xapian-letor/feature/colltfcolllenfeature.cc

   1 /** @file
   2  * @brief CollTfCollLenFeature class
   3  */
   4 /* Copyright (C) 2012 Parth Gupta
   5  * Copyright (C) 2016 Ayush Tomar
   6  * Copyright (C) 2019 Vaibhav Kansagara
   7  *
   8  * This program is free software; you can redistribute it and/or
   9  * modify it under the terms of the GNU General Public License as
  10  * published by the Free Software Foundation; either version 2 of the
  11  * License, or (at your option) any later version.
  12  *
  13  * This program is distributed in the hope that it will be useful
  14  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  15  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  16  * GNU General Public License for more details.
  17  *
  18  * You should have received a copy of the GNU General Public License
  19  * along with this program; if not, write to the Free Software
  20  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
  21  */
  22
  23 #include <config.h>
  24
  25 #include "xapian-letor/feature.h"
  26 #include "api/feature_internal.h"
  27
  28 #include "debuglog.h"
  29 #include "stringutils.h"
  30
  31 using namespace std;
  32
  33 namespace Xapian {
  34
  35 string
  36 CollTfCollLenFeature::name() const
  37 {
  38     return "CollTfCollLenFeature";
  39 }
  40
  41 /** A helper function for feature->get_value()
  42  *
  43  *  Checks if the term belongs to the title or is stemmed from the title.
  44  */
  45 static inline bool
  46 is_title_term(const std::string& term)
  47 {
  48     return startswith(term, 'S') || startswith(term, "ZS");
  49 }
  50
  51 vector<double>
  52 CollTfCollLenFeature::get_values() const
  53 {
  54     LOGCALL(API, vector<double>, "CollTfCollLenFeature::get_values", NO_ARGS);
  55
  56     vector<double> values;
  57     double value = 0;
  58     double coll_len = internal->get_collection_length("title");
  59
  60     Xapian::Query feature_query = internal->get_query();
  61     for (Xapian::TermIterator qt = feature_query.get_unique_terms_begin();
  62          qt != feature_query.get_terms_end(); ++qt) {
  63         if (is_title_term((*qt))) {
  64             double tf = internal->get_collection_termfreq(*qt);
  65             value += log10(1 + (coll_len / (1 + tf)));
  66         }
  67     }
  68     values.push_back(value);
  69     value = 0;
  70     coll_len = internal->get_collection_length("body");
  71
  72     for (Xapian::TermIterator qt = feature_query.get_unique_terms_begin();
  73          qt != feature_query.get_terms_end(); ++qt) {
  74         if (!is_title_term((*qt))) {
  75             double tf = internal->get_collection_termfreq(*qt);
  76             value += log10(1 + (coll_len / (1 + tf)));
  77         }
  78     }
  79     values.push_back(value);
  80     value = 0;
  81     coll_len = internal->get_collection_length("whole");
  82
  83     for (Xapian::TermIterator qt = feature_query.get_unique_terms_begin();
  84          qt != feature_query.get_terms_end(); ++qt) {
  85         double tf = internal->get_collection_termfreq(*qt);
  86         value += log10(1 + (coll_len / (1 + tf)));
  87     }
  88     values.push_back(value);
  89
  90     return values;
  91 }
  92
  93 }