Package smile.neighbor.lsh

Class PosterioriModel

java.lang.Object

smile.neighbor.lsh.PosterioriModel

All Implemented Interfaces:

Serializable

public class PosterioriModel
extends Object
implements Serializable

Pre-computed posteriori probabilities for generating multiple probes.

See Also:

• Serialized Form

Constructor Summary

Constructors

Constructor	Description
PosterioriModel(MultiProbeHash hash, MultiProbeSample[] samples, int Nz, double sigma)	Constructor.

Method Summary

Modifier and Type	Method	Description
IntArrayList	getProbeSequence(double[] x, double recall, int T)	Generate query-directed probes.

Methods inherited from class java.lang.Object

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

Constructor Details

PosterioriModel

public PosterioriModel(MultiProbeHash hash,
 MultiProbeSample[] samples,
 int Nz,
 double sigma)

Constructor.

Parameters:

hash - the hash function.

samples - the training samples.

Nz - the size of lookup table.

sigma - the Parzen window width.

Method Details

getProbeSequence

public IntArrayList getProbeSequence(double[] x,
 double recall,
 int T)

Generate query-directed probes.

Parameters:

x - the query object.

recall - the threshold of global probability of probes as a quality control parameter.

T - the maximum number of probes.

Returns:

the list of probe buckets.