Detailed Description

KMeans clustering, partitions the data into k (a-priori specified) clusters.

It minimizes

$\sum_{i=1}^k\sum_{x_j\in S_i} (x_j-\mu_i)^2$

where $\mu_i$ are the cluster centers and $S_i,\;i=1,\dots,k$ are the index sets of the clusters.

Beware that this algorithm obtains only a local optimum.

cf. http://en.wikipedia.org/wiki/K-means_algorithm

Definition at line 39 of file KMeans.h.

Inheritance diagram for CKMeans:

[legend]

Public Member Functions
	CKMeans ()

	CKMeans (int32_t k, CDistance *d)

virtual	~CKMeans ()

virtual EClassifierType	get_classifier_type ()

virtual bool	load (FILE *srcfile)

virtual bool	save (FILE *dstfile)

void	set_k (int32_t p_k)

int32_t	get_k ()

void	set_max_iter (int32_t iter)

float64_t	get_max_iter ()

SGVector< float64_t >	get_radiuses ()

SGMatrix< float64_t >	get_cluster_centers ()

int32_t	get_dimensions ()

virtual const char *	get_name () const

Public Member Functions inherited from CDistanceMachine
	CDistanceMachine ()

virtual	~CDistanceMachine ()

void	set_distance (CDistance *d)

CDistance *	get_distance ()

void	distances_lhs (float64_t *result, int32_t idx_a1, int32_t idx_a2, int32_t idx_b)

void	distances_rhs (float64_t *result, int32_t idx_b1, int32_t idx_b2, int32_t idx_a)

virtual CLabels *	apply ()

virtual CLabels *	apply (CFeatures *data)

virtual float64_t	apply (int32_t num)

Public Member Functions inherited from CMachine
	CMachine ()

virtual	~CMachine ()

virtual bool	train (CFeatures *data=NULL)

virtual void	set_labels (CLabels *lab)

virtual CLabels *	get_labels ()

virtual float64_t	get_label (int32_t i)

void	set_max_train_time (float64_t t)

float64_t	get_max_train_time ()

void	set_solver_type (ESolverType st)

ESolverType	get_solver_type ()

virtual void	set_store_model_features (bool store_model)

Public Member Functions inherited from CSGObject
	CSGObject ()

	CSGObject (const CSGObject &orig)

virtual	~CSGObject ()

virtual bool	is_generic (EPrimitiveType *generic) const

template<class T >
void	set_generic ()

void	unset_generic ()

virtual void	print_serializable (const char *prefix="")

virtual bool	save_serializable (CSerializableFile file, const char prefix="")

virtual bool	load_serializable (CSerializableFile file, const char prefix="")

void	set_global_io (SGIO *io)

SGIO *	get_global_io ()

void	set_global_parallel (Parallel *parallel)

Parallel *	get_global_parallel ()

void	set_global_version (Version *version)

Version *	get_global_version ()

SGVector< char * >	get_modelsel_names ()

char *	get_modsel_param_descr (const char *param_name)

index_t	get_modsel_param_index (const char *param_name)

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

Protected Member Functions
void	clustknb (bool use_old_mus, float64_t *mus_start)

virtual bool	train_machine (CFeatures *data=NULL)

virtual void	store_model_features ()

Protected Member Functions inherited from CSGObject
virtual void	load_serializable_pre () throw (ShogunException)

virtual void	load_serializable_post () throw (ShogunException)

virtual void	save_serializable_pre () throw (ShogunException)

virtual void	save_serializable_post () throw (ShogunException)

Protected Attributes
int32_t	max_iter
	maximum number of iterations More...

int32_t	k
	the k parameter in KMeans More...

int32_t	dimensions
	number of dimensions More...

SGVector< float64_t >	R
	radi of the clusters (size k) More...

