include/learner.h

   1 /*
   2  * Copyright (C) 2004 Jesus Gimenez, Lluis Marquez and Senen Moya
   3  *
   4  * This library is free software; you can redistribute it and/or
   5  * modify it under the terms of the GNU Lesser General Public
   6  * License as published by the Free Software Foundation; either
   7  * version 2.1 of the License, or (at your option) any later version.
   8  *
   9  * This library is distributed in the hope that it will be useful,
  10  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  11  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  12  * Lesser General Public License for more details.
  13  *
  14  * You should have received a copy of the GNU Lesser General Public
  15  * License along with this library; if not, write to the Free Software
  16  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  17  */
  18
  19
  20 #ifndef LEARNER_H
  21
  22 #include "hash.h"
  23 #include "dict.h"
  24 #include <string>
  25
  26 struct samples_counter_t
  27 {
  28     char *key;
  29     int positive;
  30     int negative;
  31 };
  32
  33 class learner
  34 {
  35 private:
  36         int learnerNumAMBP,learnerNumUNKP;
  37         hash_t<infoDict*>* learnerAMBP_H;
  38   hash_t<infoDict*>* learnerUNKP_H;
  39         swindow *sw;
  40   simpleList<nodo_feature_list*> learnerFeatureList;
  41   simpleList<infoDict*>* learnerAMBP_L;
  42   simpleList<infoDict*>* learnerUNKP_L;
  43         FILE *fKnown,*fUnknown;
  44         int learnerNumFeatures;
  45         char obtainAtrChar(FILE *channel);
  46         int  obtainAtrInt(FILE *channel,int *endAtr);
  47   //    void learnerCreateFeatureList(char *name, simpleList *featureList);
  48   simpleList<infoDict*>* learnerTransformHashInList(hash_t<infoDict*> *tptr);
  49         void learnerCreateDefaultFile(const std::string& modelName, const std::string& str);
  50         void learnerCreatePOSFile(const std::string& modelName, int is_ambp, hash_t< infoDict* >* h);
  51         void learnerCount(const std::string& name, int* nWords, int* nSentences);
  52   int learnerExecSVMlight(const std::string& svmdir, const std::string& options, const std::string& posFile, const std::string& outFile);
  53         int learnerLeftToRight(simpleList< nodo_feature_list* >* featureList, simpleList< nodo_feature_list* >* featureListUnk, dictionary* dKnown, dictionary* dUnknown, int numWrds, int inicio);
  54         int learnerRightToLeft(simpleList< nodo_feature_list* >* featureList, simpleList< nodo_feature_list* >* featureListUnk, dictionary* dKnown, dictionary* dUnknown, int numWrds, int inicio);
  55         void learnerGetFeatures(nodo* elem, std::stack< std::string, std::deque< std::string, std::allocator< std::string > > >& stk, dictionary* d, simpleList< nodo_feature_list* >* featureList, int direction);
  56         void learnerGenerateFeatures(nodo* elem, simpleList< nodo_feature_list* >* featureList, dictionary* d, int direction);
  57         void learnerGenerateFeaturesUnk(nodo* elem, simpleList< nodo_feature_list* >* featureList, dictionary* d, dictionary* dUnk, int direction);
  58         void learnerTrainModel(const std::string& trainingFileName, dictionary* dKnown, int numModel, int direction, int numSent, int numWords, int numChunks);
  59   weightRepository* learnerBuiltWeightRepository(weightRepository *wr,mapping *m,const std::string& pos,const std::string& fileName);
  60   hash_t<weight_node_t*>* learnerBuiltBias(hash_t<weight_node_t*>* h, const std::string& pos, const std::string& fileName);
  61   void learnerDestroyBias(hash_t<weight_node_t*> *h);
  62   int learnerIsPossiblePOS(const std::string& wrd, const std::string& pos, int Known_or_Unknown);
  63   simpleList<infoDict*>* learnerGetPotser(const std::string& wrd, int Known_or_Unknown, dictionary *d);
  64 //     void learnerTraining(FILE *f,char *modelName, int numModel,int LR_or_RL,int K_or_U,dictionary *d,simpleList *lpos);
  65         void learnerPrintMessage(int numModel, int K_or_U, int LR_or_RL,int is_fex);
  66         int  learnerNumChunks(const std::string& trainingFileName, float percentage, int nSentences);
  67         bool learnerIsInsideList(simpleList< infoDict* >* l, const std::string& key);
  68         void learnerDoLearn(FILE *f,int numModel,int LR_or_RL,int K_or_U,dictionary *d,simpleList<infoDict*>* lPosToTrain);
  69     void learnerDressNakedSetTrain(dictionary *d,mapping *m,FILE *f, const std::string& pos, int numModel, int direction, int K_or_U,int *nPos,int *nNeg);
  70     void learnerPushSample(const std::string& wrd,int numModel,int direction, int Known_or_Unknown, const std::string& pos,const std::string& samplePos,const std::string& features,dictionary *d, int *nNeg, int *nPos);
  71     void learnerPushSampleUnk(const std::string& wrd,int numModel,int direction, int Known_or_Unknown,const std::string& pos, const std::string& samplePos, const std::string& features,dictionary *d, int *nNeg, int *nPos);
  72         std::string learnerCreateFeatureString(FILE *f,mapping *m);
  73
  74         std::string read_feature_list_from_config_file(FILE *f, char *first_feature);
  75     std::string read_feature_list_from_string(const std::vector< std::string >& tokens);
  76         void read_config_file(const std::string& config_file);
  77
  78 public:
  79         learner(char *modelName);
  80         learner();
  81         ~learner();
  82         void learnerRun(const std::string& train);
  83 };
  84
  85 #define LEARNER_H
  86 #endif