详细描述

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.

The option of using mini-batch based training was added to this class. See EKMeansMethod

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

在文件 KMeans.h 第 57 行定义.

类 CKMeans 继承关系图:

[图例]

Public 成员函数
	CKMeans ()

	CKMeans (int32_t k, CDistance *d, EKMeansMethod f)

	CKMeans (int32_t k, CDistance *d, bool kmeanspp=false, EKMeansMethod f=KMM_LLOYD)

	CKMeans (int32_t k_i, CDistance *d_i, SGMatrix< float64_t > centers_i, EKMeansMethod f=KMM_LLOYD)

virtual	~CKMeans ()

virtual EMachineType	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_use_kmeanspp (bool kmpp)

bool	get_use_kmeanspp () const

void	set_fixed_centers (bool fixed)

bool	get_fixed_centers ()

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

virtual void	set_initial_centers (SGMatrix< float64_t > centers)

void	set_train_method (EKMeansMethod f)

EKMeansMethod	get_train_method () const

void	set_mbKMeans_batch_size (int32_t b)

int32_t	get_mbKMeans_batch_size () const

void	set_mbKMeans_iter (int32_t t)

int32_t	get_mbKMeans_iter () const

void	set_mbKMeans_params (int32_t b, int32_t t)

void	set_distance (CDistance *d)

CDistance *	get_distance () const

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 CMulticlassLabels *	apply_multiclass (CFeatures *data=NULL)

virtual float64_t	apply_one (int32_t num)

virtual bool	train (CFeatures *data=NULL)

virtual CLabels *	apply (CFeatures *data=NULL)

virtual CBinaryLabels *	apply_binary (CFeatures *data=NULL)

virtual CRegressionLabels *	apply_regression (CFeatures *data=NULL)

virtual CStructuredLabels *	apply_structured (CFeatures *data=NULL)

virtual CLatentLabels *	apply_latent (CFeatures *data=NULL)

virtual void	set_labels (CLabels *lab)

virtual CLabels *	get_labels ()

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)

virtual bool	train_locked (SGVector< index_t > indices)

virtual CLabels *	apply_locked (SGVector< index_t > indices)

virtual CBinaryLabels *	apply_locked_binary (SGVector< index_t > indices)

virtual CRegressionLabels *	apply_locked_regression (SGVector< index_t > indices)

virtual CMulticlassLabels *	apply_locked_multiclass (SGVector< index_t > indices)

virtual CStructuredLabels *	apply_locked_structured (SGVector< index_t > indices)

virtual CLatentLabels *	apply_locked_latent (SGVector< index_t > indices)

virtual void	data_lock (CLabels labs, CFeatures features)

virtual void	post_lock (CLabels labs, CFeatures features)

virtual void	data_unlock ()

virtual bool	supports_locking () const

bool	is_data_locked () const

virtual EProblemType	get_machine_problem_type () const

virtual CSGObject *	shallow_copy () const

virtual CSGObject *	deep_copy () const

virtual bool	is_generic (EPrimitiveType *generic) const

template<class T >
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 ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
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 ()

SGStringList< char >	get_modelsel_names ()

void	print_modsel_params ()

char *	get_modsel_param_descr (const char *param_name)

index_t	get_modsel_param_index (const char *param_name)

void	build_gradient_parameter_dictionary (CMap< TParameter , CSGObject > *dict)

virtual void	update_parameter_hash ()

virtual bool	parameter_hash_changed ()

virtual bool	equals (CSGObject *other, float64_t accuracy=0.0, bool tolerant=false)

virtual CSGObject *	clone ()

Public 属性
SGIO *	io

Parallel *	parallel

Version *	version

Parameter *	m_parameters

Parameter *	m_model_selection_parameters

Parameter *	m_gradient_parameters

uint32_t	m_hash

Protected 成员函数
virtual bool	is_label_valid (CLabels *lab) const

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)

静态 Protected 成员函数
static void *	run_distance_thread_lhs (void *p)

static void *	run_distance_thread_rhs (void *p)

Protected 属性
CDistance *	distance

float64_t	m_max_train_time

CLabels *	m_labels

ESolverType	m_solver_type

bool	m_store_model_features

bool	m_data_locked

构造及析构函数说明

CKMeans ( )

default constructor

在文件 KMeans.cpp 第 29 行定义.

CKMeans	(	int32_t	k,
		CDistance *	d,
		EKMeansMethod	f
	)

constructor

参数

k	parameter k
d	distance
f	train_method value

在文件 KMeans.cpp 第 35 行定义.

