Package elki.application.greedyensemble

Class ComputeKNNOutlierScores<O extends NumberVector>

java.lang.Object

elki.application.AbstractApplication

elki.application.AbstractDistanceBasedApplication<O>

elki.application.greedyensemble.ComputeKNNOutlierScores<O>

Type Parameters:

O - Vector type

@Reference(authors="Erich Schubert, Remigius Wojdanowski, Arthur Zimek, Hans-Peter Kriegel",
           title="On Evaluation of Outlier Rankings and Outlier Scores",
           booktitle="Proc. 12th SIAM Int. Conf. on Data Mining (SDM 2012)",
           url="https://doi.org/10.1137/1.9781611972825.90",
           bibkey="DBLP:conf/sdm/SchubertWZK12")
public class ComputeKNNOutlierScores<O extends NumberVector>
extends AbstractDistanceBasedApplication<O>

Application that runs a series of kNN-based algorithms on a data set, for building an ensemble in a second step. The output file consists of a label and one score value for each object.

Since some algorithms can be too slow to run on large data sets and for large values of k, they can be disabled. For example -disable '(LDOF|DWOF|COF|FastABOD)' disables these two methods completely. Alternatively, you can use the parameter -ksquaremax to control the maximum k for these four methods separately.

For methods where k=1 does not make sense, this value will be skipped, and the procedure will commence at 1+stepsize.

Reference:

Erich Schubert, Remigius Wojdanowski, Arthur Zimek, Hans-Peter Kriegel
On Evaluation of Outlier Rankings and Outlier Scores
Proc. 12th SIAM Int. Conf. on Data Mining (SDM 2012)

Since:

0.5.0

Author:

Erich Schubert

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	ComputeKNNOutlierScores.Par<O extends NumberVector>	Parameterization class.
private static class	ComputeKNNOutlierScores.TimeoutException	Exception used in timeout logic.

Field Summary

Fields

Modifier and Type	Field	Description
(package private) ByLabelOutlier	bylabel	By label outlier detection - reference
(package private) java.util.regex.Pattern	disable	Pattern for disabling (skipping) methods.
(package private) IntGenerator	krange	Range of k.
(package private) int	ksquarestop	Maximum k for O(k^2) methods.
private static Logging	LOG	Our logger class.
(package private) java.nio.file.Path	outfile	Output file
(package private) ScalingFunction	scaling	Scaling function.
(package private) long	timelimit	Timelimit for computation (not strictly enforced).

Fields inherited from class elki.application.AbstractDistanceBasedApplication

distance, inputstep

Fields inherited from class elki.application.AbstractApplication

REFERENCE, VERSION

Constructor Summary

Constructors

Constructor	Description
ComputeKNNOutlierScores(InputStep inputstep, Distance<? super O> distance, IntGenerator krange, ByLabelOutlier bylabel, java.nio.file.Path outfile, ScalingFunction scaling, java.util.regex.Pattern disable, int ksquarestop, long timelimit)	Constructor.

Method Summary

Modifier and Type	Method	Description
protected boolean	isDisabled(java.lang.String name)	Test if a given algorithm is disabled.
static void	main(java.lang.String[] args)	Main method.
void	run()	Runs the application.
private void	runForEachK(java.lang.String prefix, int mink, int maxk, java.util.function.IntFunction<OutlierResult> runner, java.util.function.BiConsumer<java.lang.String,OutlierResult> out)	Iterate over the k range.
(package private) void	writeResult(java.lang.Appendable out, DBIDs ids, OutlierResult result, ScalingFunction scaling, java.lang.String label)	Write a single output line.

Methods inherited from class elki.application.AbstractApplication

printErrorMessage, runCLIApplication, usage

Methods inherited from class java.lang.Object

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

Field Detail

LOG

private static final Logging LOG

Our logger class.

krange

final IntGenerator krange

Range of k.

outfile

java.nio.file.Path outfile

Output file

bylabel

ByLabelOutlier bylabel

By label outlier detection - reference

scaling

ScalingFunction scaling

Scaling function.

disable

java.util.regex.Pattern disable

Pattern for disabling (skipping) methods.

ksquarestop

int ksquarestop

Maximum k for O(k^2) methods.

timelimit

long timelimit

Timelimit for computation (not strictly enforced). In ms.

Constructor Detail

ComputeKNNOutlierScores

public ComputeKNNOutlierScores(InputStep inputstep,
                               Distance<? super O> distance,
                               IntGenerator krange,
                               ByLabelOutlier bylabel,
                               java.nio.file.Path outfile,
                               ScalingFunction scaling,
                               java.util.regex.Pattern disable,
                               int ksquarestop,
                               long timelimit)

Constructor.

Parameters:

inputstep - Input step

distance - Distance function

krange - K parameter range

bylabel - By label outlier (reference)

outfile - Output file

scaling - Scaling function

disable - Pattern for disabling methods

ksquarestop - Maximum k for O(k^2) methods

timelimit - Time limit in seconds

Method Detail

run

public void run()

Description copied from class: AbstractApplication

Runs the application.

Specified by:

run in class AbstractApplication

writeResult

void writeResult(java.lang.Appendable out,
                 DBIDs ids,
                 OutlierResult result,
                 ScalingFunction scaling,
                 java.lang.String label)

Write a single output line.

Parameters:

out - Output stream

ids - DBIDs

result - Outlier result

scaling - Scaling function

label - Identification label

runForEachK

private void runForEachK(java.lang.String prefix,
                         int mink,
                         int maxk,
                         java.util.function.IntFunction<OutlierResult> runner,
                         java.util.function.BiConsumer<java.lang.String,OutlierResult> out)

Iterate over the k range.

Parameters:

prefix - Prefix string

mink - Minimum value of k for this method

maxk - Maximum value of k for this method

runner - Runner to run

out - Output function

isDisabled

protected boolean isDisabled(java.lang.String name)

Test if a given algorithm is disabled.

Parameters:

name - Algorithm name

Returns:

true if disabled

main

public static void main(java.lang.String[] args)

Main method.

Parameters:

args - Command line parameters.