de.lmu.ifi.dbs.elki.preprocessing
Class DiSHPreprocessor<V extends NumberVector<V,?>>

java.lang.Object
  de.lmu.ifi.dbs.elki.logging.AbstractLoggable
      de.lmu.ifi.dbs.elki.preprocessing.DiSHPreprocessor<V>

Type Parameters:

V - Vector type

All Implemented Interfaces:

PreferenceVectorPreprocessor<V>, Preprocessor<V>, Parameterizable

@Description(value="Computes the preference vector of objects of a certain database according to the DiSH algorithm.")
public class DiSHPreprocessor<V extends NumberVector<V,?>>
extends AbstractLoggable
implements PreferenceVectorPreprocessor<V>, Parameterizable

Preprocessor for DiSH preference vector assignment to objects of a certain database.

Author:

Elke Achtert

Nested Class Summary

static class

DiSHPreprocessor.Strategy Available strategies for determination of the preference vector.

Field Summary

private static String	CONDITION Description for the determination of the preference vector.
static DoubleDistance	DEFAULT_EPSILON The default value for epsilon.
static DiSHPreprocessor.Strategy	DEFAULT_STRATEGY Default strategy.
private DoubleDistance[]	epsilon The epsilon value for each dimension;
static OptionID	EPSILON_ID OptionID for EPSILON_PARAM
protected DoubleListParameter	EPSILON_PARAM A comma separated list of positive doubles specifying the maximum radius of the neighborhood to be considered in each dimension for determination of the preference vector (default is DEFAULT_EPSILON in each dimension).
private int	minpts Threshold for minimum number of points in the neighborhood.
static OptionID	MINPTS_ID OptionID for MINPTS_PARAM
static String	MINPTS_P Option name for MINPTS_ID.
protected IntParameter	MINPTS_PARAM Positive threshold for minimum numbers of points in the epsilon-neighborhood of a point, must satisfy following CONDITION.
private DiSHPreprocessor.Strategy	strategy The strategy to determine the preference vector.
static OptionID	STRATEGY_ID OptionID for STRATEGY_PARAM
private StringParameter	STRATEGY_PARAM The strategy for determination of the preference vector, available strategies are: DiSHPreprocessor.Strategy.APRIORI and DiSHPreprocessor.Strategy.MAX_INTERSECTION.

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

debug, logger

Constructor Summary

DiSHPreprocessor(Parameterization config)
Constructor, adhering to Parameterizable

Method Summary

private BitSet	determinePreferenceVector(Database<V> database, Set<Integer>[] neighborIDs, StringBuffer msg) Determines the preference vector according to the specified neighbor ids.
private BitSet	determinePreferenceVectorByApriori(Database<V> database, Set<Integer>[] neighborIDs, StringBuffer msg) Determines the preference vector with the apriori strategy.
private BitSet	determinePreferenceVectorByMaxIntersection(Set<Integer>[] neighborIDs, StringBuffer msg) Determines the preference vector with the max intersection strategy.
DoubleDistance[]	getEpsilon() Returns the value of the epsilon parameter.
int	getMinpts() Returns minpts.
private DimensionSelectingDistanceFunction<V>[]	initDistanceFunctions(Database<V> database, int dimensionality) Initializes the dimension selecting distancefunctions to determine the preference vectors.
private int	max(Map<Integer,Set<Integer>> candidates) Returns the set with the maximum size contained in the specified map.
private int	maxIntersection(Map<Integer,Set<Integer>> candidates, Set<Integer> set, Set<Integer> result) Returns the index of the set having the maximum intersection set with the specified set contained in the specified map.
void	run(Database<V> database, boolean verbose, boolean time) This method executes the particular preprocessing step of this Preprocessor for the objects of the specified database.

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

Field Detail

DEFAULT_EPSILON

public static final DoubleDistance DEFAULT_EPSILON

The default value for epsilon.

EPSILON_ID

public static final OptionID EPSILON_ID

OptionID for EPSILON_PARAM

MINPTS_P

public static final String MINPTS_P

Option name for MINPTS_ID.

See Also:

Constant Field Values

CONDITION

private static final String CONDITION

Description for the determination of the preference vector.

See Also:

Constant Field Values

MINPTS_ID

public static final OptionID MINPTS_ID

OptionID for MINPTS_PARAM

DEFAULT_STRATEGY

public static DiSHPreprocessor.Strategy DEFAULT_STRATEGY

Default strategy.