CKMeans	(	int32_t	k,
		CDistance *	d,
		bool	kmeanspp = `false`,
		EKMeansMethod	f = `KMM_LLOYD`
	)

constructor

参数

k	parameter k
d	distance
kmeanspp	true for using KMeans++ (default false)
f	train_method value

在文件 KMeans.cpp 第 44 行定义.

CKMeans	(	int32_t	k_i,
		CDistance *	d_i,
		SGMatrix< float64_t >	centers_i,
		EKMeansMethod	f = `KMM_LLOYD`
	)

constructor for supplying initial centers

参数

k_i	parameter k
d_i	distance
centers_i	initial centers for KMeans algorithm
f	train_method value

在文件 KMeans.cpp 第 54 行定义.

~CKMeans ( )

virtual

在文件 KMeans.cpp 第 64 行定义.

成员函数说明

CLabels * apply ( CFeatures * data = NULL )

virtualinherited

apply machine to data if data is not specified apply to the current features

参数

data	(test)data to be classified

返回: classified labels

在文件 Machine.cpp 第 152 行定义.

CBinaryLabels * apply_binary ( CFeatures * data = NULL )

virtualinherited

apply machine to data in means of binary classification problem

被 CKernelMachine, COnlineLinearMachine, CWDSVMOcas, CNeuralNetwork, CLinearMachine, CGaussianProcessClassification, CDomainAdaptationSVMLinear, CDomainAdaptationSVM, CPluginEstimate , 以及 CBaggingMachine 重载.

在文件 Machine.cpp 第 208 行定义.

CLatentLabels * apply_latent ( CFeatures * data = NULL )

virtualinherited

apply machine to data in means of latent problem

被 CLinearLatentMachine 重载.

在文件 Machine.cpp 第 232 行定义.

CLabels * apply_locked ( SGVector< index_t > indices )

virtualinherited

Applies a locked machine on a set of indices. Error if machine is not locked

参数

indices index vector (of locked features) that is predicted

在文件 Machine.cpp 第 187 行定义.

CBinaryLabels * apply_locked_binary ( SGVector< index_t > indices )

virtualinherited

applies a locked machine on a set of indices for binary problems

被 CKernelMachine , 以及 CMultitaskLinearMachine 重载.

在文件 Machine.cpp 第 238 行定义.

CLatentLabels * apply_locked_latent ( SGVector< index_t > indices )

virtualinherited

applies a locked machine on a set of indices for latent problems

在文件 Machine.cpp 第 266 行定义.

CMulticlassLabels * apply_locked_multiclass ( SGVector< index_t > indices )

virtualinherited

applies a locked machine on a set of indices for multiclass problems

在文件 Machine.cpp 第 252 行定义.

CRegressionLabels * apply_locked_regression ( SGVector< index_t > indices )

virtualinherited

applies a locked machine on a set of indices for regression problems

被 CKernelMachine 重载.

在文件 Machine.cpp 第 245 行定义.

CStructuredLabels * apply_locked_structured ( SGVector< index_t > indices )

virtualinherited

applies a locked machine on a set of indices for structured problems

在文件 Machine.cpp 第 259 行定义.

CMulticlassLabels * apply_multiclass ( CFeatures * data = NULL )

virtualinherited

Classify all provided features. Cluster index with smallest distance to to be classified element is returned

参数

data	(test)data to be classified

返回: classified labels

重载 CMachine .

被 CKNN 重载.

在文件 DistanceMachine.cpp 第 208 行定义.

float64_t apply_one ( int32_t num )

virtualinherited

Apply machine to one example. Cluster index with smallest distance to to be classified element is returned

参数

num	which example to apply machine to

返回: cluster label nearest to example

重载 CMachine .

被 CKNN 重载.

在文件 DistanceMachine.cpp 第 234 行定义.

CRegressionLabels * apply_regression ( CFeatures * data = NULL )

virtualinherited

apply machine to data in means of regression problem

被 CKernelMachine, CWDSVMOcas, COnlineLinearMachine, CNeuralNetwork, CCHAIDTree, CStochasticGBMachine, CCARTree, CLinearMachine, CGaussianProcessRegression , 以及 CBaggingMachine 重载.

在文件 Machine.cpp 第 214 行定义.

CStructuredLabels * apply_structured ( CFeatures * data = NULL )

virtualinherited

apply machine to data in means of SO classification problem

被 CLinearStructuredOutputMachine 重载.

