cc.mallet.topics
Class LDAHyper

java.lang.Object
  cc.mallet.topics.LDAHyper

All Implemented Interfaces:

java.io.Serializable

Direct Known Subclasses:

DMRTopicModel, LDAStream

Deprecated. Use ParallelTopicModel instead, which uses substantially faster data structures even for non-parallel operation.

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

Latent Dirichlet Allocation with optimized hyperparameters

Author:

David Mimno, Andrew McCallum

See Also:

Serialized Form

Nested Class Summary

class

LDAHyper.Topication Deprecated.

Field Summary

protected double[]	alpha Deprecated.
protected Alphabet	alphabet Deprecated.
protected double	alphaSum Deprecated.
protected double	beta Deprecated.
protected double	betaSum Deprecated.
int	burninPeriod Deprecated.
protected double[]	cachedCoefficients Deprecated.
protected java.util.ArrayList<LDAHyper.Topication>	data Deprecated.
static double	DEFAULT_BETA Deprecated.
protected int[]	docLengthCounts Deprecated.
protected java.text.NumberFormat	formatter Deprecated.
int	iterationsSoFar Deprecated.
int	numIterations Deprecated.
protected int	numTopics Deprecated.
protected int	numTypes Deprecated.
protected int[]	oneDocTopicCounts Deprecated.
int	optimizeInterval Deprecated.
protected java.lang.String	outputModelFilename Deprecated.
protected int	outputModelInterval Deprecated.
protected boolean	printLogLikelihood Deprecated.
protected Randoms	random Deprecated.
int	saveSampleInterval Deprecated.
protected int	saveStateInterval Deprecated.
int	showTopicsInterval Deprecated.
protected double	smoothingOnlyMass Deprecated.
protected java.lang.String	stateFilename Deprecated.
protected InstanceList	testing Deprecated.
protected int[]	tokensPerTopic Deprecated.
protected LabelAlphabet	topicAlphabet Deprecated.
protected int[][]	topicDocCounts Deprecated.
protected gnu.trove.TIntIntHashMap[]	typeTopicCounts Deprecated.
int	wordsPerTopic Deprecated.

Constructor Summary

LDAHyper(int numberOfTopics)
Deprecated.

LDAHyper(int numberOfTopics, double alphaSum, double beta)
Deprecated.

LDAHyper(int numberOfTopics, double alphaSum, double beta, Randoms random)
Deprecated.

LDAHyper(LabelAlphabet topicAlphabet, double alphaSum, double beta, Randoms random)
Deprecated.

Method Summary

void	addInstances(InstanceList training) Deprecated.
void	addInstances(InstanceList training, java.util.List<LabelSequence> topics) Deprecated.
double	empiricalLikelihood(int numSamples, InstanceList testing) Deprecated.
void	estimate() Deprecated.
void	estimate(int iterationsThisRound) Deprecated.
Alphabet	getAlphabet() Deprecated.
int	getCountFeatureTopic(int featureIndex, int topicIndex) Deprecated.
int	getCountTokensPerTopic(int topicIndex) Deprecated.
java.util.ArrayList<LDAHyper.Topication>	getData() Deprecated.
int	getNumTopics() Deprecated.
IDSorter[]	getSortedTopicWords(int topic) Deprecated.
LabelAlphabet	getTopicAlphabet() Deprecated.
protected void	initializeHistogramsAndCachedValues() Deprecated. Gather statistics on the size of documents and create histograms for use in Dirichlet hyperparameter optimization.
protected int	instanceLength(Instance instance) Deprecated.
static void	main(java.lang.String[] args) Deprecated.
double	modelLogLikelihood() Deprecated.
void	printDocumentTopics(java.io.File f) Deprecated.
void	printDocumentTopics(java.io.PrintWriter pw) Deprecated.
void	printDocumentTopics(java.io.PrintWriter pw, double threshold, int max) Deprecated.
void	printState(java.io.File f) Deprecated.
void	printState(java.io.PrintStream out) Deprecated.
void	printTopWords(java.io.File file, int numWords, boolean useNewLines) Deprecated.
void	printTopWords(java.io.PrintStream out, int numWords, boolean usingNewLines) Deprecated.
static LDAHyper	read(java.io.File f) Deprecated.
protected void	sampleTopicsForOneDoc(FeatureSequence tokenSequence, FeatureSequence topicSequence, boolean shouldSaveState, boolean readjustTopicsAndStats) Deprecated.
void	setBurninPeriod(int burninPeriod) Deprecated.
void	setModelOutput(int interval, java.lang.String filename) Deprecated.
void	setNumIterations(int numIterations) Deprecated.
void	setOptimizeInterval(int interval) Deprecated.
void	setRandomSeed(int seed) Deprecated.
void	setSaveState(int interval, java.lang.String filename) Deprecated. Define how often and where to save the state
void	setTestingInstances(InstanceList testing) Deprecated. Held-out instances for empirical likelihood calculation
void	setTopicDisplay(int interval, int n) Deprecated.
double	topicLabelMutualInformation() Deprecated.
void	topicXMLReport(java.io.PrintWriter out, int numWords) Deprecated.
void	topicXMLReportPhrases(java.io.PrintStream out, int numWords) Deprecated.
void	write(java.io.File f) Deprecated.

