/usr/include/shogun/clustering/Hierarchical.h is in libshogun-dev 1.1.0-4ubuntu2.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 | /*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 3 of the License, or
* (at your option) any later version.
*
* Written (W) 2007-2009 Soeren Sonnenburg
* Copyright (C) 2007-2009 Fraunhofer Institute FIRST and Max-Planck-Society
*/
#ifndef _HIERARCHICAL_H__
#define _HIERARCHICAL_H__
#include <stdio.h>
#include <shogun/lib/common.h>
#include <shogun/io/SGIO.h>
#include <shogun/distance/Distance.h>
#include <shogun/machine/DistanceMachine.h>
namespace shogun
{
class CDistanceMachine;
/** @brief Agglomerative hierarchical single linkage clustering.
*
* Starting with each object being assigned to its own cluster clusters are
* iteratively merged. Here the clusters are merged whose elements have
* minimum distance, i.e. the clusters A and B that obtain
*
* \f[
* \min\{d({\bf x},{\bf x'}): {\bf x}\in {\cal A},{\bf x'}\in {\cal B}\}
* \f]
*
* are merged.
*
* cf e.g. http://en.wikipedia.org/wiki/Data_clustering*/
class CHierarchical : public CDistanceMachine
{
public:
/** default constructor */
CHierarchical();
/** constructor
*
* @param merges the merges
* @param d distance
*/
CHierarchical(int32_t merges, CDistance* d);
virtual ~CHierarchical();
/** get classifier type
*
* @return classifier type HIERARCHICAL
*/
virtual EClassifierType get_classifier_type();
/** load distance machine from file
*
* @param srcfile file to load from
* @return if loading was successful
*/
virtual bool load(FILE* srcfile);
/** save distance machine to file
*
* @param dstfile file to save to
* @return if saving was successful
*/
virtual bool save(FILE* dstfile);
/** set merges
*
* @param m new merges
*/
inline void set_merges(int32_t m)
{
ASSERT(m>0);
merges=m;
}
/** get merges
*
* @return merges
*/
int32_t get_merges();
/** get assignment
*
*/
SGVector<int32_t> get_assignment();
/** get merge distance
*
*/
SGVector<float64_t> get_merge_distances();
/** get cluster pairs
*
*/
SGMatrix<int32_t> get_cluster_pairs();
/** @return object name */
inline virtual const char* get_name() const { return "Hierarchical"; }
protected:
/** estimate hierarchical clustering
*
* @param data training data (parameter can be avoided if distance or
* kernel-based classifiers are used and distance/kernels are
* initialized with train data)
*
* @return whether training was successful
*/
virtual bool train_machine(CFeatures* data=NULL);
/** TODO: Ensures cluster centers are in lhs of underlying distance
* Currently: does nothing.
* */
virtual void store_model_features();
/** NOT IMPLEMENTED */
virtual CLabels* apply();
/** NOT IMPLEMENTED */
virtual CLabels* apply(CFeatures* data);
/** NOT IMPLEMENTED */
virtual float64_t apply(int32_t num);
protected:
/// the number of merges in hierarchical clustering
int32_t merges;
/// number of dimensions
int32_t dimensions;
/// size of assignment table
int32_t assignment_size;
/// cluster assignment for the num_points
int32_t* assignment;
/// size of the below tables
int32_t table_size;
/// tuples of i/j
int32_t* pairs;
/// distance at which pair i/j was added
float64_t* merge_distance;
};
}
#endif
|