org.apache.mahout.math.neighborhood

Class LocalitySensitiveHashSearch

java.lang.Object

org.apache.mahout.math.neighborhood.Searcher

org.apache.mahout.math.neighborhood.UpdatableSearcher

org.apache.mahout.math.neighborhood.LocalitySensitiveHashSearch

All Implemented Interfaces:

Iterable<Vector>

public class LocalitySensitiveHashSearch
extends UpdatableSearcher

Implements a Searcher that uses locality sensitivity hash as a first pass approximation to estimate distance without floating point math. The clever bit about this implementation is that it does an adaptive cutoff for the cutoff on the bitwise distance. Making this cutoff adaptive means that we only needs to make a single pass through the data.

Field Summary

Fields inherited from class org.apache.mahout.math.neighborhood.Searcher

distanceMeasure

Constructor Summary

Constructors

Constructor and Description
LocalitySensitiveHashSearch(DistanceMeasure distanceMeasure, int searchSize)

Method Summary

Modifier and Type	Method and Description
void	add(Vector vector) Add a new Vector to the Searcher that will be checked when getting the nearest neighbors.
void	clear()
int	getSearchSize()
Iterator<Vector>	iterator()
boolean	remove(Vector v, double epsilon)
protected static WeightedThing<Vector>	removeHash(WeightedThing<Vector> input)
int	resetEvaluationCount() This is only for testing.
List<WeightedThing<Vector>>	search(Vector query, int limit) When querying the Searcher for the closest vectors, a list of WeightedThings is returned.
WeightedThing<Vector>	searchFirst(Vector query, boolean differentThanQuery) Returns the closest vector to the query.
void	setRaiseHashLimitStrategy(double strategy)
void	setSearchSize(int size)
int	size() Returns the number of WeightedVectors being searched for nearest neighbors.

Methods inherited from class org.apache.mahout.math.neighborhood.Searcher

addAll, addAllMatrixSlices, addAllMatrixSlicesAsWeightedVectors, getCandidateQueue, getDistanceMeasure, search, searchFirst

Methods inherited from class java.lang.Object

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

Methods inherited from interface java.lang.Iterable

forEach, spliterator

Constructor Detail

LocalitySensitiveHashSearch

public LocalitySensitiveHashSearch(DistanceMeasure distanceMeasure,
                                   int searchSize)

Method Detail

search

public List<WeightedThing<Vector>> search(Vector query,
                                          int limit)

Description copied from class: Searcher

When querying the Searcher for the closest vectors, a list of WeightedThings is returned. The value of the WeightedThing is the neighbor and the weight is the the distance (calculated by some metric - see a concrete implementation) between the query and neighbor. The actual type of vector in the pair is the same as the vector added to the Searcher.

Specified by:

search in class Searcher

Parameters:

query - the vector to search for

limit - the number of results to return

Returns:

the list of weighted vectors closest to the query

searchFirst

public WeightedThing<Vector> searchFirst(Vector query,
                                         boolean differentThanQuery)

Returns the closest vector to the query. When only one the nearest vector is needed, use this method, NOT search(query, limit) because it's faster (less overhead). This is nearly the same as search().

Specified by:

searchFirst in class Searcher

Parameters:

query - the vector to search for

differentThanQuery - if true, returns the closest vector different than the query (this only matters if the query is among the searched vectors), otherwise, returns the closest vector to the query (even the same vector).

Returns:

the weighted vector closest to the query

removeHash

protected static WeightedThing<Vector> removeHash(WeightedThing<Vector> input)

add

public void add(Vector vector)

Description copied from class: Searcher

Add a new Vector to the Searcher that will be checked when getting the nearest neighbors. The vector IS NOT CLONED. Do not modify the vector externally otherwise the internal Searcher data structures could be invalidated.

Specified by:

add in class Searcher

size

public int size()

Description copied from class: Searcher

Returns the number of WeightedVectors being searched for nearest neighbors.

Specified by:

size in class Searcher

getSearchSize

public int getSearchSize()

setSearchSize

public void setSearchSize(int size)

setRaiseHashLimitStrategy

public void setRaiseHashLimitStrategy(double strategy)

resetEvaluationCount

public int resetEvaluationCount()

This is only for testing.

Returns:

the number of times the actual distance between two vectors was computed.

iterator

public Iterator<Vector> iterator()

remove

public boolean remove(Vector v,
                      double epsilon)

Specified by:

remove in class UpdatableSearcher

clear

public void clear()

Specified by:

clear in class UpdatableSearcher