xapian-core/weight/ifb2weight.cc

   1 /** @file
   2  * @brief Xapian::IfB2Weight class - the IfB2 weighting scheme of the DFR framework.
   3  */
   4 /* Copyright (C) 2013,2014 Aarsh Shah
   5  *
   6  * This program is free software; you can redistribute it and/or
   7  * modify it under the terms of the GNU General Public License as
   8  * published by the Free Software Foundation; either version 2 of the
   9  * License, or (at your option) any later version.
  10  *
  11  * This program is distributed in the hope that it will be useful
  12  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  13  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  14  * GNU General Public License for more details.
  15  *
  16  * You should have received a copy of the GNU General Public License
  17  * along with this program; if not, write to the Free Software
  18  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
  19  */
  20
  21 #include <config.h>
  22
  23 #include "xapian/weight.h"
  24 #include "common/log2.h"
  25
  26 #include "serialise-double.h"
  27
  28 #include "xapian/error.h"
  29
  30 using namespace std;
  31
  32 namespace Xapian {
  33
  34 IfB2Weight::IfB2Weight(double c)
  35     : param_c(c)
  36 {
  37     if (param_c <= 0)
  38         throw Xapian::InvalidArgumentError("Parameter c is invalid");
  39     need_stat(AVERAGE_LENGTH);
  40     need_stat(DOC_LENGTH);
  41     need_stat(DOC_LENGTH_MIN);
  42     need_stat(COLLECTION_SIZE);
  43     need_stat(COLLECTION_FREQ);
  44     need_stat(WDF);
  45     need_stat(WDF_MAX);
  46     need_stat(WQF);
  47     need_stat(TERMFREQ);
  48 }
  49
  50 IfB2Weight *
  51 IfB2Weight::clone() const
  52 {
  53     return new IfB2Weight(param_c);
  54 }
  55
  56 void
  57 IfB2Weight::init(double factor)
  58 {
  59     if (factor == 0.0) {
  60         // This object is for the term-independent contribution, and that's
  61         // always zero for this scheme.
  62         return;
  63     }
  64
  65     double wdfn_upper = get_wdf_upper_bound();
  66     if (wdfn_upper == 0) {
  67         upper_bound = 0.0;
  68         return;
  69     }
  70
  71     double F = get_collection_freq();
  72     double N = get_collection_size();
  73
  74     wdfn_upper *= log2(1 + (param_c * get_average_length()) /
  75                     get_doclength_lower_bound());
  76
  77     // This term is constant for all documents.
  78     double idf_max = log2((N + 1.0) / (F + 0.5));
  79
  80     /* Calculate constant values to be used in get_sumpart(). */
  81     wqf_product_idf = get_wqf() * idf_max * factor;
  82     c_product_avlen = param_c * get_average_length();
  83     B_constant = (F + 1.0) / get_termfreq();
  84
  85     // wdfn * B = wdfn * (F + 1.0) / (get_termfreq() * (wdfn + 1.0)).
  86     // By cancelling out wdfn, we get (F + 1.0) / (get_termfreq() * (1.0 + 1.0 / wdfn)).
  87     // In order to maximize the product, we need to minimize the denominator, and so we use wdfn_upper.
  88     double max_wdfn_product_B = wdfn_upper * B_constant / (wdfn_upper + 1.0);
  89
  90     upper_bound = wqf_product_idf * max_wdfn_product_B * factor;
  91 }
  92
  93 string
  94 IfB2Weight::name() const
  95 {
  96     return "Xapian::IfB2Weight";
  97 }
  98
  99 string
 100 IfB2Weight::serialise() const
 101 {
 102     return serialise_double(param_c);
 103 }
 104
 105 IfB2Weight *
 106 IfB2Weight::unserialise(const string & s) const
 107 {
 108     const char *ptr = s.data();
 109     const char *end = ptr + s.size();
 110     double c = unserialise_double(&ptr, end);
 111     if (rare(ptr != end))
 112         throw Xapian::SerialisationError("Extra data in IfB2Weight::unserialise()");
 113     return new IfB2Weight(c);
 114 }
 115
 116 double
 117 IfB2Weight::get_sumpart(Xapian::termcount wdf, Xapian::termcount len,
 118                         Xapian::termcount) const
 119 {
 120     if (wdf == 0) return 0.0;
 121     double wdfn = wdf;
 122     wdfn *= log2(1 + c_product_avlen / len);
 123
 124     double wdfn_product_B = wdfn * B_constant / (wdfn + 1.0);
 125
 126     return (wqf_product_idf * wdfn_product_B);
 127 }
 128
 129 double
 130 IfB2Weight::get_maxpart() const
 131 {
 132     return upper_bound;
 133 }
 134
 135 double
 136 IfB2Weight::get_sumextra(Xapian::termcount, Xapian::termcount) const
 137 {
 138     return 0;
 139 }
 140
 141 double
 142 IfB2Weight::get_maxextra() const
 143 {
 144     return 0;
 145 }
 146
 147 }