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 #ifndef SVMT_LEARNER_H
  20
  21 struct samples_counter_t
  22 {
  23         char *key;
  24         int positive;
  25         int negative;
  26 };
  27
  28 class learner
  29 {
  30 private:
  31         int learnerNumAMBP,learnerNumUNKP;
  32         hash_t *learnerAMBP_H,*learnerUNKP_H;
  33         swindow *sw;
  34         simpleList learnerFeatureList,*learnerAMBP_L,*learnerUNKP_L;
  35         FILE *fKnown,*fUnknown;
  36         int learnerNumFeatures;
  37         char obtainAtrChar(FILE *channel);
  38         int  obtainAtrInt(FILE *channel,int *endAtr);
  39         void learnerCreateFeatureList(char *name, simpleList *featureList);
  40         simpleList *learnerTransformHashInList(hash_t *tptr);
  41         void learnerCreateDefaultFile(const char *modelName, const char *str);
  42         void learnerCreatePOSFile(char *modelName, int is_ambp, hash_t *h);
  43         void learnerCount(char *name, int *sentences, int *words);
  44         int learnerExecSVMlight(char *svmdir, char *options, char *posFile, char *outFile);
  45         int learnerLeftToRight(simpleList *, simpleList *, dictionary *dKnown, dictionary *dUnknown,/*mapping *mKnown, mapping *mUnknown,*/int numWrds, int inicio);
  46         int learnerRightToLeft(simpleList *,simpleList *,   dictionary *dKnown, dictionary *dUnknown,/*mapping *mKnown, mapping *mUnknown,*/int numWrds, int inicio);
  47         void learnerGetFeatures(nodo *elem, stack_t *stk,dictionary *d, simpleList *featureList, int direction);
  48         void learnerGenerateFeatures(nodo *elem,simpleList *featureList, dictionary *d, int direction);
  49         void learnerGenerateFeaturesUnk(nodo *elem,simpleList *featureList, dictionary *d, dictionary *dUnk, int direction);
  50         void learnerTrainModel(char *trainingFileName,dictionary *d, int numModel,int direction,  int numSent, int numWords, int numChunks);
  51         weightRepository *learnerBuiltWeightRepository(weightRepository *wr,mapping *m,char *pos,char *fileName);
  52         hash_t *learnerBuiltBias(hash_t *,char *pos,char *fileName);
  53         void learnerDestroyBias(hash_t *h);
  54         int learnerIsPossiblePOS(char *wrd, char *pos, int Known_or_Unknown);
  55         simpleList *learnerGetPotser(char *wrd, int Known_or_Unknown, dictionary *d);
  56         void learnerTraining(FILE *f,char *modelName, int numModel,int LR_or_RL,int K_or_U,dictionary *d,simpleList *lpos);
  57         void learnerPrintMessage(int numModel, int K_or_U, int LR_or_RL,int is_fex);
  58         int  learnerNumChunks(char *trainingFileName,float percentage,int nSentences);
  59         int learnerIsInsideList(simpleList *l, char *key);
  60         void learnerDoLearn(FILE *f,int numModel,int LR_or_RL,int K_or_U,dictionary *d,simpleList *lPosToTrain);
  61         void learnerDressNakedSetTrain(dictionary *d,mapping *m,FILE *f, char* pos, int numModel, int direction, int K_or_U,int *nPos,int *nNeg);
  62         void learnerPushSample(char *wrd,int numModel,int direction, int Known_or_Unknown, char *pos,char *samplePos,char *features,dictionary *d, int *nNeg, int *nPos);
  63         void learnerPushSampleUnk(char *wrd,int numModel,int direction, int Known_or_Unknown,char *pos, char *samplePos, char *features,dictionary *d, int *nNeg, int *nPos);
  64         char *learnerCreateFeatureString(FILE *f,mapping *m);
  65
  66         char *read_feature_list_from_config_file(FILE *f, char *first_feature);
  67         void read_config_file(const char *config_file);
  68
  69 public:
  70         learner(char *modelName);
  71         learner();
  72         ~learner();
  73         void learnerRun(char *train);
  74 };
  75
  76 #define SVMT_LEARNER_H
  77 #endif