org.simulator.math

Class QualityMeasure

java.lang.Object

org.simulator.math.QualityMeasure

All Implemented Interfaces:

Serializable

Direct Known Subclasses:

MaxAbsDistance, MaxDivergenceTolerance, N_Metric, PearsonCorrelation, Relative_N_Metric, RelativeMaxDistance

public abstract class QualityMeasure
extends Object
implements Serializable

This class is the basis of various implementations of distance functions.

Since:

1.0

Author:

Roland Keller, Andreas Dräger

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
QualityMeasure() Default constructor.
QualityMeasure(double defaultValue) Constructor, which allows setting the parameter value for default value.
QualityMeasure(double defaultValue, MeanFunction meanFunction) Constructor, which allows setting the parameter values for meanFunction and defaultValue.

Method Summary

Modifier and Type	Method and Description
double	distance(MultiTable.Block.Column x, MultiTable.Block.Column y) Returns the distance of the two vectors x and y where the currently set root is used.
abstract double	distance(MultiTable.Block.Column x, MultiTable.Block.Column y, double defaultValue) Returns the distance of the two vectors x and y with the given root.
double	distance(MultiTable x, MultiTable expected)
List<Double>	getColumnDistances(MultiTable x, MultiTable expected) Computes the distance of two matrices as the sum of the distances of each row.
double	getDefaultValue() Returns the default value that is returned by the distance function in cases in which the computation of the distance is not possible.
Map<String,Double>	getMaxAbsDistances(MultiTable x, MultiTable expected)
MeanFunction	getMeanFunction()
void	setDefaultValue(double defaultValue) Set the value to be returned by the distance function in cases, in which no distance can be computed.
void	setMeanFunction(MeanFunction meanFunction)

Methods inherited from class java.lang.Object

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

Constructor Detail

QualityMeasure

public QualityMeasure()

Default constructor. This sets the standard value for the parameter as given by the getStandardParameter() method. The default value is set to NaN.

QualityMeasure

public QualityMeasure(double defaultValue)

Constructor, which allows setting the parameter value for default value.

Parameters:

defaultValue -

QualityMeasure

public QualityMeasure(double defaultValue,
                      MeanFunction meanFunction)

Constructor, which allows setting the parameter values for meanFunction and defaultValue.

Parameters:

defaultValue -

meanFunction -

Method Detail

distance

public double distance(MultiTable.Block.Column x,
                       MultiTable.Block.Column y)

Returns the distance of the two vectors x and y where the currently set root is used. It is possible that one matrix contains more columns than the other one. If so, the additional values in the bigger matrix are ignored and do not contribute to the distance. NaN values do also not contribute to the distance.

Parameters:

x -

y -

Returns:

distance the distance between the two vectors

Throws:

IllegalArgumentException

distance

public abstract double distance(MultiTable.Block.Column x,
                                MultiTable.Block.Column y,
                                double defaultValue)

Returns the distance of the two vectors x and y with the given root. This may be the root in a formal way or a default value to be returned if the distance uses a non defined operation. If one array is longer than the other one additional values do not contribute to the distance. Double.NaN values are also ignored.

Parameters:

x - an array

y - another array

defaultValue - The value to be returned in cases in which no distance computation is possible.

Returns:

The distance between the two arrays x and y.

Throws:

IllegalArgumentException

distance

public double distance(MultiTable x,
                       MultiTable expected)

Parameters:

x -

expected -

Returns:

distance the distance between the two tables

getColumnDistances

public List<Double> getColumnDistances(MultiTable x,
                                       MultiTable expected)

Computes the distance of two matrices as the sum of the distances of each row. It is possible that one matrix contains more columns than the other one. If so, the additional values in the bigger matrix are ignored and do not contribute to the distance. Double.NaN values do also not contribute to the distance. Only columns with matching identifiers are considered for the distance computation.

Parameters:

x -

expected -

Returns:

columnDistances the list of distances for the columns in the blocks

getMaxAbsDistances

public Map<String,Double> getMaxAbsDistances(MultiTable x,
                                             MultiTable expected)

Parameters:

x -

expected -

Returns:

maxAbsDistances the list of maximum absolute distances in the blocks

getDefaultValue

public double getDefaultValue()

Returns the default value that is returned by the distance function in cases in which the computation of the distance is not possible.

Returns:

defaultValue

getMeanFunction

public final MeanFunction getMeanFunction()

Returns:

the meanFunction

setDefaultValue

public void setDefaultValue(double defaultValue)

Set the value to be returned by the distance function in cases, in which no distance can be computed.

Parameters:

defaultValue -

setMeanFunction

public final void setMeanFunction(MeanFunction meanFunction)

Parameters:

meanFunction - the meanFunction to set