在文件 Machine.cpp 第 226 行定义.

void build_gradient_parameter_dictionary ( CMap< TParameter *, CSGObject * > * dict )

inherited

Builds a dictionary of all parameters in SGObject as well of those of SGObjects that are parameters of this object. Dictionary maps parameters to the objects that own them.

参数

dict	dictionary of parameters to be built.

在文件 SGObject.cpp 第 597 行定义.

CSGObject * clone ( )

virtualinherited

Creates a clone of the current object. This is done via recursively traversing all parameters, which corresponds to a deep copy. Calling equals on the cloned object always returns true although none of the memory of both objects overlaps.

返回: an identical copy of the given object, which is disjoint in memory. NULL if the clone fails. Note that the returned object is SG_REF'ed

在文件 SGObject.cpp 第 714 行定义.

void data_lock	(	CLabels *	labs,
		CFeatures *	features
	)

virtualinherited

Locks the machine on given labels and data. After this call, only train_locked and apply_locked may be called

Only possible if supports_locking() returns true

参数

labs	labels used for locking
features	features used for locking

被 CKernelMachine 重载.

在文件 Machine.cpp 第 112 行定义.

void data_unlock ( )

virtualinherited

Unlocks a locked machine and restores previous state

被 CKernelMachine 重载.

在文件 Machine.cpp 第 143 行定义.

CSGObject * deep_copy ( ) const

virtualinherited

A deep copy. All the instance variables will also be copied.

在文件 SGObject.cpp 第 198 行定义.

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

inherited

get distance functions for lhs feature vectors going from a1 to a2 and rhs feature vector b

参数

result	array of distance values
idx_a1	first feature vector a1 at idx_a1
idx_a2	last feature vector a2 at idx_a2
idx_b	feature vector b at idx_b

在文件 DistanceMachine.cpp 第 52 行定义.

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

inherited

get distance functions for rhs feature vectors going from b1 to b2 and lhs feature vector a

参数

result	array of distance values
idx_b1	first feature vector a1 at idx_b1
idx_b2	last feature vector a2 at idx_b2
idx_a	feature vector a at idx_a

在文件 DistanceMachine.cpp 第 114 行定义.

bool equals	(	CSGObject *	other,
		float64_t	accuracy = `0.0`,
		bool	tolerant = `false`
	)

virtualinherited

Recursively compares the current SGObject to another one. Compares all registered numerical parameters, recursion upon complex (SGObject) parameters. Does not compare pointers!

May be overwritten but please do with care! Should not be necessary in most cases.

参数

other	object to compare with
accuracy	accuracy to use for comparison (optional)
tolerant	allows linient check on float equality (within accuracy)

返回: true if all parameters were equal, false if not

在文件 SGObject.cpp 第 618 行定义.

virtual EMachineType get_classifier_type ( )

virtual

get classifier type

返回: classifier type KMEANS

重载 CMachine .

在文件 KMeans.h 第 96 行定义.

SGMatrix< float64_t > get_cluster_centers ( )

get centers

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

在文件 KMeans.cpp 第 370 行定义.

int32_t get_dimensions ( )

get dimensions

返回: number of dimensions

在文件 KMeans.cpp 第 382 行定义.

CDistance * get_distance ( ) const

inherited

get distance

返回: distance

在文件 DistanceMachine.cpp 第 270 行定义.

bool get_fixed_centers ( )

get fixed centers

返回: whether boolean centers are to be used

在文件 KMeans.cpp 第 392 行定义.

SGIO * get_global_io ( )

inherited

get the io object

返回: io object

在文件 SGObject.cpp 第 235 行定义.

Parallel * get_global_parallel ( )

inherited

get the parallel object

返回: parallel object

在文件 SGObject.cpp 第 277 行定义.

Version * get_global_version ( )

inherited

get the version object

返回: version object

在文件 SGObject.cpp 第 290 行定义.

int32_t get_k ( )

get k

返回: the parameter k

在文件 KMeans.cpp 第 309 行定义.

CLabels * get_labels ( )

virtualinherited

get labels

返回: labels

在文件 Machine.cpp 第 76 行定义.

virtual EProblemType get_machine_problem_type ( ) const

virtualinherited

returns type of problem machine solves

被 CNeuralNetwork, CRandomForest, CCHAIDTree, CCARTree , 以及 CBaseMulticlassMachine 重载.

