uk.ac.gla.dcs.renaissance.iqir.qpr
Class Density

java.lang.Object
  uk.ac.gla.dcs.renaissance.iqir.qpr.EigenDecomposition
      uk.ac.gla.dcs.renaissance.iqir.qpr.Density

All Implemented Interfaces:

Serializable

public class Density
extends EigenDecomposition

A probability density

Author:

B. Piwowarski

See Also:

Serialized Form

Field Summary

Fields inherited from class uk.ac.gla.dcs.renaissance.iqir.qpr.EigenDecomposition

map, mS, mU

Constructor Summary

Density(DensityTracker tracker, boolean deepCopy)

Density(bpiwowar.maths.matrix.DoubleMatrix2D u, bpiwowar.maths.matrix.DiagonalDoubleMatrix s, it.unimi.dsi.fastutil.ints.Int2IntSortedMap map)

Density(bpiwowar.maths.matrix.DoubleMatrix2D mU, bpiwowar.maths.matrix.DiagonalDoubleMatrix mS, it.unimi.dsi.fastutil.ints.Int2IntSortedMap map, boolean deepCopy)

Density(SubspaceTracker tracker)
Uses a subspace tracker (SVD) to initialise

Method Summary

double	computeProbability(bpiwowar.maths.matrix.DoubleMatrix1D vector) Compute the probability of a one-dimensional subspace
double	computeProbability(bpiwowar.maths.matrix.DoubleMatrix1D vector, boolean sameMap) Compute the probability of a one-dimensional subspace
double	computeProbability(Subspace subspace, boolean fuzzyEvent) Compute the probability of an event
double	computeProbability(Subspace subspace, boolean fuzzyEvent, boolean sameMap) Compute the probability of an event
Density	copy()
bpiwowar.maths.matrix.DoubleMatrix2D	getProbabilityMatrix(bpiwowar.maths.matrix.DoubleMatrix1D vector, boolean sameMap) Get the matrix v^T * (U x S) where U is the basis and S is the square root of the eigenvalues.
bpiwowar.maths.matrix.DoubleMatrix2D	getProbabilityMatrix(Subspace subspace, boolean fuzzyEvent, boolean sameMap) Pre-computation of a probability.

Methods inherited from class uk.ac.gla.dcs.renaissance.iqir.qpr.EigenDecomposition

getGlobalMatrix, getLocalToGobalTermIdMap, getMatrix, getRank, getS, normalise, normalise, normalise, trim

Methods inherited from class java.lang.Object

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

Constructor Detail

Density

public Density(bpiwowar.maths.matrix.DoubleMatrix2D u,
               bpiwowar.maths.matrix.DiagonalDoubleMatrix s,
               it.unimi.dsi.fastutil.ints.Int2IntSortedMap map)

Density

public Density(SubspaceTracker tracker)

Uses a subspace tracker (SVD) to initialise

Parameters:

tracker -

Density

public Density(DensityTracker tracker,
               boolean deepCopy)

Parameters:

tracker - The tracker from which to build this density

deepCopy - If true, copy all the matrices (but sigma)

Density

public Density(bpiwowar.maths.matrix.DoubleMatrix2D mU,
               bpiwowar.maths.matrix.DiagonalDoubleMatrix mS,
               it.unimi.dsi.fastutil.ints.Int2IntSortedMap map,
               boolean deepCopy)

Method Detail

computeProbability

public final double computeProbability(Subspace subspace,
                                       boolean fuzzyEvent)

Compute the probability of an event

Parameters:

subspace - The event

fuzzyEvent - The event should be considered as "fuzzy" -- i.e. each dimension is weighted by the corresponding sigma

Returns:

computeProbability

public final double computeProbability(Subspace subspace,
                                       boolean fuzzyEvent,
                                       boolean sameMap)

Compute the probability of an event

Parameters:

subspace - The event

fuzzyEvent - The event should be considered as "fuzzy" -- i.e. each dimension is weighted by the corresponding sigma

sameMap -

Returns:

getProbabilityMatrix

public bpiwowar.maths.matrix.DoubleMatrix2D getProbabilityMatrix(Subspace subspace,
                                                                 boolean fuzzyEvent,
                                                                 boolean sameMap)

Pre-computation of a probability.

Given the subspace representation S U and the density S' U', computes U^T U' S' (crisp subspace) or S U^T U' S' (fuzzy subspace). The sum of the squares of the matrix correspond to the probability of observing the subspace given the density.

Each row of the resulting matrix correspond to the probability associated with one of the dimension of the subspace. Similarly, each column is associated to a dimension of the density.

Parameters:

subspace -

fuzzyEvent -

sameMap -

Returns:

getProbabilityMatrix

public bpiwowar.maths.matrix.DoubleMatrix2D getProbabilityMatrix(bpiwowar.maths.matrix.DoubleMatrix1D vector,
                                                                 boolean sameMap)

Get the matrix v^T * (U x S) where U is the basis and S is the square root of the eigenvalues. The Froebenius norm of the resulting matrix is the probability of the event defined by v x v^t

Parameters:

vector - The vector v

sameMap -

Returns:

copy

public Density copy()

computeProbability

public double computeProbability(bpiwowar.maths.matrix.DoubleMatrix1D vector,
                                 boolean sameMap)

Compute the probability of a one-dimensional subspace

Parameters:

vector -

Returns:

computeProbability

public double computeProbability(bpiwowar.maths.matrix.DoubleMatrix1D vector)

Compute the probability of a one-dimensional subspace

Parameters:

vector -

Returns: