smile.neighbor.lsh

Class Hash

java.lang.Object

smile.neighbor.lsh.Hash

All Implemented Interfaces:

java.io.Serializable

Direct Known Subclasses:

MultiProbeHash

public class Hash
extends java.lang.Object
implements java.io.Serializable

The hash function for Euclidean spaces.

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
Hash(int d, int k, double w, int H) Constructor.

Method Summary

Modifier and Type	Method and Description
void	add(int index, double[] x) Insert an item into the hash table.
Bucket	get(double[] x) Returns the bucket entry for the given point.
Bucket	get(int i) Returns the bucket entry for the given hash value.
int	hash(double[] x) Apply hash functions on given vector x.

Methods inherited from class java.lang.Object

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

Constructor Detail

Hash

public Hash(int d,
            int k,
            double w,
            int H)

Constructor.

Parameters:

d - the dimensionality of data.

k - the number of random projection hash functions, which is usually set to log(N) where N is the dataset size.

w - the width of random projections. It should be sufficiently away from 0. But we should not choose an w value that is too large, which will increase the query time.

H - the size of universal hash tables.

Method Detail

hash

public int hash(double[] x)

Apply hash functions on given vector x.

Parameters:

x - the vector to be hashed.

Returns:

the bucket of hash table for given vector x.

add

public void add(int index,
                double[] x)

Insert an item into the hash table.

get

public Bucket get(int i)

Returns the bucket entry for the given hash value.

get

public Bucket get(double[] x)

Returns the bucket entry for the given point.