering<Model> runInTime(Database<O> database)
                               throws IllegalStateException

Run the actual clustering algorithm.

Specified by:

runInTime in class AbstractAlgorithm<O extends DatabaseObject,Clustering<Model>>

Parameters:

database - The database to process

Returns:

the Result computed by this algorithm

Throws:

IllegalStateException - if the algorithm has not been initialized properly (e.g. the setParameters(String[]) method has been failed to be called).

singleAssignment

private HashMap<String,Collection<Integer>> singleAssignment(Database<O> database)

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

Parameters:

database - the database storing the objects

Returns:

a mapping of labels to ids

multipleAssignment

private HashMap<String,Collection<Integer>> multipleAssignment(Database<O> database)

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

Parameters:

database - the database storing the objects

Returns:

a mapping of labels to ids

assign

private void assign(HashMap<String,Collection<Integer>> labelMap,
                    String label,
                    Integer 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

setMultiple

public void setMultiple(boolean multiple)

Sets the multiple flag to indicate that a multiple cluster assignment is possible.

Parameters:

multiple - the flag to be set