uk.ac.gla.dcs.renaissance.kqpr.sparse
Class SparseVectors

java.lang.Object
  java.util.AbstractCollection<E>
      java.util.AbstractList<T>
          uk.ac.gla.dcs.renaissance.kqpr.KernelVectorList<SparseVector>
              uk.ac.gla.dcs.renaissance.kqpr.sparse.SparseVectors

All Implemented Interfaces:

Iterable<SparseVector>, Collection<SparseVector>, List<SparseVector>

public class SparseVectors
extends KernelVectorList<SparseVector>

This is used for a simple kernel, where vectors are sparse. This class optimises the computation of the inner product with a new vector

Author:

B. Piwowarski

Field Summary

Fields inherited from class java.util.AbstractList

modCount

Constructor Summary

SparseVectors()

Method Summary

boolean	add(SparseVector e)
boolean	canLinearlyCombine() Returns true if the vectors can be linearly combined
double	computeInnerProduct(int i, SparseVector vector) Index from an id to a list of values from the vectors
double[]	computeInnerProducts(SparseVector vector) Compute the inner products with each of the vectors.
SparseVector	get(int index)
int	size()

Methods inherited from class uk.ac.gla.dcs.renaissance.kqpr.KernelVectorList

computeInnerProducts, linearCombination

Methods inherited from class java.util.AbstractList

add, addAll, clear, equals, hashCode, indexOf, iterator, lastIndexOf, listIterator, listIterator, remove, removeRange, set, subList

Methods inherited from class java.util.AbstractCollection

addAll, contains, containsAll, isEmpty, remove, removeAll, retainAll, toArray, toArray, toString

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Methods inherited from interface java.util.List

addAll, contains, containsAll, isEmpty, remove, removeAll, retainAll, toArray, toArray

Constructor Detail

SparseVectors

public SparseVectors()

Method Detail

add

public boolean add(SparseVector e)

Specified by:

add in interface Collection<SparseVector>

Specified by:

add in interface List<SparseVector>

Overrides:

add in class AbstractList<SparseVector>

get

public SparseVector get(int index)

Specified by:

get in interface List<SparseVector>

Specified by:

get in class AbstractList<SparseVector>

size

public int size()

Specified by:

size in interface Collection<SparseVector>

Specified by:

size in interface List<SparseVector>

Specified by:

size in class AbstractCollection<SparseVector>

computeInnerProduct

public double computeInnerProduct(int i,
                                  SparseVector vector)

Index from an id to a list of values from the vectors

Specified by:

computeInnerProduct in class KernelVectorList<SparseVector>

Parameters:

i - The index of the vector in the list

vector - The vector provided

Returns:

The inner product between both vectors

computeInnerProducts

public double[] computeInnerProducts(SparseVector vector)

Description copied from class: KernelVectorList

Compute the inner products with each of the vectors. This method might be re-implemented for efficiency reason, and by default calls iteratively #computeInnerProduct(int, Object).

Overrides:

computeInnerProducts in class KernelVectorList<SparseVector>

Parameters:

vector - The vector with which the inner product is computed each time

Returns:

A series of inner products, one for each of the base vectors

canLinearlyCombine

public boolean canLinearlyCombine()

Description copied from class: KernelVectorList

Returns true if the vectors can be linearly combined

Overrides:

canLinearlyCombine in class KernelVectorList<SparseVector>