CKNN Class Reference

---

Detailed Description

Class KNN, an implementation of the standard k-nearest neigbor classifier.

An example is classified to belong to the class of which the majority of the k closest examples belong to.

To avoid ties, k should be an odd number. To define how close examples are k-NN requires a CDistance object to work with (e.g., CEuclideanDistance ).

Note that k-NN has zero training time but classification times increase dramatically with the number of examples. Also note that k-NN is capable of multi-class-classification.

Definition at line 37 of file KNN.h.

Inheritance diagram for CKNN:

[legend]

List of all members.

Public Member Functions
	CKNN ()
	CKNN (int32_t k, CDistance *d, CLabels *trainlab)
virtual	~CKNN ()
virtual EClassifierType	get_classifier_type ()
virtual bool	train ()
virtual CLabels *	classify (CLabels *output=NULL)
virtual float64_t	classify_example (int32_t vec_idx)
	get output for example "vec_idx"
virtual bool	load (FILE *srcfile)
virtual bool	save (FILE *dstfile)
void	set_k (float64_t p_k)
float64_t	get_k ()
virtual const char *	get_name () const
Protected Attributes
float64_t	k
	the k parameter in KNN
int32_t	num_classes
	number of classes (i.e. number of values labels can take)
int32_t	min_label
	smallest label, i.e. -1
int32_t	num_train_labels
	number of train examples
int32_t *	train_labels
	the actual trainlabels

---

Constructor & Destructor Documentation

CKNN::CKNN

(

)

default constructor

Definition at line 17 of file KNN.cpp.

CKNN::CKNN	(	int32_t	k,
		CDistance *	d,
		CLabels *	trainlab
	)

constructor

Parameters:

	k	k
	d	distance
	trainlab	labels for training

Definition at line 22 of file KNN.cpp.

CKNN::~CKNN

(

)

[virtual]

Definition at line 31 of file KNN.cpp.

---

Member Function Documentation

CLabels * CKNN::classify

(

CLabels *

output = NULL

)

[virtual]

classify all examples

Parameters:

output

resulting labels

Returns:

resulting labels

histogram of classes and returned output

Reimplemented from CClassifier.

Definition at line 64 of file KNN.cpp.

virtual float64_t CKNN::classify_example

(

int32_t

vec_idx

)

[virtual]

get output for example "vec_idx"

Reimplemented from CClassifier.

Definition at line 73 of file KNN.h.

virtual EClassifierType CKNN::get_classifier_type

(

)

[virtual]

get classifier type

Returns:

classifier type KNN

Reimplemented from CClassifier.

Definition at line 56 of file KNN.h.

float64_t CKNN::get_k

(

)

get k

Returns:

k

Definition at line 107 of file KNN.h.

virtual const char* CKNN::get_name

(

)

const [virtual]

Returns:

object name

Implements CSGObject.

Definition at line 113 of file KNN.h.

bool CKNN::load

(

FILE *

srcfile

)

[virtual]

load from file

Parameters:

srcfile

file to load from

Returns:

if loading was successful

Reimplemented from CClassifier.

Definition at line 139 of file KNN.cpp.

bool CKNN::save

(

FILE *

dstfile

)

[virtual]

save to file

Parameters:

dstfile

file to save to

Returns:

if saving was successful

Reimplemented from CClassifier.

Definition at line 144 of file KNN.cpp.

void CKNN::set_k

(

float64_t

p_k

)

set k

Parameters:

p_k

new k

Definition at line 97 of file KNN.h.

bool CKNN::train

(

)

[virtual]

train classifier

Returns:

if training was successful

Reimplemented from CClassifier.

Definition at line 36 of file KNN.cpp.

---

Member Data Documentation

float64_t CKNN::k [protected]

the k parameter in KNN

Definition at line 117 of file KNN.h.

int32_t CKNN::min_label [protected]

smallest label, i.e. -1

Definition at line 123 of file KNN.h.

int32_t CKNN::num_classes [protected]

number of classes (i.e. number of values labels can take)

Definition at line 120 of file KNN.h.

int32_t CKNN::num_train_labels [protected]

number of train examples

Definition at line 126 of file KNN.h.

int32_t* CKNN::train_labels [protected]

the actual trainlabels

Definition at line 129 of file KNN.h.

---

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

• KNN.h
• KNN.cpp