Package cc.mallet.topics

Class WeightedTopicModel

java.lang.Object

cc.mallet.topics.WeightedTopicModel

All Implemented Interfaces:

java.io.Serializable

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

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field	Description
protected double	alpha
protected Alphabet	alphabet
protected double	alphaSum
protected double	beta
protected double	betaSum
protected java.util.ArrayList<TopicAssignment>	data
protected java.text.NumberFormat	formatter
protected double[]	logCountRatioCache
protected double[][]	logTypeTopicWeights
protected int	numTopics
protected int	numTypes
protected int[]	oneDocTopicCounts
protected boolean	printLogLikelihood
protected Randoms	random
int	showTopicsInterval
static java.util.regex.Pattern	sourceWordPattern
static java.util.regex.Pattern	targetWordPattern
protected int[]	tokensPerTopic
protected LabelAlphabet	topicAlphabet
protected double[]	totalTopicWeights
protected int[][]	typeTopicCounts
protected double[][]	typeTopicWeights
protected com.carrotsearch.hppc.IntDoubleHashMap[]	typeTypeWeights
int	wordsPerTopic

Constructor Summary

Constructors

Constructor	Description
WeightedTopicModel(int numberOfTopics, double alphaSum, double beta, Randoms random)

Method Summary

Modifier and Type	Method	Description
void	addInstances(InstanceList training)
Alphabet	getAlphabet()
java.util.ArrayList<TopicAssignment>	getData()
MarginalProbEstimator	getEstimator()
int	getNumTopics()
LabelAlphabet	getTopicAlphabet()
int[]	getTopicTotals()
int[][]	getTypeTopicCounts()
static void	main(java.lang.String[] args)
void	printState(java.io.File f)
void	printState(java.io.PrintStream stream)
void	readTypeTypeWeights(java.io.File weightsFile)
void	sample(int iterations, boolean shouldInitialize, int docCycleCount)
protected void	sampleTopicsForOneDoc(FeatureSequence tokenSequence, FeatureSequence topicSequence, boolean initializing, boolean debugging)
void	setRandomSeed(int seed)
void	setTopicDisplay(int interval, int n)
java.lang.String	topWords(int numWords)

Methods inherited from class java.lang.Object

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

Field Detail

sourceWordPattern

public static java.util.regex.Pattern sourceWordPattern

targetWordPattern

public static java.util.regex.Pattern targetWordPattern

data

protected java.util.ArrayList<TopicAssignment> data

alphabet

protected Alphabet alphabet

topicAlphabet

protected LabelAlphabet topicAlphabet

numTopics

protected int numTopics

numTypes

protected int numTypes

alpha

protected double alpha

alphaSum

protected double alphaSum

beta

protected double beta

betaSum

protected double betaSum

oneDocTopicCounts

protected int[] oneDocTopicCounts

typeTopicCounts

protected int[][] typeTopicCounts

tokensPerTopic

protected int[] tokensPerTopic

typeTypeWeights

protected com.carrotsearch.hppc.IntDoubleHashMap[] typeTypeWeights

logTypeTopicWeights

protected double[][] logTypeTopicWeights

typeTopicWeights

protected double[][] typeTopicWeights

totalTopicWeights

protected double[] totalTopicWeights

showTopicsInterval

public int showTopicsInterval

wordsPerTopic

public int wordsPerTopic

random

protected Randoms random

formatter

protected java.text.NumberFormat formatter

printLogLikelihood

protected boolean printLogLikelihood

logCountRatioCache

protected double[] logCountRatioCache

Constructor Detail

WeightedTopicModel

public WeightedTopicModel(int numberOfTopics,
                          double alphaSum,
                          double beta,
                          Randoms random)

Method Detail

getAlphabet

public Alphabet getAlphabet()

getTopicAlphabet

public LabelAlphabet getTopicAlphabet()

getNumTopics

public int getNumTopics()

getData

public java.util.ArrayList<TopicAssignment> getData()

setTopicDisplay

public void setTopicDisplay(int interval,
                            int n)

setRandomSeed

public void setRandomSeed(int seed)

getTypeTopicCounts

public int[][] getTypeTopicCounts()

getTopicTotals

public int[] getTopicTotals()

addInstances

public void addInstances(InstanceList training)

readTypeTypeWeights

public void readTypeTypeWeights(java.io.File weightsFile)
                         throws java.lang.Exception

Throws:

java.lang.Exception

sample

public void sample(int iterations,
                   boolean shouldInitialize,
                   int docCycleCount)
            throws java.io.IOException

Throws:

java.io.IOException

sampleTopicsForOneDoc

protected void sampleTopicsForOneDoc(FeatureSequence tokenSequence,
                                     FeatureSequence topicSequence,
                                     boolean initializing,
                                     boolean debugging)

topWords

public java.lang.String topWords(int numWords)

getEstimator

public MarginalProbEstimator getEstimator()

printState

public void printState(java.io.File f)
                throws java.io.IOException

Throws:

java.io.IOException

printState

public void printState(java.io.PrintStream stream)

main

public static void main(java.lang.String[] args)
                 throws java.lang.Exception

Throws:

java.lang.Exception