CDomainAdaptationSVMLinear Class Reference

---

Detailed Description

class DomainAdaptationSVMLinear

Definition at line 25 of file DomainAdaptationSVMLinear.h.

Inheritance diagram for CDomainAdaptationSVMLinear:

List of all members.

Public Member Functions
	CDomainAdaptationSVMLinear ()
	CDomainAdaptationSVMLinear (float64_t C, CDotFeatures *f, CLabels *lab, CLinearMachine *presvm, float64_t B)
virtual	~CDomainAdaptationSVMLinear ()
void	init (CLinearMachine *presvm, float64_t B)
virtual EClassifierType	get_classifier_type ()
virtual CLabels *	apply (CDotFeatures *data)
virtual CLinearMachine *	get_presvm ()
virtual float64_t	get_B ()
virtual float64_t	get_train_factor ()
virtual void	set_train_factor (float64_t factor)
virtual const char *	get_name () const
Protected Member Functions
virtual bool	is_presvm_sane ()
virtual bool	train_machine (CDotFeatures *data=NULL)
Protected Attributes
CLinearMachine *	presvm
float64_t	B
float64_t	train_factor

---

Constructor & Destructor Documentation

CDomainAdaptationSVMLinear

(

)

default constructor

Definition at line 24 of file DomainAdaptationSVMLinear.cpp.

CDomainAdaptationSVMLinear	(	float64_t	C,
		CDotFeatures *	f,
		CLabels *	lab,
		CLinearMachine *	presvm,
		float64_t	B
	)

constructor

Parameters:

	C	cost constant C
	f	features
	lab	labels
	presvm	trained SVM to regularize against
	B	trade-off constant B

Definition at line 30 of file DomainAdaptationSVMLinear.cpp.

~CDomainAdaptationSVMLinear

(

)

[virtual]

destructor

Definition at line 37 of file DomainAdaptationSVMLinear.cpp.

---

Member Function Documentation

CLabels * apply

(

CDotFeatures *

data

)

[virtual]

classify objects

Parameters:

data

(test)data to be classified

Returns:

classified labels

Definition at line 200 of file DomainAdaptationSVMLinear.cpp.

float64_t get_B

(

)

[virtual]

getter for regularization parameter B

Returns:

regularization parameter B

Definition at line 182 of file DomainAdaptationSVMLinear.cpp.

virtual EClassifierType get_classifier_type

(

)

[virtual]

get classifier type

Returns:

classifier type DASVMLINEAR

Reimplemented from CLibLinear.

Definition at line 60 of file DomainAdaptationSVMLinear.h.

virtual const char* get_name

(

)

const [virtual]

get linear term

Returns:

lin the linear term

object name

Reimplemented from CLibLinear.

Definition at line 114 of file DomainAdaptationSVMLinear.h.

CLinearMachine * get_presvm

(

)

[virtual]

returns SVM that is used as prior information

Returns:

presvm

Definition at line 176 of file DomainAdaptationSVMLinear.cpp.

float64_t get_train_factor

(

)

[virtual]

getter for train_factor

Returns:

train_factor

Definition at line 188 of file DomainAdaptationSVMLinear.cpp.

void init	(	CLinearMachine *	presvm,
		float64_t	B
	)

init SVM

Parameters:

	presvm	trained SVM to regularize against
	B	trade-off constant B

Definition at line 45 of file DomainAdaptationSVMLinear.cpp.

bool is_presvm_sane

(

)

[protected, virtual]

check sanity of presvm

Returns:

true if sane, throws SG_ERROR otherwise

Definition at line 74 of file DomainAdaptationSVMLinear.cpp.

void set_train_factor

(

float64_t

factor

)

[virtual]

setter for train_factor

Definition at line 194 of file DomainAdaptationSVMLinear.cpp.

bool train_machine

(

CDotFeatures *

data = NULL

)

[protected, virtual]

train SVM classifier

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

Definition at line 97 of file DomainAdaptationSVMLinear.cpp.

---

Member Data Documentation

float64_t B [protected]

regularization parameter B

Definition at line 141 of file DomainAdaptationSVMLinear.h.

CLinearMachine* presvm [protected]

SVM to regularize against

Definition at line 137 of file DomainAdaptationSVMLinear.h.

float64_t train_factor [protected]

flag to switch off regularization in training

Definition at line 145 of file DomainAdaptationSVMLinear.h.

---

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

• DomainAdaptationSVMLinear.h
• DomainAdaptationSVMLinear.cpp