在文件 Machine.h 第 299 行定义.

float64_t get_max_iter ( )

get maximum number of iterations

返回: maximum number of iterations

在文件 KMeans.cpp 第 320 行定义.

float64_t get_max_train_time ( )

inherited

get maximum training time

返回: maximum training time

在文件 Machine.cpp 第 87 行定义.

int32_t get_mbKMeans_batch_size ( ) const

get batch size for mini-batch KMeans

返回: batch size

在文件 KMeans.cpp 第 341 行定义.

int32_t get_mbKMeans_iter ( ) const

get no. of iterations for mini-batch KMeans

返回: no. of iterations

在文件 KMeans.cpp 第 352 行定义.

SGStringList< char > get_modelsel_names ( )

inherited

返回: vector of names of all parameters which are registered for model selection

在文件 SGObject.cpp 第 498 行定义.

char * get_modsel_param_descr ( const char * param_name )

inherited

Returns description of a given parameter string, if it exists. SG_ERROR otherwise

参数

param_name name of the parameter

返回: description of the parameter

在文件 SGObject.cpp 第 522 行定义.

index_t get_modsel_param_index ( const char * param_name )

inherited

Returns index of model selection parameter with provided index

参数

param_name name of model selection parameter

返回: index of model selection parameter with provided name, -1 if there is no such

在文件 SGObject.cpp 第 535 行定义.

virtual const char* get_name ( ) const

virtual

返回: object name

重载 CDistanceMachine .

在文件 KMeans.h 第 179 行定义.

SGVector< float64_t > get_radiuses ( )

get radiuses

返回: radiuses

在文件 KMeans.cpp 第 365 行定义.

ESolverType get_solver_type ( )

inherited

get solver type

返回: solver

在文件 Machine.cpp 第 102 行定义.

EKMeansMethod get_train_method ( ) const

get training method

返回: training method used - minibatch or lloyd

在文件 KMeans.cpp 第 330 行定义.

bool get_use_kmeanspp ( ) const

get use_kmeanspp attribute

返回: use_kmeanspp true=>use KMeans++ false=>don't use KMeans++

在文件 KMeans.cpp 第 298 行定义.

bool is_data_locked ( ) const

inherited

返回: whether this machine is locked

在文件 Machine.h 第 296 行定义.

bool is_generic ( EPrimitiveType * generic ) const

virtualinherited

If the SGSerializable is a class template then TRUE will be returned and GENERIC is set to the type of the generic.

参数

generic set to the type of the generic if returning TRUE

返回: TRUE if a class template.

在文件 SGObject.cpp 第 296 行定义.

virtual bool is_label_valid ( CLabels * lab ) const

protectedvirtualinherited

check whether the labels is valid.

Subclasses can override this to implement their check of label types.

参数

lab	the labels being checked, guaranteed to be non-NULL

被 CNeuralNetwork, CCARTree, CCHAIDTree, CGaussianProcessRegression , 以及 CBaseMulticlassMachine 重载.

在文件 Machine.h 第 348 行定义.

bool load ( FILE * srcfile )

virtual

load distance machine from file

参数

srcfile file to load from

返回: if loading was successful

在文件 KMeans.cpp 第 279 行定义.

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

virtualinherited

Load this object from file. If it will fail (returning FALSE) then this object will contain inconsistent data and should not be used!

参数

file	where to load from
prefix	prefix for members

返回: TRUE if done, otherwise FALSE

在文件 SGObject.cpp 第 369 行定义.

void load_serializable_post	(		)
throw	(	ShogunException
	)

protectedvirtualinherited

Can (optionally) be overridden to post-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::LOAD_SERIALIZABLE_POST is called.

异常

ShogunException will be thrown if an error occurs.

被 CKernel, CWeightedDegreePositionStringKernel, CList, CAlphabet, CLinearHMM, CGaussianKernel, CInverseMultiQuadricKernel, CCircularKernel , 以及 CExponentialKernel 重载.

在文件 SGObject.cpp 第 426 行定义.

void load_serializable_pre	(		)
throw	(	ShogunException
	)

protectedvirtualinherited

Can (optionally) be overridden to pre-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::LOAD_SERIALIZABLE_PRE is called.

异常

ShogunException will be thrown if an error occurs.

被 CDynamicArray< T >, CDynamicArray< float64_t >, CDynamicArray< float32_t >, CDynamicArray< int32_t >, CDynamicArray< char >, CDynamicArray< bool > , 以及 CDynamicObjectArray 重载.