STRATEGY_ID

public static final OptionID STRATEGY_ID

OptionID for STRATEGY_PARAM

EPSILON_PARAM

protected final DoubleListParameter EPSILON_PARAM

A comma separated list of positive doubles specifying the maximum radius of the neighborhood to be considered in each dimension for determination of the preference vector (default is DEFAULT_EPSILON in each dimension). If only one value is specified, this value will be used for each dimension.

Key: -dish.epsilon

Default value: DEFAULT_EPSILON

epsilon

private DoubleDistance[] epsilon

The epsilon value for each dimension;

MINPTS_PARAM

protected final IntParameter MINPTS_PARAM

Positive threshold for minimum numbers of points in the epsilon-neighborhood of a point, must satisfy following CONDITION.

Key: -dish.minpts

minpts

private int minpts

Threshold for minimum number of points in the neighborhood.

STRATEGY_PARAM

private final StringParameter STRATEGY_PARAM

The strategy for determination of the preference vector, available strategies are: DiSHPreprocessor.Strategy.APRIORI and DiSHPreprocessor.Strategy.MAX_INTERSECTION.

Key: -dish.strategy

Default value: DEFAULT_STRATEGY

strategy

private DiSHPreprocessor.Strategy strategy

The strategy to determine the preference vector.

Constructor Detail

DiSHPreprocessor

public DiSHPreprocessor(Parameterization config)

Constructor, adhering to Parameterizable

Parameters:

config - Parameterization

Method Detail

run

public void run(Database<V> database,
                boolean verbose,
                boolean time)

Description copied from interface: Preprocessor

This method executes the particular preprocessing step of this Preprocessor for the objects of the specified database.

Specified by:

run in interface Preprocessor<V extends NumberVector<V,?>>

Parameters:

database - the database for which the preprocessing is performed

verbose - flag to allow verbose messages while performing the algorithm

time - flag to request output of performance time

determinePreferenceVector

private BitSet determinePreferenceVector(Database<V> database,
                                         Set<Integer>[] neighborIDs,
                                         StringBuffer msg)
                                  throws ParameterException,
                                         UnableToComplyException

Determines the preference vector according to the specified neighbor ids.

Parameters:

database - the database storing the objects

neighborIDs - the list of ids of the neighbors in each dimension

msg - a string buffer for debug messages

Returns:

the preference vector

Throws:

ParameterException

UnableToComplyException

determinePreferenceVectorByApriori

private BitSet determinePreferenceVectorByApriori(Database<V> database,
                                                  Set<Integer>[] neighborIDs,
                                                  StringBuffer msg)
                                           throws ParameterException,
                                                  UnableToComplyException

Determines the preference vector with the apriori strategy.

Parameters:

database - the database storing the objects

neighborIDs - the list of ids of the neighbors in each dimension

msg - a string buffer for debug messages

Returns:

the preference vector

Throws:

ParameterException

UnableToComplyException

determinePreferenceVectorByMaxIntersection

private BitSet determinePreferenceVectorByMaxIntersection(Set<Integer>[] neighborIDs,
                                                          StringBuffer msg)

Determines the preference vector with the max intersection strategy.

Parameters:

neighborIDs - the list of ids of the neighbors in each dimension

msg - a string buffer for debug messages

Returns:

the preference vector

max

private int max(Map<Integer,Set<Integer>> candidates)

Returns the set with the maximum size contained in the specified map.

Parameters:

candidates - the map containing the sets

Returns:

the set with the maximum size

maxIntersection

private int maxIntersection(Map<Integer,Set<Integer>> candidates,
                            Set<Integer> set,
                            Set<Integer> result)

Returns the index of the set having the maximum intersection set with the specified set contained in the specified map.

Parameters:

candidates - the map containing the sets

set - the set to intersect with

result - the set to put the result in

Returns:

the set with the maximum size

initDistanceFunctions

private DimensionSelectingDistanceFunction<V>[] initDistanceFunctions(Database<V> database,
                                                                      int dimensionality)
                                                                                         throws ParameterException

Initializes the dimension selecting distancefunctions to determine the preference vectors.

Parameters:

database - the database storing the objects

dimensionality - the dimensionality of the objects

Returns:

the dimension selecting distancefunctions to determine the preference vectors

Throws:

ParameterException

getEpsilon

public DoubleDistance[] getEpsilon()

Returns the value of the epsilon parameter.

Returns:

the value of the epsilon parameter

getMinpts

public int getMinpts()

Returns minpts.

Returns:

minpts