Package cc.mallet.topics

Class DMRInferencer

java.lang.Object

cc.mallet.topics.TopicInferencer

cc.mallet.topics.DMRInferencer

All Implemented Interfaces:

java.io.Serializable

public class DMRInferencer
extends TopicInferencer
implements java.io.Serializable

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field	Description
protected int	defaultFeatureIndex
protected MaxEnt	dmrParameters
protected int	numFeatures

Fields inherited from class cc.mallet.topics.TopicInferencer

alpha, alphabet, beta, betaSum, cachedCoefficients, numTopics, numTypes, random, smoothingOnlyMass, tokensPerTopic, topicBits, topicMask, typeTopicCounts

Constructor Summary

Constructors

Constructor	Description
DMRInferencer(int[][] typeTopicCounts, int[] tokensPerTopic, MaxEnt dmrParameters, Alphabet alphabet, double beta, double betaSum)

Method Summary

Modifier and Type	Method	Description
double[]	getSampledDistribution(Instance instance, int numIterations, int thinning, int burnIn)	Use Gibbs sampling to infer a topic distribution.
static DMRInferencer	read(java.io.File f)

Methods inherited from class cc.mallet.topics.TopicInferencer

setRandomSeed, writeInferredDistributions

Methods inherited from class java.lang.Object

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

Field Detail

dmrParameters

protected MaxEnt dmrParameters

numFeatures

protected int numFeatures

defaultFeatureIndex

protected int defaultFeatureIndex

Constructor Detail

DMRInferencer

public DMRInferencer(int[][] typeTopicCounts,
                     int[] tokensPerTopic,
                     MaxEnt dmrParameters,
                     Alphabet alphabet,
                     double beta,
                     double betaSum)

Method Detail

getSampledDistribution

public double[] getSampledDistribution(Instance instance,
                                       int numIterations,
                                       int thinning,
                                       int burnIn)

Description copied from class: TopicInferencer

Use Gibbs sampling to infer a topic distribution. Topics are initialized to the (or a) most probable topic for each token. Using zero iterations returns exactly this initial topic distribution.

This code does not adjust type-topic counts: P(w|t) is clamped.

Overrides:

getSampledDistribution in class TopicInferencer

read

public static DMRInferencer read(java.io.File f)
                          throws java.lang.Exception

Throws:

java.lang.Exception