xapian-applications/omega/clickmodel/simplifieddbn.h

   1 /** @file simplifieddbn.h
   2  * @brief SimplifiedDBN class - the Simplified DBN click model.
   3  */
   4 /* Copyright (C) 2017 Vivek Pal
   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 #ifndef OMEGA_INCLUDED_SIMPLIFIEDDBN_H
  22 #define OMEGA_INCLUDED_SIMPLIFIEDDBN_H
  23
  24 #include <map>
  25 #include <string>
  26 #include <utility>
  27 #include <vector>
  28
  29 #include "session.h"
  30
  31 enum {
  32     PARAM_ATTR_PROB,
  33     PARAM_SAT_PROB,
  34     PARAM_COUNT_
  35 };
  36
  37 /**
  38  * SimplifiedDBN class implementing the SDBN click model.
  39  *
  40  * For more information of DBN click model, see the following paper:
  41  *
  42  * Olivier Chapelle and Ya Zhang. 2009. A dynamic bayesian network click
  43  * model for web search ranking. In Proceedings of the 18th international
  44  * conference on World wide web (WWW '09).
  45  */
  46 class SimplifiedDBN {
  47     /// Relevances of documents corresponding to a query in a search session.
  48     std::map<std::string, std::map<std::string, std::map<int, double>>>
  49     doc_relevances;
  50   public:
  51     /// Return the name of the click model.
  52     std::string name();
  53
  54     /** Builds search sessions from the input log file and returns a list
  55      * of generated sessions. Each session contains three values: queryid,
  56      * a list of documents in the search result and a list of count of clicks
  57      * made on each document in the search result.
  58      *
  59      * @param logfile           Path to the final log file.
  60      */
  61     std::vector<Session> build_sessions(const std::string &logfile);
  62
  63     /** Trains the model i.e. learning the values of attractiveness
  64      * and satisfactoriness parameters modelled by the click model.
  65      *
  66      * @param sessions          List of all sessions.
  67      */
  68     void train(const std::vector<Session> &sessions);
  69
  70     /** Return predicted relevance of each document in a session i.e. the
  71      * estimations of the relevance of each document in a given session based
  72      * on a trained model. Values ranging from 0.0 to 1.0.
  73      *
  74      * @param sessions          Session class object representing a session.
  75      */
  76     std::vector<std::pair<std::string, double>>
  77     get_predicted_relevances(const Session &session);
  78 };
  79
  80 #endif // OMEGA_INCLUDED_SIMPLIFIEDDBN_H