xmm::KMeans Class Reference

K-Means Clustering algorithm. More...

#include <xmmKMeans.hpp>

Inheritance diagram for xmm::KMeans:

Collaboration diagram for xmm::KMeans:

Public Types
enum	InitializationMode { InitializationMode::Random, InitializationMode::Biased }
	Type of initizalization of the K-Means algorithm. More...

Public Member Functions
	KMeans (unsigned int clusters=1)
	Default Constructor. More...
	KMeans (KMeans const &src)
	Copy Constructor. More...
KMeans &	operator= (KMeans const &src)
	Assignment. More...
void	train (TrainingSet *trainingSet)
	Train the K-Means clutering from the given training set. More...
void	reset ()
	Resets the fitering process (cluster association) More...
void	filter (std::vector< float > const &observation)
	filters a incoming observation (performs cluster association) More...
Json I/O
Json::Value	toJson () const
	Write the object to a JSON Structure. More...
void	fromJson (Json::Value const &root)
	Read the object from a JSON Structure. More...
Python File I/O
void	writeFile (char *fileName) const
	write method for python wrapping ('write' keyword forbidden, name has to be different) More...
void	readFile (char *fileName)
	read method for python wrapping ('read' keyword forbidden, name has to be different) More...
std::string	__str__ () const
	"print" method for python => returns the results of write method More...

Static Public Member Functions
static const float	DEFAULT_RELATIVE_VARIATION_THRESHOLD ()

Public Attributes
std::shared_ptr< SharedParameters >	shared_parameters
	Set of Parameters shared among classes. More...
Configuration< KMeans >	configuration
	Configuration (default and class-specific parameters) More...
Results< KMeans >	results
	Results of the cluster association after update with an observation. More...
std::vector< float >	centers
	Clusters centers. More...
KMeans::InitializationMode	initialization_mode
	Type of initialization for the K-Means Algorithm. More...

Static Public Attributes
static const unsigned int	DEFAULT_MAX_ITERATIONS = 50

Protected Member Functions
void	randomizeClusters (std::vector< float > const &trainingSetVariance)
	randomzie Cluster Centers (normalized width data variance) of the first phrase of the training set More...
void	initClustersWithFirstPhrase (std::shared_ptr< Phrase > phrase)
	Initialize the clusters using a regular segmentation of the first phrase of the training set. More...
void	updateCenters (std::vector< float > &previous_centers, TrainingSet *trainingSet)
	Update method for training. More...

Detailed Description

K-Means Clustering algorithm.

Member Enumeration Documentation

enum xmm::KMeans::InitializationMode

strong

Type of initizalization of the K-Means algorithm.

Enumerator
Random	random initialization (scaled using training set variance)
Biased	biased initialization: initialiazed with the first phrase

Constructor & Destructor Documentation

xmm::KMeans::KMeans

(

unsigned int

clusters = 1

)

Default Constructor.

Parameters

clusters

number of clusters

xmm::KMeans::KMeans

(

KMeans const &

src

)

Copy Constructor.

Parameters

src	Source Model

Member Function Documentation

std::string xmm::Writable::__str__ ( ) const

inlineinherited

"print" method for python => returns the results of write method

Warning

only defined if SWIGPYTHON is defined

static const float xmm::KMeans::DEFAULT_RELATIVE_VARIATION_THRESHOLD ( )

inlinestatic

void xmm::KMeans::filter

(

std::vector< float > const &

observation

)

filters a incoming observation (performs cluster association)

the results of the inference process are stored in the results attribute

Parameters

observation

observation vector

void xmm::KMeans::fromJson ( Json::Value const &  root )

virtual

Read the object from a JSON Structure.

Parameters

root	JSON value containing the object's information

Exceptions

JsonException

if the JSON value has a wrong format

Implements xmm::Writable.

void xmm::KMeans::initClustersWithFirstPhrase ( std::shared_ptr< Phrase >  phrase )

protected

Initialize the clusters using a regular segmentation of the first phrase of the training set.

xmm::KMeans & xmm::KMeans::operator=

(

KMeans const &

src

)

Assignment.

Parameters

src	Source Model

void xmm::KMeans::randomizeClusters ( std::vector< float > const &  trainingSetVariance )

protected

randomzie Cluster Centers (normalized width data variance) of the first phrase of the training set

void xmm::Writable::readFile ( char *  fileName )

inlineinherited

read method for python wrapping ('read' keyword forbidden, name has to be different)

Warning

only defined if SWIGPYTHON is defined

void xmm::KMeans::reset

(

)

Resets the fitering process (cluster association)

Json::Value xmm::KMeans::toJson ( ) const

virtual

Write the object to a JSON Structure.

Returns

Json value containing the object's information

Implements xmm::Writable.

void xmm::KMeans::train

(

TrainingSet *

trainingSet

)

Train the K-Means clutering from the given training set.

Parameters

trainingSet

Training Set

void xmm::KMeans::updateCenters ( std::vector< float > &  previous_centers, TrainingSet *  trainingSet  )

protected

Update method for training.

computes the cluster associated with each data points, and update Cluster centers

void xmm::Writable::writeFile ( char *  fileName ) const

inlineinherited

write method for python wrapping ('write' keyword forbidden, name has to be different)

Warning

only defined if SWIGPYTHON is defined

Member Data Documentation

std::vector<float> xmm::KMeans::centers

Clusters centers.

Configuration<KMeans> xmm::KMeans::configuration

Configuration (default and class-specific parameters)

const unsigned int xmm::KMeans::DEFAULT_MAX_ITERATIONS = 50

static

KMeans::InitializationMode xmm::KMeans::initialization_mode

Type of initialization for the K-Means Algorithm.

Results<KMeans> xmm::KMeans::results

Results of the cluster association after update with an observation.

std::shared_ptr<SharedParameters> xmm::KMeans::shared_parameters

Set of Parameters shared among classes.

---

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

• xmmKMeans.hpp
• xmmKMeans.cpp