xapian-letor/featuremanager.h

   1 /* featuremanager.h: The feature manager file.
   2  *
   3  * Copyright (C) 2012 Parth Gupta
   4  *
   5  * This program is free software; you can redistribute it and/or
   6  * modify it under the terms of the GNU General Public License as
   7  * published by the Free Software Foundation; either version 2 of the
   8  * License, or (at your option) any later version.
   9  *
  10  * This program is distributed in the hope that it will be useful,
  11  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  12  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  13  * GNU General Public License for more details.
  14  *
  15  * You should have received a copy of the GNU General Public License
  16  * along with this program; if not, write to the Free Software
  17  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301
  18  * USA
  19  */
  20
  21 #ifndef FEATURE_MANAGER_H
  22 #define FEATURE_MANAGER_H
  23
  24
  25 #include <xapian/letor.h>
  26 #include "letor_features.h"
  27 #include "featurevector.h"
  28 #include "ranklist.h"
  29 #include <map>
  30 #include <string>
  31
  32 using namespace std;
  33
  34 namespace Xapian {
  35
  36 class RankList;
  37 class FeatureVector;
  38
  39 class XAPIAN_VISIBILITY_DEFAULT FeatureManager {
  40
  41 public:
  42
  43     Xapian::Features f;
  44
  45     FeatureManager();
  46
  47     std::map<int,double> transform(const Document &doc, double &weight);
  48
  49     Xapian::RankList create_rank_list(const Xapian::MSet & mset,std::string & qid);
  50
  51     map<string, map<string,int> > load_relevance(const std::string & qrel_file);
  52
  53     Xapian::FeatureVector create_feature_vector(map<int,double> fvals, int &label, std::string & did);
  54
  55     std::string getdid(const Document &doc);
  56
  57     int getlabel(map<string, map<string, int> > qrel, const Document &doc, std::string & qid);
  58
  59     static const int fNum = 20;
  60
  61     virtual ~FeatureManager() {};
  62
  63     // accessors
  64     inline void set_database(const Database &db) { letor_db = db; update_collection_level();}
  65     inline const Database &get_database() const { return letor_db; }
  66     inline void set_query(const Query &query) { letor_query = query; update_query_level();}
  67     inline const Query &get_query() const { return letor_query; }
  68
  69     // fill "dest" with the corresponding values NOTE: dest should have size NUM_FEATURES (vector safer?)
  70     // TODO: the definition of this should be generated (or the whole class inherited from this one)
  71 //    void compute(const Document &doc, double *dest);
  72
  73
  74
  75 private:
  76     Database letor_db;
  77     Query letor_query;
  78
  79     map<string,long int> coll_len;
  80     map<string,long int> coll_tf;
  81     map<string,double> idf;
  82
  83     map<string, map<string, int> > qrel;
  84
  85     // update collection-level measures
  86     void update_collection_level();
  87
  88     // update query-level measures
  89     void update_query_level();
  90
  91 };
  92
  93 }
  94
  95
  96
  97 #endif // FEATURE_MANAGER_H