Detailed Description

Class OnlineLinearMachine is a generic interface for linear machines like classifiers which work through online algorithms.

A linear classifier computes

$f({\bf x})= {\bf w} \cdot {\bf x} + b$

where ${\bf w}$ are the weights assigned to each feature in training and $b$ the bias.

To implement a linear classifier all that is required is to define the train() function that delivers ${\bf w}$ above.

Note that this framework works with linear classifiers of arbitrary feature type, e.g. dense and sparse and even string based features. This is implemented by using CStreamingDotFeatures that may provide a mapping function $\Phi({\bf x})\mapsto {\cal R^D}$ encapsulating all the required operations (like the dot product). The decision function is thus

$f({\bf x})= {\bf w} \cdot \Phi({\bf x}) + b.$

Definition at line 49 of file OnlineLinearMachine.h.

Inheritance diagram for COnlineLinearMachine:

[legend]

Public Member Functions
	COnlineLinearMachine ()

virtual	~COnlineLinearMachine ()

virtual void	get_w (float32_t *&dst_w, int32_t &dst_dims)

virtual void	get_w (float64_t *&dst_w, int32_t &dst_dims)

virtual SGVector< float32_t >	get_w ()

virtual void	set_w (float32_t *src_w, int32_t src_w_dim)

virtual void	set_w (float64_t *src_w, int32_t src_w_dim)

virtual void	set_bias (float32_t b)

virtual float32_t	get_bias ()

virtual bool	load (FILE *srcfile)

virtual bool	save (FILE *dstfile)

virtual void	set_features (CStreamingDotFeatures *feat)

virtual CLabels *	apply ()

virtual CLabels *	apply (CFeatures *data)

virtual float64_t	apply (int32_t vec_idx)
	get output for example "vec_idx" More...

virtual float32_t	apply (float32_t *vec, int32_t len)

virtual float32_t	apply_to_current_example ()

virtual CStreamingDotFeatures *	get_features ()

virtual const char *	get_name () const

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 ()

virtual EClassifierType	get_classifier_type ()

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 Attributes
int32_t	w_dim

float32_t *	w

float32_t	bias

CStreamingDotFeatures *	features

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

Protected Member Functions inherited from CMachine
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)

Constructor & Destructor Documentation

COnlineLinearMachine ( )

default constructor

Definition at line 16 of file OnlineLinearMachine.cpp.

~COnlineLinearMachine ( )

virtual

Definition at line 24 of file OnlineLinearMachine.cpp.

Member Function Documentation

CLabels * apply ( )

virtual

apply linear machine to all examples

Returns: resulting labels

Implements CMachine.

Definition at line 47 of file OnlineLinearMachine.cpp.

CLabels * apply ( CFeatures * data )

virtual

apply linear machine to data

Parameters

data	(test)data to be classified

Returns: classified labels

Implements CMachine.

Definition at line 74 of file OnlineLinearMachine.cpp.

virtual float64_t apply ( int32_t vec_idx )

virtual

get output for example "vec_idx"

Reimplemented from CMachine.

Definition at line 178 of file OnlineLinearMachine.h.

float32_t apply	(	float32_t *	vec,
		int32_t	len
	)

virtual

apply linear machine to one vector

Parameters

vec	feature vector
len	length of vector

Returns: classified label

Definition at line 84 of file OnlineLinearMachine.cpp.

float32_t apply_to_current_example ( )

virtual

apply linear machine to vector currently being processed

Returns: classified label

Definition at line 89 of file OnlineLinearMachine.cpp.

virtual float32_t get_bias ( )

virtual

get bias

Returns: bias

Definition at line 133 of file OnlineLinearMachine.h.

virtual CStreamingDotFeatures* get_features ( )

virtual

get features

Returns: features

Definition at line 205 of file OnlineLinearMachine.h.

virtual const char* get_name ( ) const

virtual

Returns the name of the SGSerializable instance. It MUST BE the CLASS NAME without the prefixed `C'.

Returns: name of the SGSerializable

Implements CSGObject.

Reimplemented in CVowpalWabbit, COnlineSVMSGD, and COnlineLibLinear.

Definition at line 212 of file OnlineLinearMachine.h.

virtual void get_w	(	float32_t *&	dst_w,
		int32_t &	dst_dims
	)

virtual

get w

Parameters

dst_w	store w in this argument
dst_dims	dimension of w

Definition at line 61 of file OnlineLinearMachine.h.

virtual void get_w	(	float64_t *&	dst_w,
		int32_t &	dst_dims
	)

virtual

Get w as a new float64_t array

Parameters

dst_w	store w in this argument
dst_dims	dimension of w

Definition at line 74 of file OnlineLinearMachine.h.

virtual SGVector<float32_t> get_w ( )

virtual

get w

Returns: weight vector

Definition at line 87 of file OnlineLinearMachine.h.

bool load ( FILE * srcfile )

virtual

load from file

Parameters

srcfile file to load from

Returns: if loading was successful

Reimplemented from CMachine.

Definition at line 33 of file OnlineLinearMachine.cpp.

bool save ( FILE * dstfile )

virtual

save to file

Parameters

dstfile file to save to

Returns: if saving was successful

Reimplemented from CMachine.

Definition at line 40 of file OnlineLinearMachine.cpp.

virtual void set_bias ( float32_t b )

virtual

set bias

Parameters

b new bias

Definition at line 124 of file OnlineLinearMachine.h.

virtual void set_features ( CStreamingDotFeatures * feat )

virtual

set features

Parameters

feat	features to set

Definition at line 156 of file OnlineLinearMachine.h.

virtual void set_w	(	float32_t *	src_w,
		int32_t	src_w_dim
	)

virtual

set w

Parameters

src_w	new w
src_w_dim	dimension of new w

Definition at line 97 of file OnlineLinearMachine.h.

virtual void set_w	(	float64_t *	src_w,
		int32_t	src_w_dim
	)

virtual

Set weight vector from a float64_t vector

Parameters

src_w	new w
src_w_dim	dimension of new w

Definition at line 111 of file OnlineLinearMachine.h.

Member Data Documentation

float32_t bias

protected

bias

Definition at line 220 of file OnlineLinearMachine.h.

CStreamingDotFeatures* features

protected

features

Definition at line 222 of file OnlineLinearMachine.h.

float32_t* w

protected

w

Definition at line 218 of file OnlineLinearMachine.h.

int32_t w_dim

protected

dimension of w

Definition at line 216 of file OnlineLinearMachine.h.

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

Detailed Description

Public Member Functions

Protected Attributes

Additional Inherited Members

Constructor & Destructor Documentation

Member Function Documentation

Member Data Documentation