public class TopKOutlierScaling extends Object implements OutlierScalingFunction
Modifier and Type | Class and Description |
---|---|
static class |
TopKOutlierScaling.Parameterizer
Parameterization class.
|
Modifier and Type | Field and Description |
---|---|
private boolean |
binary
Do a binary decision
|
static OptionID |
BINARY_ID
Parameter to specify the lambda value
Key:
-topk.binary
|
private double |
cutoff
The value we cut off at.
|
private double |
ground
The "ground" value
|
private int |
k
Number of outliers to keep.
|
static OptionID |
K_ID
Parameter to specify the number of outliers to keep
Key:
-topk.k
|
private double |
max
The maximum value
|
Constructor and Description |
---|
TopKOutlierScaling(int k,
boolean binary)
Constructor.
|
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.
|
<A> void |
prepare(A array,
NumberArrayAdapter<?,A> adapter)
Prepare is called once for each data set, before getScaled() will be
called.
|
void |
prepare(OutlierResult or)
Prepare is called once for each data set, before getScaled() will be
called.
|
public static final OptionID K_ID
Key: -topk.k
public static final OptionID BINARY_ID
Key: -topk.binary
private int k
private boolean binary
private double cutoff
private double ground
private double max
public TopKOutlierScaling(int k, boolean binary)
k
- binary
- public void prepare(OutlierResult or)
OutlierScalingFunction
prepare
in interface OutlierScalingFunction
or
- Outlier result to usepublic <A> void prepare(A array, NumberArrayAdapter<?,A> adapter)
OutlierScalingFunction
OutlierResult
is preferred, as it will
allow access to the metadata.prepare
in interface OutlierScalingFunction
array
- Data to processadapter
- Array adapterpublic double getMax()
ScalingFunction
Double.NaN
or
Double.POSITIVE_INFINITY
.getMax
in interface ScalingFunction
public double getMin()
ScalingFunction
Double.NaN
or
Double.NEGATIVE_INFINITY
.getMin
in interface ScalingFunction
public double getScaled(double value)
ScalingFunction
getScaled
in interface ScalingFunction
value
- Original valueCopyright © 2015 ELKI Development Team, Lehr- und Forschungseinheit für Datenbanksysteme, Ludwig-Maximilians-Universität München. License information.