Cluster.hpp

Go to the documentation of this file.

/*==========================================================================
 * Copyright (c) 2002 University of Massachusetts.  All Rights Reserved.
 *
 * Use of the Lemur Toolkit for Language Modeling and Information Retrieval
 * is subject to the terms of the software license set forth in the LICENSE
 * file included with this software, and also available at
 * http://www.lemurproject.org/license.html
 *
 *==========================================================================
 */

// David Fisher
// init: 11/18/2002
#ifndef _CLUSTER_HPP
#define _CLUSTER_HPP
#include <string>
#include "common_headers.hpp"
#include "Index.hpp"
#include "ClusterRep.hpp"
#include "SimilarityMethod.hpp"
#include "ClusterParam.hpp"
namespace lemur
{
  namespace cluster
  {
    // need an enumeration of types
#define DOC_ELT 1
#define CLUSTER_ELT 2
    // maximum length of a cluster name string.
#define NAMESIZE 50

    class ClusterElt {
    public:
      bool operator==(const ClusterElt& second) const {
        return (myType == second.myType && id == second.id);
      }
      int id;
      int myType;
    };

    class Cluster {
    public:
      Cluster(int cid, const lemur::api::Index &ind, 
              const SimilarityMethod &sim);
      virtual ~Cluster();
      void setId(int cid);
      void setName(const string &newName);
      int getId() const;
      const string &getName() const;
      const vector <ClusterElt> *getIds() const;
      vector <lemur::api::DOCID_T> getDocIds() const;
      virtual ClusterRep *getClusterRep() const = 0;
      virtual double score(const ClusterRep *rep) const = 0;
      virtual void add(const ClusterElt &elt);
      virtual void add(const vector<lemur::api::DOCID_T> docids);
      virtual void remove(const ClusterElt &elt);
      virtual vector<Cluster *> split(int numParts = 2);
      virtual void merge(const Cluster *c);
      virtual bool read(ifstream &in);
      virtual void write(ofstream &out);
      void print() const ;  
      int  getSize() const { return size;}
      virtual double sum2() const { return 0; }
      virtual string getKeyWords(int numTerms = 10) const ;
  
    protected:
      int id;
      string name;
      vector<ClusterElt> ids;
      const SimilarityMethod &similarity;
      int size;
      double weight;
      const lemur::api::Index &ind;
      fstream *datFile;
      long offset;
    };
  }
}

#endif

---