de.lmu.ifi.dbs.elki.data.uncertain

Class WeightedDiscreteUncertainObject

java.lang.Object

de.lmu.ifi.dbs.elki.data.uncertain.AbstractUncertainObject

de.lmu.ifi.dbs.elki.data.uncertain.WeightedDiscreteUncertainObject

All Implemented Interfaces:

FeatureVector<Double>, SpatialComparable, DiscreteUncertainObject, UncertainObject

@Reference(authors="O. Benjelloun, A. D. Sarma, A. Halevy, J. Widom",
           title="ULDBs: Databases with uncertainty and lineage",
           booktitle="Proc. of the 32nd international conference on Very Large Data Bases (VLDB)",
           url="http://www.vldb.org/conf/2006/p953-benjelloun.pdf")
public class WeightedDiscreteUncertainObject
extends AbstractUncertainObject
implements DiscreteUncertainObject

Weighted version of discrete uncertain objects.

• Every object is represented by a finite number of discrete samples.
• Every sample has a weight associated with it.
• Samples with higher weight are more likely to be returned by drawSample(java.util.Random).

This is called the block independent-disjoint (BID model) in:

N. Dalvi, C. Ré, D. Suciu
Probabilistic databases: diamonds in the dirt
Communications of the ACM 52, 7

This is also known as the X-Tuple model in:

O. Benjelloun, A. D. Sarma, A. Halevy, J. Widom
ULDBs: Databases with uncertainty and lineage
In Proc. of the 32nd international conference on Very Large Data Bases (VLDB)

If only a single sample is provided, this can be used to model existential uncertainty as in:

N. Dalvi, D. Suciu
Efficient query evaluation on probabilistic databases.
The VLDB Journal, 16(4)

and:

T. Bernecker, H.-P. Kriegel, M. Renz, F. Verhein, A. Züfle
Probabilistic frequent itemset mining in uncertain databases.
In Proc. 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.

Author:

Alexander Koos, Erich Schubert

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
private static class	WeightedDiscreteUncertainObject.Factory Factory class for this data type.

Field Summary

Fields

Modifier and Type	Field and Description
static FeatureVector.Factory<WeightedDiscreteUncertainObject,?>	FACTORY Vector factory.
private DoubleVector[]	samples Samples
private double[]	weights Sample weights

Fields inherited from class de.lmu.ifi.dbs.elki.data.uncertain.AbstractUncertainObject

bounds, DEFAULT_TRY_LIMIT

Constructor Summary

Constructors

Constructor and Description
WeightedDiscreteUncertainObject(DoubleVector[] samples, double[] weights) Constructor.

Method Summary

Methods

Modifier and Type	Method and Description
DoubleVector	drawSample(Random rand) Draw a random sampled instance.
DoubleVector	getCenterOfMass() Get the center of mass of the uncertain object.
int	getNumberSamples() Get the number of samples available (or -1 for infinite).
DoubleVector	getSample(int i) Get the i'th vector.
double	getWeight(int i) Get the weight of the i'th vector.

Methods inherited from class de.lmu.ifi.dbs.elki.data.uncertain.AbstractUncertainObject

computeBounds, getDimensionality, getMax, getMin, getValue

Methods inherited from class java.lang.Object

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

Methods inherited from interface de.lmu.ifi.dbs.elki.data.spatial.SpatialComparable

getDimensionality, getMax, getMin

Methods inherited from interface de.lmu.ifi.dbs.elki.data.FeatureVector

getDimensionality, getValue, toString

Field Detail

FACTORY

public static final FeatureVector.Factory<WeightedDiscreteUncertainObject,?> FACTORY

Vector factory.

samples

private DoubleVector[] samples

Samples

weights

private double[] weights

Sample weights

Constructor Detail

WeightedDiscreteUncertainObject

public WeightedDiscreteUncertainObject(DoubleVector[] samples,
                               double[] weights)

Constructor.

Parameters:

samples - Samples

weights - Weights (must be in ]0:1] and sum up to at most 1).

Method Detail

drawSample

public DoubleVector drawSample(Random rand)

Description copied from interface: UncertainObject

Draw a random sampled instance.

Specified by:

drawSample in interface UncertainObject

Specified by:

drawSample in class AbstractUncertainObject

Parameters:

rand - Random generator

Returns:

Sampled object.

getCenterOfMass

public DoubleVector getCenterOfMass()

Description copied from interface: UncertainObject

Get the center of mass of the uncertain object.

Specified by:

getCenterOfMass in interface UncertainObject

Specified by:

getCenterOfMass in class AbstractUncertainObject

Returns:

Center of mass.

getNumberSamples

public int getNumberSamples()

Description copied from interface: DiscreteUncertainObject

Get the number of samples available (or -1 for infinite).

Specified by:

getNumberSamples in interface DiscreteUncertainObject

Returns:

Number of samples, negative indicates infinite.

getSample

public DoubleVector getSample(int i)

Description copied from interface: DiscreteUncertainObject

Get the i'th vector.

Specified by:

getSample in interface DiscreteUncertainObject

Parameters:

i - Index

Returns:

Vector

getWeight

public double getWeight(int i)

Description copied from interface: DiscreteUncertainObject

Get the weight of the i'th vector.

Specified by:

getWeight in interface DiscreteUncertainObject

Parameters:

i - Index

Returns:

Weight