xapian-core/cluster/clusterinternal.h

   1 /** @file clusterinternal.h
   2  *  @brief Cluster API
   3  */
   4 /* Copyright (C) 2017 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 <xapian/intrusive_ptr.h>
  23
  24 #include <vector>
  25
  26 /** Internal class for ClusterSet
  27  */
  28 class Xapian::ClusterSet::Internal : public Xapian::Internal::intrusive_base {
  29     /// Copies are not allowed
  30     Internal(const Internal &);
  31
  32     /// Assignment is not allowed
  33     void operator=(const Internal &);
  34
  35     /** A vector storing the clusters that are created by the
  36      *  clusterers
  37      */
  38     std::vector<Cluster> clusters;
  39
  40   public:
  41     /// Constructor
  42     Internal() {}
  43
  44     /// Destructor
  45     ~Internal() {}
  46
  47     /// Add a cluster to the ClusterSet
  48     void add_cluster(const Cluster &cluster);
  49
  50     /// Add the point to the cluster at position 'index'
  51     void add_to_cluster(const Point &point, unsigned int index);
  52
  53     /// Return the number of clusters
  54     Xapian::doccount size() const;
  55
  56     /// Return the cluster at index 'i'
  57     Cluster& get_cluster(Xapian::doccount i);
  58
  59     /// Return the cluster at index 'i'
  60     const Cluster& get_cluster(Xapian::doccount i) const;
  61
  62     /// Clear all the clusters in the ClusterSet
  63     void clear_clusters();
  64
  65     /** Recalculate the centroids for all the clusters
  66      *  in the ClusterSet
  67      */
  68     void recalculate_centroids();
  69 };
  70
  71 /** Internal class for Cluster
  72  */
  73 class Xapian::Cluster::Internal : public Xapian::Internal::intrusive_base {
  74     /// Copies are not allowed
  75     Internal(const Internal &);
  76
  77     /// Assignment is not allowed
  78     void operator=(const Internal &);
  79
  80     /// Documents (or Points in the vector space) within the cluster
  81     std::vector<Point> cluster_docs;
  82
  83     /// Point or Document representing the cluster centroid
  84     Centroid centroid;
  85
  86   public:
  87     /// Constructor that initialises cluster with centroid
  88     explicit Internal(const Centroid &centroid_) : centroid(centroid_) {}
  89
  90     /// Constructor
  91     Internal() {}
  92
  93     /// Destructor
  94     ~Internal() {}
  95
  96     /// Returns size of the cluster
  97     Xapian::doccount size() const;
  98
  99     /// Add a document to the cluster
 100     void add_point(const Point &point);
 101
 102     /// Clear the cluster values
 103     void clear();
 104
 105     /// Return the point at the given index in the cluster
 106     Point& get_point(Xapian::doccount i);
 107
 108     /// Return the point at the given index in the cluster
 109     const Point& get_point(Xapian::doccount i) const;
 110
 111     /// Return the documents that are contained within the cluster
 112     DocumentSet get_documents() const;
 113
 114     /// Return the current centroid of the cluster
 115     const Centroid& get_centroid() const;
 116
 117     /// Set the centroid of the Cluster to 'centroid'
 118     void set_centroid(const Centroid &centroid);
 119
 120     /** Recalculate the centroid of the Cluster after each iteration
 121      *  of the KMeans algorithm by taking the mean of all document vectors (Points)
 122      *  that belong to the Cluster
 123      */
 124     void recalculate();
 125 };
 126
 127 /** Internal class for DocumentSet
 128  */
 129 class Xapian::DocumentSet::Internal : public Xapian::Internal::intrusive_base {
 130     /// Copies are not allowed.
 131     Internal(const Internal &);
 132
 133     /// Assignment is not allowed.
 134     void operator=(const Internal &);
 135
 136     /// Vector storing the documents for this DocumentSet
 137     std::vector<Xapian::Document> documents;
 138
 139   public:
 140     /// Constructor
 141     Internal() {}
 142
 143     /// Destructor
 144     ~Internal() {}
 145
 146     /// Returns the size of the DocumentSet
 147     Xapian::doccount size() const;
 148
 149     /// Returns the Document at the index 'i' in the DocumentSet
 150     Xapian::Document& get_document(Xapian::doccount i);
 151
 152     /// Returns the Document at the index 'i' in the DocumentSet
 153     const Xapian::Document& get_document(Xapian::doccount i) const;
 154
 155     /// Add a new Document to the DocumentSet
 156     void add_document(const Xapian::Document &document);
 157 };