xapian-letor/featurevector.cc

   1 /* featurevector.cc: The file responsible for transforming the document into the feature space.
   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
  22
  23 #include <config.h>
  24
  25 #include <xapian.h>
  26
  27 #include "featurevector.h"
  28 #include "featuremanager.h"
  29
  30 #include <list>
  31 #include <map>
  32
  33 #include "str.h"
  34 #include "stringutils.h"
  35
  36 #include <cstdio>
  37 #include <cstdlib>
  38 #include <cstring>
  39 #include "safeerrno.h"
  40 #include "safeunistd.h"
  41 #include <iostream>
  42 #include <fstream>
  43 #include <sstream>
  44 #include <string>
  45
  46
  47 using namespace std;
  48
  49 using namespace Xapian;
  50
  51 FeatureVector::FeatureVector() {
  52 }
  53
  54 FeatureVector::FeatureVector(const FeatureVector & /*o*/) {
  55 }
  56
  57 map<string, map<string, int> >
  58 FeatureVector::load_relevance(const std::string & qrel_file) {
  59     typedef map<string, int> Map1;              //docid and relevance judjement 0/1
  60     typedef map<string, Map1> Map2;             // qid and map1
  61     Map2 qrel;
  62
  63     string inLine;
  64     ifstream myfile(qrel_file.c_str(), ifstream::in);
  65     string token[4];
  66     if (myfile.is_open()) {
  67         while (myfile.good()) {
  68             getline(myfile, inLine);            //read a file line by line
  69             char * str;
  70             char * x1;
  71             x1 = const_cast<char*>(inLine.c_str());
  72             str = strtok(x1, " ,.-");
  73             int i = 0;
  74             while (str != NULL) {
  75                 token[i] = str;         //store tokens in a string array
  76                 ++i;
  77                 str = strtok(NULL, " ,.-");
  78             }
  79
  80             qrel.insert(make_pair(token[0], Map1()));
  81             qrel[token[0]].insert(make_pair(token[2], atoi(token[3].c_str())));
  82         }
  83         myfile.close();
  84     }
  85     return qrel;
  86 }
  87
  88 void
  89 FeatureVector::set_did(const std::string & did1) {
  90     this->did=did1;
  91 }
  92
  93 void
  94 FeatureVector::set_label(double label1) {
  95     this->label=label1;
  96 }
  97
  98 void
  99 FeatureVector::set_fvals(map<int,double> fvals1) {
 100     this->fvals=fvals1;
 101 }
 102
 103