Methods inherited from class java.lang.Object

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

Field Detail

data

protected java.util.ArrayList<LDAHyper.Topication> data

Deprecated.

alphabet

protected Alphabet alphabet

Deprecated.

topicAlphabet

protected LabelAlphabet topicAlphabet

Deprecated.

numTopics

protected int numTopics

Deprecated.

numTypes

protected int numTypes

Deprecated.

alpha

protected double[] alpha

Deprecated.

alphaSum

protected double alphaSum

Deprecated.

beta

protected double beta

Deprecated.

betaSum

protected double betaSum

Deprecated.

DEFAULT_BETA

public static final double DEFAULT_BETA

Deprecated.

See Also:

Constant Field Values

smoothingOnlyMass

protected double smoothingOnlyMass

Deprecated.

cachedCoefficients

protected double[] cachedCoefficients

Deprecated.

testing

protected InstanceList testing

Deprecated.

oneDocTopicCounts

protected int[] oneDocTopicCounts

Deprecated.

typeTopicCounts

protected gnu.trove.TIntIntHashMap[] typeTopicCounts

Deprecated.

tokensPerTopic

protected int[] tokensPerTopic

Deprecated.

docLengthCounts

protected int[] docLengthCounts

Deprecated.

topicDocCounts

protected int[][] topicDocCounts

Deprecated.

iterationsSoFar

public int iterationsSoFar

Deprecated.

numIterations

public int numIterations

Deprecated.

burninPeriod

public int burninPeriod

Deprecated.

saveSampleInterval

public int saveSampleInterval

Deprecated.

optimizeInterval

public int optimizeInterval

Deprecated.

showTopicsInterval

public int showTopicsInterval

Deprecated.

wordsPerTopic

public int wordsPerTopic

Deprecated.

outputModelInterval

protected int outputModelInterval

Deprecated.

outputModelFilename

protected java.lang.String outputModelFilename

Deprecated.

saveStateInterval

protected int saveStateInterval

Deprecated.

stateFilename

protected java.lang.String stateFilename

Deprecated.

random

protected Randoms random

Deprecated.

formatter

protected java.text.NumberFormat formatter

Deprecated.

printLogLikelihood

protected boolean printLogLikelihood

Deprecated.

Constructor Detail

LDAHyper

public LDAHyper(int numberOfTopics)

Deprecated.

LDAHyper

public LDAHyper(int numberOfTopics,
                double alphaSum,
                double beta)

Deprecated.

LDAHyper

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

Deprecated.

LDAHyper

public LDAHyper(LabelAlphabet topicAlphabet,
                double alphaSum,
                double beta,
                Randoms random)

Deprecated.

