de.lmu.ifi.dbs.elki.utilities.scaling.outlier

Class OutlierGammaScaling

java.lang.Object

de.lmu.ifi.dbs.elki.utilities.scaling.outlier.OutlierGammaScaling

All Implemented Interfaces:

InspectionUtilFrequentlyScanned, Parameterizable, OutlierScalingFunction, ScalingFunction

Direct Known Subclasses:

MinusLogGammaScaling

@Reference(authors="H.-P. Kriegel, P. Kr\u00f6ger, E. Schubert, A. Zimek",
           title="Interpreting and Unifying Outlier Scores",
           booktitle="Proc. 11th SIAM International Conference on Data Mining (SDM), Mesa, AZ, 2011",
           url="http://www.dbs.ifi.lmu.de/~zimek/publications/SDM2011/SDM11-outlier-preprint.pdf")
public class OutlierGammaScaling
extends Object
implements OutlierScalingFunction

Scaling that can map arbitrary values to a probability in the range of [0:1] by assuming a Gamma distribution on the values.

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	OutlierGammaScaling.Parameterizer Parameterization class.

Field Summary

Fields

Modifier and Type	Field and Description
(package private) double	atmean Score at the mean, for cut-off.
(package private) double	k Gamma parameter k
(package private) OutlierScoreMeta	meta Keep a reference to the outlier score meta, for normalization.
(package private) boolean	normalize Store flag to Normalize data before curve fitting.
static OptionID	NORMALIZE_ID Normalization flag.
(package private) double	theta Gamma parameter theta

Constructor Summary

Constructors

Constructor and Description
OutlierGammaScaling(boolean normalize) Constructor.

Method Summary

Methods

Modifier and Type	Method and Description
double	getMax() Get maximum resulting value.
double	getMin() Get minimum resulting value.
double	getScaled(double value) Transform a given value using the scaling function.
void	prepare(OutlierResult or) Prepare is called once for each data set, before getScaled() will be called.
protected double	preScale(double score) Normalize data if necessary.

Methods inherited from class java.lang.Object

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

Field Detail

NORMALIZE_ID

public static final OptionID NORMALIZE_ID

Normalization flag.

 -gammascale.normalize
 

k

double k

Gamma parameter k

theta

double theta

Gamma parameter theta

atmean

double atmean

Score at the mean, for cut-off.

normalize

boolean normalize

Store flag to Normalize data before curve fitting.

meta

OutlierScoreMeta meta

Keep a reference to the outlier score meta, for normalization.

Constructor Detail

OutlierGammaScaling

public OutlierGammaScaling(boolean normalize)

Constructor.

Parameters:

normalize - Normalization flag

Method Detail

getScaled

public double getScaled(double value)

Description copied from interface: ScalingFunction

Transform a given value using the scaling function.

Specified by:

getScaled in interface ScalingFunction

Parameters:

value - Original value

Returns:

Scaled value

prepare

public void prepare(OutlierResult or)

Description copied from interface: OutlierScalingFunction

Prepare is called once for each data set, before getScaled() will be called. This function can be used to extract global parameters such as means, minimums or maximums from the Database, Result or Annotation.

Specified by:

prepare in interface OutlierScalingFunction

Parameters:

or - Outlier result to use

preScale

protected double preScale(double score)

Normalize data if necessary. Note: this is overridden by MinusLogGammaScaling!

Parameters:

score - Original score

Returns:

Normalized score.

getMin

public double getMin()

Description copied from interface: ScalingFunction

Get minimum resulting value. May be Double.NaN or Double.NEGATIVE_INFINITY.

Specified by:

getMin in interface ScalingFunction

Returns:

Minimum resulting value.

getMax

public double getMax()

Description copied from interface: ScalingFunction

Get maximum resulting value. May be Double.NaN or Double.POSITIVE_INFINITY.

Specified by:

getMax in interface ScalingFunction

Returns:

Maximum resulting value.