在文件 SGObject.cpp 第 421 行定义.

bool parameter_hash_changed ( )

virtualinherited

返回: whether parameter combination has changed since last update

在文件 SGObject.cpp 第 262 行定义.

virtual void post_lock	(	CLabels *	labs,
		CFeatures *	features
	)

virtualinherited

post lock

被 CMultitaskLinearMachine 重载.

在文件 Machine.h 第 287 行定义.

void print_modsel_params ( )

inherited

prints all parameter registered for model selection and their type

在文件 SGObject.cpp 第 474 行定义.

void print_serializable ( const char * prefix = "" )

virtualinherited

prints registered parameters out

参数

prefix prefix for members

在文件 SGObject.cpp 第 308 行定义.

void * run_distance_thread_lhs ( void * p )

staticprotectedinherited

thread function for computing distance values

参数

p	thread parameter

在文件 DistanceMachine.cpp 第 176 行定义.

void * run_distance_thread_rhs ( void * p )

staticprotectedinherited

thread function for computing distance values

参数

p	thread parameter

在文件 DistanceMachine.cpp 第 192 行定义.

bool save ( FILE * dstfile )

virtual

save distance machine to file

参数

dstfile file to save to

返回: if saving was successful

在文件 KMeans.cpp 第 286 行定义.

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

virtualinherited

Save this object to file.

参数

file	where to save the object; will be closed during returning if PREFIX is an empty string.
prefix	prefix for members

返回: TRUE if done, otherwise FALSE

在文件 SGObject.cpp 第 314 行定义.

void save_serializable_post	(		)
throw	(	ShogunException
	)

protectedvirtualinherited

Can (optionally) be overridden to post-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::SAVE_SERIALIZABLE_POST is called.

异常

ShogunException will be thrown if an error occurs.

被 CKernel 重载.

在文件 SGObject.cpp 第 436 行定义.

void save_serializable_pre	(		)
throw	(	ShogunException
	)

protectedvirtualinherited

Can (optionally) be overridden to pre-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::SAVE_SERIALIZABLE_PRE is called.

异常

ShogunException will be thrown if an error occurs.

被 CKernel, CDynamicArray< T >, CDynamicArray< float64_t >, CDynamicArray< float32_t >, CDynamicArray< int32_t >, CDynamicArray< char >, CDynamicArray< bool > , 以及 CDynamicObjectArray 重载.

在文件 SGObject.cpp 第 431 行定义.

void set_distance ( CDistance * d )

inherited

set distance

参数

d	distance to set

在文件 DistanceMachine.cpp 第 263 行定义.

void set_fixed_centers ( bool fixed )

set fixed centers

参数

fixed true if fixed cluster centers are intended

在文件 KMeans.cpp 第 387 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 41 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 46 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 51 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 56 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 61 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 66 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 71 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 76 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 81 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 86 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 91 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 96 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 101 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 106 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 111 行定义.

void set_generic ( )

inherited

set generic type to T

void set_global_io ( SGIO * io )

inherited

set the io object

参数

io	io object to use

在文件 SGObject.cpp 第 228 行定义.

void set_global_parallel ( Parallel * parallel )

inherited

set the parallel object

参数

parallel parallel object to use

在文件 SGObject.cpp 第 241 行定义.

void set_global_version ( Version * version )

inherited

set the version object

参数

version version object to use

在文件 SGObject.cpp 第 283 行定义.

void set_initial_centers ( SGMatrix< float64_t > centers )

virtual

set the initial cluster centers

参数

centers matrix with cluster centers (k colums, dim rows)

在文件 KMeans.cpp 第 68 行定义.

void set_k ( int32_t p_k )

set k

参数

p_k new k

在文件 KMeans.cpp 第 303 行定义.

void set_labels ( CLabels * lab )

virtualinherited

set labels

参数

lab labels

被 CNeuralNetwork, CGaussianProcessMachine, CCARTree, CStructuredOutputMachine, CRelaxedTree , 以及 CMulticlassMachine 重载.

