Serialized Form

Package org.knowceans.corpus.analysis

Class org.knowceans.corpus.analysis.VariationOfInformationAnalyser extends java.lang.Object implements Serializable

serialVersionUID: 1L

Serialized Fields

docCategories

int[][] docCategories

docCategories sparse matrix (will be )

catDocuments

org.knowceans.map.HashMultiMap<X,Y> catDocuments

sparse transpose of docCategories

nCats

int nCats

number of categories

nDocs

int nDocs

number of documents

nValidDocs

int nValidDocs

number of valid documents

nTopics

int nTopics

number of topics

theta

double[][] theta

the document--topic associations (theta)

iptc

IptcCategories iptc

IPTC-Codes

outfile

java.lang.String outfile

comment

java.lang.String comment

sumPCatDoc

double sumPCatDoc

hierup

boolean hierup

hierdown

boolean hierdown

includeunknown

boolean includeunknown

Package org.knowceans.corpus.parsers.dpa

Class org.knowceans.corpus.parsers.dpa.IptcCategories extends java.lang.Object implements Serializable

serialVersionUID: 1L

Serialized Fields

iptcMap

java.util.HashMap<K,V> iptcMap

iptcIndex

java.util.Vector<E> iptcIndex

Package org.knowceans.dirichlet.atm

Class org.knowceans.dirichlet.atm.AtmGibbsQuerySampler extends AtmGibbsSampler implements Serializable

serialVersionUID: -1772624211078485094L

Serialized Fields

atmstateq

AtmMarkovState atmstateq

stateq contains the query documents. Its nw and nwsum fields are shared with the corpus state.

stateSave

AtmMarkovState stateSave

stateSave contains the saved markov state (after initially loading the state. It is a complete copy of the

thetasumq

double[][] thetasumq

Class org.knowceans.dirichlet.atm.AtmGibbsSampler extends LdaGibbsSampler implements Serializable

serialVersionUID: 1L

Serialized Fields

atmstate

AtmMarkovState atmstate

State variables of the Lda gibbs sampler. The contract is to set this pointer equal to the pointer on LdaMarkovState LdaGibbsSampler.state.

Class org.knowceans.dirichlet.atm.AtmMarkovState extends LdaMarkovState implements Serializable

serialVersionUID: 1L

Serialized Fields

ad

int[][] ad

document authors [M][]

x

int[][] x

word authors

A

int A

total number of authors

Package org.knowceans.dirichlet.lda

Class org.knowceans.dirichlet.lda.ExtLdaConfiguration extends LdaConfiguration implements Serializable

serialVersionUID: 1451977000310757825L

Serialized Fields

hyperMethod

int hyperMethod

backupInterval

int backupInterval

interSamples

int[] interSamples

corpusbase

java.lang.String corpusbase

outfilebase

java.lang.String outfilebase

interSave

boolean interSave

interTopics

boolean interTopics

forQuery

boolean forQuery

doNative

boolean doNative

Class org.knowceans.dirichlet.lda.LdaConfiguration extends java.lang.Object implements Serializable

serialVersionUID: -812799395305637798L

Serialized Fields

K

int K

number of topics

alpha

double alpha

Dirichlet parameter (document--topic associations)

beta

double beta

Dirichlet parameter (topic--term associations)

burnIn

int burnIn

burn-in period

iterations

int iterations

max iterations

sampleLag

int sampleLag

sample lag (if -1 only one sample taken)

thinInterval

int thinInterval

sampling lag (?)

Class org.knowceans.dirichlet.lda.LdaGibbsQuerySampler extends LdaGibbsSampler implements Serializable

serialVersionUID: -1772624211078485094L

Serialized Fields

stateq

LdaMarkovState stateq

stateq contains the query documents. Its nw and nwsum fields are shared with the corpus state.

stateSave

LdaMarkovState stateSave

stateSave contains the saved markov state (after initially loading the state. It is a complete copy of the

thetasumq

double[][] thetasumq

Class org.knowceans.dirichlet.lda.LdaGibbsSampler extends java.lang.Object implements Serializable

serialVersionUID: 1L

Serialized Fields

conf

ExtLdaConfiguration conf

Configuration object with the current parameters.

state

LdaMarkovState state

State variables of the Lda gibbs sampler.

thetasum

double[][] thetasum

cumulative statistics of theta

phisum

double[][] phisum

cumulative statistics of phi

backupIteration

int backupIteration

iteration in the last backup

numstats

int numstats

size of statistics

dispcol

int dispcol

rand

java.util.Random rand

Random generator

Class org.knowceans.dirichlet.lda.LdaMarkovState extends java.lang.Object implements Serializable

serialVersionUID: 3380802444939432054L

Serialized Fields

w

int[][] w

w_m,n: word vectors of the corpus.

V

int V

V: size of vocabulary.

z

int[][] z

z_m,n: topic assignments z_m,n for each word (= term occurrence).

nw

int[][] nw

n_k,t: nw[k][t] number of instances of term t assigned to topic k. In subclasses, this can be generalised as the number of associations between topics and latent-semantic "minor" items (words, links, recommendations).

nd

int[][] nd

n_m,k: nd[m][k] number of words (not terms!) in document m assigned to topic k. This should be equal to the document length. In subclasses, this can be generalised as the number associations between latent-semantic "major" items (documents, authors, searchers, recommenders) and topics.

nwsum

int[] nwsum

n_k: nwsum[k] total number of words (not terms!) assigned to topic k.

ndsum

int[] ndsum

n_m: ndsum[m] total number of words in document m.

