xapian-core/cluster/cosine_sim.cc

   1 /** @file cosine_sim.cc
   2  *  @brief Cosine similarity calculation between documents
   3  */
   4 /* Copyright (C) 2016 Richhiey Thomas
   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
  19  * USA
  20  */
  21
  22 #include <config.h>
  23
  24 #include "xapian/cluster.h"
  25
  26 #include "debuglog.h"
  27
  28 #include <cmath>
  29
  30 using namespace std;
  31 using namespace Xapian;
  32
  33 string
  34 CosineDistance::get_description() const
  35 {
  36     return "CosineDistance()";
  37 }
  38
  39 double
  40 CosineDistance::similarity(const PointType &a, const PointType &b) const
  41 {
  42     LOGCALL(API, double, "CosineDistance::similarity", a | b);
  43     double denom_a = a.get_magnitude();
  44     double denom_b = b.get_magnitude();
  45     double inner_product = 0;
  46
  47     if (denom_a == 0 || denom_b == 0)
  48         return 0.0;
  49
  50     for (TermIterator it = a.termlist_begin(); it != a.termlist_end(); ++it) {
  51         const string &term = *it;
  52         double a_weight = a.get_weight(term);
  53         if (a_weight == 0)
  54             continue;
  55         double b_weight = b.get_weight(term);
  56         if (b_weight == 0)
  57             continue;
  58         inner_product += a_weight * b_weight;
  59     }
  60
  61     return 1 - (inner_product / (sqrt(denom_a * denom_b)));
  62 }