---

PLSA.hpp

Go to the documentation of this file.

/*==========================================================================
 * Copyright (c) 2003 University of Massachusetts.  All Rights Reserved.
 *
 * Use of the Lemur Toolkit for Language Modeling and Information Retrieval
 * is subject to the terms of the software license set forth in the LICENSE
 * file included with this software, and also available at
 * http://www.lemurproject.org/license.html
 *
 *==========================================================================
*/
/*
  Probabilistic Latent Semantic Analysis 
  Java Reference implementation from Andrew Schein and Alexandrin Popescul
  Author: dmf 2/2003
 */

#ifndef _PLSA_HPP
#define _PLSA_HPP
#include "common_headers.hpp"
#include <cmath>
#include <set>
#include "Index.hpp"
#include "FreqVector.hpp"

//forward declaration.
class PLSA;

// Needed to declare member function parameter (not sure why...).
typedef double (PLSA::*jointfuncType)(int, int);


// Need both transient and permanent versions (store model components).
class PLSA  {
public:
  // need to pass in many parameters. Use sensible defaults...
  // document arguments.
  PLSA(const Index &dbIndex, int numCats, HashFreqVector **train, 
       HashFreqVector **validate, int numIter, 
       int numRestarts, double betastart, 
       double betastop, double anneal, double betaMod);

  PLSA(const Index &dbIndex, int testPercentage, int numCats, int numIter, 
       int numRestarts, double betastart, 
       double betastop, double anneal, double betaMod);
  PLSA(const Index &dbIndex);
  virtual ~PLSA();
    
  void iterateWithRestarts();

  double *get_p_z() const   {return p_z_best;}
  double **get_p_w_z() const {return p_w_z_best;}
  double **get_p_d_z() const {return p_d_z_best;}
  double getProb(int d, int w) const ;
  // get the matrix sizes
  int numWords() const {return sizeW;}
  int numDocs() const {return sizeD;}
  int numCats() const {return sizeZ;}
  bool readArrays();

private:
  // attributes
  const Index &ind;
  int sizeZ;
  int sizeD;
  int sizeW;

  HashFreqVector **data; // passed in
  HashFreqVector **testData; // passed in
  set<int, less<int> > *invIndex; // constructed
  
  double startBeta, beta, betaMin;
  double betaModifier;
  double annealcue;
  int R;
  int numberOfIterations;
  int numberOfRestarts;
  double bestTestLL;
  double bestA;
  bool bestOnly;
  bool ownMem;
  double *p_z_current;
  double **p_w_z_current;
  double **p_d_z_current;

  double *p_z_prev;
  double **p_w_z_prev;
  double **p_d_z_prev;

  double *p_z_best;
  double **p_w_z_best;
  double **p_d_z_best;

  // methods
  void setPrevToCurrent();
  void setCurrentToBest();
  void setBestToCurrent();
  void setBestToPrev();
  void setPrevToBest();

  double getAverageLikelihood();
  double getAverageLikelihoodPrev();

  double jointEstimate (int indexD, int indexW);
  double jointEstimateCurrent (int indexD, int indexW);
  double jointEstimateBest (int indexD, int indexW);
  double jointEstimateBeta (int indexD, int indexW);
  
  void iterate();
  void initializeParameters();

  double doLogLikelihood(jointfuncType, HashFreqVector **&myData);
  double logLikelihood();
  double validateDataLogLikelihood();
  double validateCurrentLogLikelihood();
  double bestDataLogLikelihood();
  double interleavedIterationEM();
  void selectTestTrain(int testPercent);
  void init();
  void initR();
  enum pType {P_Z = 0, P_W_Z = 1, P_D_Z = 2};

  //  bool readArrays();
  void writeArrays();  
  bool readArray(ifstream& infile, enum pType which);
  void writeArray(ofstream& ofile, enum pType which);
};

#endif /* _PLSA_HPP */

---