Protected Attributes inherited from CDistanceMachine
CDistance *	distance

Protected Attributes inherited from CMachine
float64_t	max_train_time

CLabels *	labels

ESolverType	solver_type

bool	m_store_model_features

Additional Inherited Members
Public Attributes inherited from CSGObject
SGIO *	io

Parallel *	parallel

Version *	version

Parameter *	m_parameters

Parameter *	m_model_selection_parameters

Static Protected Member Functions inherited from CDistanceMachine
static void *	run_distance_thread_lhs (void *p)

static void *	run_distance_thread_rhs (void *p)

Constructor & Destructor Documentation

CKMeans ( )

default constructor

Definition at line 29 of file KMeans.cpp.

CKMeans	(	int32_t	k,
		CDistance *	d
	)

constructor

Parameters

k	parameter k
d	distance

Definition at line 35 of file KMeans.cpp.

~CKMeans ( )

virtual

Definition at line 43 of file KMeans.cpp.

Member Function Documentation

void clustknb	(	bool	use_old_mus,
		float64_t *	mus_start
	)

protected

clustknb

Parameters

use_old_mus	if old mus shall be used
mus_start	mus start

replace rhs feature vectors

set rhs to mus_start

update rhs

Definition at line 179 of file KMeans.cpp.

virtual EClassifierType get_classifier_type ( )

virtual

get classifier type

Returns: classifier type KMEANS

Reimplemented from CMachine.

Definition at line 57 of file KMeans.h.

SGMatrix< float64_t > get_cluster_centers ( )

get centers

Returns: cluster centers or empty matrix if no radiuses are there (not trained yet)

Definition at line 115 of file KMeans.cpp.

int32_t get_dimensions ( )

get dimensions

Returns: number of dimensions

Definition at line 127 of file KMeans.cpp.

int32_t get_k ( )

get k

Returns: the parameter k

Definition at line 94 of file KMeans.cpp.

float64_t get_max_iter ( )

get maximum number of iterations

Returns: maximum number of iterations

Definition at line 105 of file KMeans.cpp.

virtual const char* get_name ( ) const

virtual

Returns: object name

Reimplemented from CDistanceMachine.

Definition at line 116 of file KMeans.h.

SGVector< float64_t > get_radiuses ( )

get radiuses

Returns: radiuses

Definition at line 110 of file KMeans.cpp.

bool load ( FILE * srcfile )

virtual

load distance machine from file

Parameters

srcfile file to load from

Returns: if loading was successful

Reimplemented from CMachine.

Definition at line 73 of file KMeans.cpp.

bool save ( FILE * dstfile )

virtual

save distance machine to file

Parameters

dstfile file to save to

Returns: if saving was successful

Reimplemented from CMachine.

Definition at line 80 of file KMeans.cpp.

void set_k ( int32_t p_k )

set k

Parameters

p_k new k

Definition at line 88 of file KMeans.cpp.

void set_max_iter ( int32_t iter )

set maximum number of iterations

Parameters

iter	the new maximum

Definition at line 99 of file KMeans.cpp.

void store_model_features ( )

protectedvirtual

Ensures cluster centers are in lhs of underlying distance

Reimplemented from CDistanceMachine.

Definition at line 464 of file KMeans.cpp.

bool train_machine ( CFeatures * data = NULL )

protectedvirtual

train k-means

Parameters

data	training data (parameter can be avoided if distance or kernel-based classifiers are used and distance/kernels are initialized with train data)

Returns: whether training was successful

Reimplemented from CMachine.

Definition at line 48 of file KMeans.cpp.

Member Data Documentation

int32_t dimensions

protected

number of dimensions

Definition at line 150 of file KMeans.h.

int32_t k

protected

the k parameter in KMeans

Definition at line 147 of file KMeans.h.

int32_t max_iter

protected

maximum number of iterations

Definition at line 144 of file KMeans.h.

SGVector<float64_t> R

protected

radi of the clusters (size k)

Definition at line 153 of file KMeans.h.

The documentation for this class was generated from the following files:

Detailed Description

Public Member Functions

Protected Member Functions

Protected Attributes

Additional Inherited Members

Constructor & Destructor Documentation

Member Function Documentation

Member Data Documentation