/usr/include/shogun/clustering/KMeans.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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 | /*
* 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) 1999-2008 Gunnar Raetsch
* Written (W) 2007-2009 Soeren Sonnenburg
* Copyright (C) 1999-2009 Fraunhofer Institute FIRST and Max-Planck-Society
*/
#ifndef _KMEANS_H__
#define _KMEANS_H__
#include <stdio.h>
#include <shogun/lib/common.h>
#include <shogun/io/SGIO.h>
#include <shogun/features/SimpleFeatures.h>
#include <shogun/distance/Distance.h>
#include <shogun/machine/DistanceMachine.h>
namespace shogun
{
class CDistanceMachine;
/** @brief KMeans clustering, partitions the data into k (a-priori specified) clusters.
*
* It minimizes
* \f[
* \sum_{i=1}^k\sum_{x_j\in S_i} (x_j-\mu_i)^2
* \f]
*
* where \f$\mu_i\f$ are the cluster centers and \f$S_i,\;i=1,\dots,k\f$ are the index
* sets of the clusters.
*
* Beware that this algorithm obtains only a <em>local</em> optimum.
*
* cf. http://en.wikipedia.org/wiki/K-means_algorithm */
class CKMeans : public CDistanceMachine
{
public:
/** default constructor */
CKMeans();
/** constructor
*
* @param k parameter k
* @param d distance
*/
CKMeans(int32_t k, CDistance* d);
virtual ~CKMeans();
/** get classifier type
*
* @return classifier type KMEANS
*/
virtual inline EClassifierType get_classifier_type() { return CT_KMEANS; }
/** 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 k
*
* @param p_k new k
*/
void set_k(int32_t p_k);
/** get k
*
* @return the parameter k
*/
int32_t get_k();
/** set maximum number of iterations
*
* @param iter the new maximum
*/
void set_max_iter(int32_t iter);
/** get maximum number of iterations
*
* @return maximum number of iterations
*/
float64_t get_max_iter();
/** get radiuses
*
* @return radiuses
*/
SGVector<float64_t> get_radiuses();
/** get centers
*
* @return cluster centers or empty matrix if no radiuses are there (not trained yet)
*/
SGMatrix<float64_t> get_cluster_centers();
/** get dimensions
*
* @return number of dimensions
*/
int32_t get_dimensions();
/** @return object name */
inline virtual const char* get_name() const { return "KMeans"; }
protected:
/** clustknb
*
* @param use_old_mus if old mus shall be used
* @param mus_start mus start
*/
void clustknb(bool use_old_mus, float64_t *mus_start);
/** train k-means
*
* @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);
/** Ensures cluster centers are in lhs of underlying distance */
virtual void store_model_features();
private:
void init();
protected:
/// maximum number of iterations
int32_t max_iter;
/// the k parameter in KMeans
int32_t k;
/// number of dimensions
int32_t dimensions;
/// radi of the clusters (size k)
SGVector<float64_t> R;
private:
/* temporary variable for weighting over the train data */
SGVector<float64_t> Weights;
/* temp variable for cluster centers */
SGMatrix<float64_t> mus;
};
}
#endif
|