xapian-letor/feature/idffeature.cc

   1 /** @file idffeature.cc
   2  * @brief IdfFeature class
   3  */
   4 /* Copyright (C) 2012 Parth Gupta
   5  * Copyright (C) 2016 Ayush Tomar
   6  *
   7  * This program is free software; you can redistribute it and/or
   8  * modify it under the terms of the GNU General Public License as
   9  * published by the Free Software Foundation; either version 2 of the
  10  * License, or (at your option) any later version.
  11  *
  12  * This program is distributed in the hope that it will be useful
  13  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  14  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  15  * GNU General Public License for more details.
  16  *
  17  * You should have received a copy of the GNU General Public License
  18  * along with this program; if not, write to the Free Software
  19  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
  20  */
  21
  22 #include <config.h>
  23
  24 #include "xapian-letor/feature.h"
  25
  26 #include "debuglog.h"
  27 #include "stringutils.h"
  28
  29 using namespace std;
  30
  31 namespace Xapian {
  32
  33 string
  34 IdfFeature::name() const
  35 {
  36     return "IdfFeature";
  37 }
  38
  39 /** A helper function for feature->get_value()
  40  *
  41  *  Checks if the term belongs to the title or is stemmed from the title.
  42  */
  43 inline bool
  44 is_title_term(const std::string& term)
  45 {
  46     return startswith(term, 'S') || startswith(term, "ZS");
  47 }
  48
  49 vector<double>
  50 IdfFeature::get_values() const
  51 {
  52     LOGCALL(API, vector<double>, "IdfFeature::get_values", NO_ARGS);
  53
  54     vector<double> values;
  55     double value = 0;
  56
  57     for (Xapian::TermIterator qt = feature_query.get_unique_terms_begin();
  58          qt != feature_query.get_terms_end(); ++qt) {
  59         if (is_title_term((*qt))) {
  60             auto idf_iterator = inverse_doc_freq.find(*qt);
  61             if (idf_iterator != inverse_doc_freq.end())
  62                 value += log10(1 + idf_iterator->second);
  63         }
  64     }
  65     values.push_back(value);
  66     value = 0;
  67
  68     for (Xapian::TermIterator qt = feature_query.get_unique_terms_begin();
  69          qt != feature_query.get_terms_end(); ++qt) {
  70         if (!is_title_term((*qt))) {
  71             auto idf_iterator = inverse_doc_freq.find(*qt);
  72             if (idf_iterator != inverse_doc_freq.end())
  73                 value += log10(1 + idf_iterator->second);
  74         }
  75     }
  76     values.push_back(value);
  77     value = 0;
  78
  79     for (Xapian::TermIterator qt = feature_query.get_unique_terms_begin();
  80          qt != feature_query.get_terms_end(); ++qt) {
  81         auto idf_iterator = inverse_doc_freq.find(*qt);
  82         if (idf_iterator != inverse_doc_freq.end())
  83             value += log10(1 + idf_iterator->second);
  84     }
  85     values.push_back(value);
  86
  87     return values;
  88 }
  89
  90 }