xapian-core/weight/inl2weight.cc

   1 /** @file
   2  * @brief Xapian::InL2Weight class - the InL2 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 InL2Weight::InL2Weight(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(WDF);
  44     need_stat(WDF_MAX);
  45     need_stat(WQF);
  46     need_stat(TERMFREQ);
  47 }
  48
  49 InL2Weight *
  50 InL2Weight::clone() const
  51 {
  52     return new InL2Weight(param_c);
  53 }
  54
  55 void
  56 InL2Weight::init(double factor)
  57 {
  58     if (factor == 0.0) {
  59         // This object is for the term-independent contribution, and that's
  60         // always zero for this scheme.
  61         return;
  62     }
  63
  64     double wdfn_upper = get_wdf_upper_bound();
  65     if (wdfn_upper == 0) {
  66         upper_bound = 0.0;
  67         return;
  68     }
  69
  70     double termfreq = get_termfreq();
  71     double N = get_collection_size();
  72
  73     wdfn_upper *= log2(1 + (param_c * get_average_length()) /
  74                        get_doclength_lower_bound());
  75
  76     // wdfn * L = wdfn / (wdfn + 1) = 1 / (1 + 1 / wdfn).
  77     // To maximize the product, we need to minimize the denominator and so we use wdfn_upper in (1 / wdfn).
  78     double maximum_wdfn_product_L = wdfn_upper / (wdfn_upper + 1.0);
  79
  80     // This term is constant for all documents.
  81     double idf_max = log2((N + 1) / (termfreq + 0.5));
  82
  83     /* Calculate constant values to be used in get_sumpart() upfront. */
  84     wqf_product_idf = get_wqf() * idf_max * factor;
  85     c_product_avlen = param_c * get_average_length();
  86
  87     upper_bound = wqf_product_idf * maximum_wdfn_product_L * factor;
  88 }
  89
  90 string
  91 InL2Weight::name() const
  92 {
  93     return "Xapian::InL2Weight";
  94 }
  95
  96 string
  97 InL2Weight::serialise() const
  98 {
  99     return serialise_double(param_c);
 100 }
 101
 102 InL2Weight *
 103 InL2Weight::unserialise(const string & s) const
 104 {
 105     const char *ptr = s.data();
 106     const char *end = ptr + s.size();
 107     double c = unserialise_double(&ptr, end);
 108     if (rare(ptr != end))
 109         throw Xapian::SerialisationError("Extra data in InL2Weight::unserialise()");
 110     return new InL2Weight(c);
 111 }
 112
 113 double
 114 InL2Weight::get_sumpart(Xapian::termcount wdf, Xapian::termcount len,
 115                         Xapian::termcount) const
 116 {
 117     if (wdf == 0) return 0.0;
 118     double wdfn = wdf;
 119
 120     wdfn *= log2(1 + c_product_avlen / len);
 121
 122     double wdfn_product_L = wdfn / (wdfn + 1.0);
 123
 124     return (wqf_product_idf * wdfn_product_L);
 125 }
 126
 127 double
 128 InL2Weight::get_maxpart() const
 129 {
 130     return upper_bound;
 131 }
 132
 133 double
 134 InL2Weight::get_sumextra(Xapian::termcount, Xapian::termcount) const
 135 {
 136     return 0;
 137 }
 138
 139 double
 140 InL2Weight::get_maxextra() const
 141 {
 142     return 0;
 143 }
 144
 145 }