Method Detail

getAlphabet

public Alphabet getAlphabet()

Deprecated.

getTopicAlphabet

public LabelAlphabet getTopicAlphabet()

Deprecated.

getNumTopics

public int getNumTopics()

Deprecated.

getData

public java.util.ArrayList<LDAHyper.Topication> getData()

Deprecated.

getCountFeatureTopic

public int getCountFeatureTopic(int featureIndex,
                                int topicIndex)

Deprecated.

getCountTokensPerTopic

public int getCountTokensPerTopic(int topicIndex)

Deprecated.

setTestingInstances

public void setTestingInstances(InstanceList testing)

Deprecated.

Held-out instances for empirical likelihood calculation

setNumIterations

public void setNumIterations(int numIterations)

Deprecated.

setBurninPeriod

public void setBurninPeriod(int burninPeriod)

Deprecated.

setTopicDisplay

public void setTopicDisplay(int interval,
                            int n)

Deprecated.

setRandomSeed

public void setRandomSeed(int seed)

Deprecated.

setOptimizeInterval

public void setOptimizeInterval(int interval)

Deprecated.

setModelOutput

public void setModelOutput(int interval,
                           java.lang.String filename)

Deprecated.

setSaveState

public void setSaveState(int interval,
                         java.lang.String filename)

Deprecated.

Define how often and where to save the state

Parameters:

interval - Save a copy of the state every interval iterations.

filename - Save the state to this file, with the iteration number as a suffix

instanceLength

protected int instanceLength(Instance instance)

Deprecated.

addInstances

public void addInstances(InstanceList training)

Deprecated.

addInstances

public void addInstances(InstanceList training,
                         java.util.List<LabelSequence> topics)

Deprecated.

initializeHistogramsAndCachedValues

protected void initializeHistogramsAndCachedValues()

Deprecated.

Gather statistics on the size of documents and create histograms for use in Dirichlet hyperparameter optimization.

estimate

public void estimate()
              throws java.io.IOException

Deprecated.

Throws:

java.io.IOException

estimate

public void estimate(int iterationsThisRound)
              throws java.io.IOException

Deprecated.

Throws:

java.io.IOException

sampleTopicsForOneDoc

protected void sampleTopicsForOneDoc(FeatureSequence tokenSequence,
                                     FeatureSequence topicSequence,
                                     boolean shouldSaveState,
                                     boolean readjustTopicsAndStats)

Deprecated.

getSortedTopicWords

public IDSorter[] getSortedTopicWords(int topic)

Deprecated.

printTopWords

public void printTopWords(java.io.File file,
                          int numWords,
                          boolean useNewLines)
                   throws java.io.IOException

Deprecated.

Throws:

java.io.IOException

printTopWords

public void printTopWords(java.io.PrintStream out,
                          int numWords,
                          boolean usingNewLines)

Deprecated.

topicXMLReport

public void topicXMLReport(java.io.PrintWriter out,
                           int numWords)

Deprecated.

topicXMLReportPhrases

public void topicXMLReportPhrases(java.io.PrintStream out,
                                  int numWords)

Deprecated.

printDocumentTopics

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

Deprecated.

Throws:

java.io.IOException

printDocumentTopics

public void printDocumentTopics(java.io.PrintWriter pw)

Deprecated.

printDocumentTopics

public void printDocumentTopics(java.io.PrintWriter pw,
                                double threshold,
                                int max)

Deprecated.

Parameters:

pw - A print writer

threshold - Only print topics with proportion greater than this number

max - Print no more than this many topics

printState

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

Deprecated.

Throws:

java.io.IOException

printState

public void printState(java.io.PrintStream out)

Deprecated.

write

public void write(java.io.File f)

Deprecated.

read

public static LDAHyper read(java.io.File f)

Deprecated.

topicLabelMutualInformation

public double topicLabelMutualInformation()

Deprecated.

empiricalLikelihood

public double empiricalLikelihood(int numSamples,
                                  InstanceList testing)

Deprecated.

modelLogLikelihood

public double modelLogLikelihood()

Deprecated.

main

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

Deprecated.

Throws:

java.io.IOException