在文件 Machine.cpp 第 65 行定义.

void set_max_iter ( int32_t iter )

set maximum number of iterations

参数

iter	the new maximum

在文件 KMeans.cpp 第 314 行定义.

void set_max_train_time ( float64_t t )

inherited

set maximum training time

参数

t	maximimum training time

在文件 Machine.cpp 第 82 行定义.

void set_mbKMeans_batch_size ( int32_t b )

set batch size for mini-batch KMeans

参数

b	batch size int32_t(greater than 0)

在文件 KMeans.cpp 第 335 行定义.

void set_mbKMeans_iter ( int32_t t )

set no. of iterations for mini-batch KMeans

参数

t	no. of iterations int32_t(greater than 0)

在文件 KMeans.cpp 第 346 行定义.

void set_mbKMeans_params	(	int32_t	b,
		int32_t	t
	)

set batch size and no. of iteration for mini-batch KMeans

参数

b	batch size
t	no. of iterations

在文件 KMeans.cpp 第 357 行定义.

void set_solver_type ( ESolverType st )

inherited

set solver type

参数

st	solver type

在文件 Machine.cpp 第 97 行定义.

void set_store_model_features ( bool store_model )

virtualinherited

Setter for store-model-features-after-training flag

参数

store_model whether model should be stored after training

在文件 Machine.cpp 第 107 行定义.

void set_train_method ( EKMeansMethod f )

set training method

参数

f	minibatch if mini-batch KMeans

在文件 KMeans.cpp 第 325 行定义.

void set_use_kmeanspp ( bool kmpp )

set use_kmeanspp attribute

参数

kmpp	true=>use KMeans++ false=>don't use KMeans++

在文件 KMeans.cpp 第 293 行定义.

CSGObject * shallow_copy ( ) const

virtualinherited

A shallow copy. All the SGObject instance variables will be simply assigned and SG_REF-ed.

被 CGaussianKernel 重载.

在文件 SGObject.cpp 第 192 行定义.

virtual bool supports_locking ( ) const

virtualinherited

返回: whether this machine supports locking

被 CKernelMachine , 以及 CMultitaskLinearMachine 重载.

在文件 Machine.h 第 293 行定义.

bool train ( CFeatures * data = NULL )

virtualinherited

train machine

参数

data	training data (parameter can be avoided if distance or kernel-based classifiers are used and distance/kernels are initialized with train data). If flag is set, model features will be stored after training.

返回: whether training was successful

被 CRelaxedTree, CAutoencoder, CSGDQN , 以及 COnlineSVMSGD 重载.

在文件 Machine.cpp 第 39 行定义.

virtual bool train_locked ( SGVector< index_t > indices )

virtualinherited

Trains a locked machine on a set of indices. Error if machine is not locked

NOT IMPLEMENTED

参数

indices index vector (of locked features) that is used for training

返回: whether training was successful

被 CKernelMachine , 以及 CMultitaskLinearMachine 重载.

在文件 Machine.h 第 239 行定义.

void unset_generic ( )

inherited

unset generic type

this has to be called in classes specializing a template class

在文件 SGObject.cpp 第 303 行定义.

void update_parameter_hash ( )

virtualinherited

Updates the hash of current parameter combination

在文件 SGObject.cpp 第 248 行定义.

类成员变量说明

CDistance* distance

protectedinherited

the distance

在文件 DistanceMachine.h 第 130 行定义.

SGIO* io

inherited

io

在文件 SGObject.h 第 369 行定义.

bool m_data_locked

protectedinherited

whether data is locked

在文件 Machine.h 第 370 行定义.

Parameter* m_gradient_parameters

inherited

parameters wrt which we can compute gradients

在文件 SGObject.h 第 384 行定义.

uint32_t m_hash

inherited

Hash of parameter values

在文件 SGObject.h 第 387 行定义.

CLabels* m_labels

protectedinherited

labels

在文件 Machine.h 第 361 行定义.

float64_t m_max_train_time

protectedinherited

maximum training time

在文件 Machine.h 第 358 行定义.

Parameter* m_model_selection_parameters

inherited

model selection parameters

在文件 SGObject.h 第 381 行定义.

Parameter* m_parameters

inherited

parameters

在文件 SGObject.h 第 378 行定义.

ESolverType m_solver_type

protectedinherited

solver type

在文件 Machine.h 第 364 行定义.

bool m_store_model_features

protectedinherited

whether model features should be stored after training

在文件 Machine.h 第 367 行定义.

Parallel* parallel

inherited

parallel

在文件 SGObject.h 第 372 行定义.

Version* version

inherited

version

在文件 SGObject.h 第 375 行定义.

该类的文档由以下文件生成:

详细描述

Public 成员函数

Public 属性

Protected 成员函数

静态 Protected 成员函数

Protected 属性

构造及析构函数说明

成员函数说明

类成员变量说明