Package org.knowceans.dirichlet.sandbox

Class org.knowceans.dirichlet.sandbox.LdaGibbsSamplerDpa extends java.lang.Object implements Serializable

serialVersionUID: 1L

Serialized Fields

documents

int[][] documents

Deprecated.

document data (term lists)

V

int V

Deprecated.

vocabulary size

K

int K

Deprecated.

number of topics

alpha

double alpha

Deprecated.

Dirichlet parameter (document--topic associations)

beta

double beta

Deprecated.

Dirichlet parameter (topic--term associations)

z

int[][] z

Deprecated.

topic assignments for each word.

nw

int[][] nw

Deprecated.

cwt[k][j] number of instances of word j (term?) assigned to topic k.

nd

int[][] nd

Deprecated.

nd[d][k] number of words in document d assigned to topic k.

nwsum

int[] nwsum

Deprecated.

nwsum[k] total number of words assigned to topic k.

ndsum

int[] ndsum

Deprecated.

ndsum[d] total number of words in document d.

thetasum

double[][] thetasum

Deprecated.

cumulative statistics of theta

phisum

double[][] phisum

Deprecated.

cumulative statistics of phi

numstats

int numstats

Deprecated.

size of statistics

interSamples

int[] interSamples

Deprecated.

number of iteration at which intermediate (single) samples are taken.

THIN_INTERVAL

int THIN_INTERVAL

Deprecated.

sampling lag (?)

BURN_IN

int BURN_IN

Deprecated.

burn-in period

ITERATIONS

int ITERATIONS

Deprecated.

max iterations

SAMPLE_LAG

int SAMPLE_LAG

Deprecated.

sample lag (if -1 only one sample taken)

dispcol

int dispcol

Deprecated.

corpusname

java.lang.String corpusname

Deprecated.

outfilename

java.lang.String outfilename

Deprecated.

messagetext

java.lang.String messagetext

Deprecated.

messageheader

java.lang.String messageheader

Deprecated.

messagerecipients

java.lang.String[] messagerecipients

Deprecated.

interSave

boolean interSave

Deprecated.

analyser

VariationOfInformationAnalyser analyser

Deprecated.

interTopics

boolean interTopics

Deprecated.

backupIteration

int backupIteration

Deprecated.

iteration in the last backup

timeElapsed

long timeElapsed

Deprecated.

backupInterval

int backupInterval

Deprecated.

t0

long t0

Deprecated.

Class org.knowceans.dirichlet.sandbox.LdaGibbsSamplerHyper extends LdaGibbsSampler implements Serializable

serialVersionUID: 1L

Serialized Fields

alphaSampler

InvGammaArms alphaSampler

betaSampler

InvGammaArms betaSampler

alphaParams

int[] alphaParams

betaParams

int[] betaParams

state

LdaMarkovStateHyper state

Class org.knowceans.dirichlet.sandbox.LdaMarkovStateHyper extends LdaMarkovState implements Serializable

Serialized Fields

valpha

double[] valpha

K hyperparameters alpha trained from observations, not used for a priori alpha.

vbeta

double[] vbeta

V hyperparameters beta trained from observations; not used for a priori beta.

alpha

double alpha

symmetric hyperparameter alpha or sum of valpha trained from observations, not used for a priori alpha.

beta

double beta

symmetric hyperparameter beta or sum of vbeta trained from observations; not used for a priori beta.

Package org.knowceans.sandbox

Class org.knowceans.sandbox.ListPrinter extends java.util.Vector<E> implements Serializable

serialVersionUID: 3256438097242765105L

Serialized Fields

linewidth

int linewidth

count

int count

entryStart

java.lang.String entryStart

entryEnd

java.lang.String entryEnd

entrySeparator

java.lang.String entrySeparator

listStart

java.lang.String listStart

listEnd

java.lang.String listEnd

Package org.knowceans.sandbox.hlda

Class org.knowceans.sandbox.hlda.HldaGibbsSampler extends LdaGibbsSampler implements Serializable

Serialized Fields

c

NestedCrpNode[][] c

c[m][ell] is the restaurant corresponding to the ell'th topic for document m. (Points at nodes in the hierarchy ncrp.)

ncrp

NestedCrpNode ncrp

the nested CRP structure into which c points

M

int M

number of documents

ncw

int[][][] ncw

ncw[ell][m][v] number of times topic ell was assigned word v in document m (need doc index because topics are indexed from the CRP tree nodes and need document-specific counts). TODO: also put the totals here which are now non-sparse in tree nodes.

ncwsum

int[][] ncwsum

ncwsum[ell][m] number of words from m assigned to topic ell

Package org.knowceans.sandbox.ilda

Class org.knowceans.sandbox.ilda.IldaGibbsSampler extends LdaGibbsSampler implements Serializable

serialVersionUID: 1L

Serialized Fields

growstep

int growstep

array grow step

nwunrep

int[] nwunrep

number of times a term is unrepresented by current topics

ndunrep

int[] ndunrep

nubmer of unrepresented words in a document

nwsumunrep

int nwsumunrep

total number of unrepresented words