#include <KMeans.h>

Inheritance diagram for KMeans:

Public Member Functions
	KMeans (const UINT numClusters=10, const UINT minNumEpochs=5, const UINT maxNumEpochs=1000, const Float minChange=1.0e-5, const bool computeTheta=true)

	KMeans (const KMeans &rhs)

virtual	~KMeans ()

KMeans &	operator= (const KMeans &rhs)

virtual bool	deepCopyFrom (const Clusterer *clusterer)

virtual bool	reset ()

virtual bool	clear ()

bool	trainModel (MatrixFloat &data)

virtual bool	train_ (MatrixFloat &data)

virtual bool	train_ (ClassificationData &trainingData)

virtual bool	train_ (UnlabelledData &trainingData)

virtual bool	predict_ (VectorFloat &inputVector)

virtual bool	saveModelToFile (std::fstream &file) const

virtual bool	loadModelFromFile (std::fstream &file)

Float	getTheta ()

bool	getModelTrained ()

const VectorFloat &	getTrainingThetaLog () const

const MatrixFloat &	getClusters () const

const Vector< UINT > &	getClassLabelsVector () const

const Vector< UINT > &	getClassCountVector () const

bool	setComputeTheta (const bool computeTheta)

bool	setClusters (const MatrixFloat &clusters)

Public Member Functions inherited from Clusterer
	Clusterer (const std::string &id="")

virtual	~Clusterer (void)

bool	copyBaseVariables (const Clusterer *clusterer)

UINT	getNumClusters () const

UINT	getPredictedClusterLabel () const

Float	getMaximumLikelihood () const

Float	getBestDistance () const

VectorFloat	getClusterLikelihoods () const

VectorFloat	getClusterDistances () const

Vector< UINT >	getClusterLabels () const

	GRT_DEPRECATED_MSG ("getClustererType() is deprecated, use getId() or getBaseId() instead", std::string getClustererType() const )

bool	setNumClusters (const UINT numClusters)

Clusterer *	create () const

	GRT_DEPRECATED_MSG ("createNewInstance is deprecated, use create instead.", Clusterer *createNewInstance() const )

	GRT_DEPRECATED_MSG ("createInstanceFromString is deprecated, use create instead.", static Clusterer *createInstanceFromString(const std::string &id))

Clusterer *	deepCopy () const

const Clusterer &	getBaseClusterer () const

Public Member Functions inherited from MLBase
	MLBase (const std::string &id="", const BaseType type=BASE_TYPE_NOT_SET)

virtual	~MLBase (void)

bool	copyMLBaseVariables (const MLBase *mlBase)

virtual bool	train (ClassificationData trainingData)

virtual bool	train (RegressionData trainingData)

virtual bool	train_ (RegressionData &trainingData)

virtual bool	train (RegressionData trainingData, RegressionData validationData)

virtual bool	train_ (RegressionData &trainingData, RegressionData &validationData)

virtual bool	train (TimeSeriesClassificationData trainingData)

virtual bool	train_ (TimeSeriesClassificationData &trainingData)

virtual bool	train (ClassificationDataStream trainingData)

virtual bool	train_ (ClassificationDataStream &trainingData)

virtual bool	train (UnlabelledData trainingData)

virtual bool	train (MatrixFloat data)

virtual bool	predict (VectorFloat inputVector)

virtual bool	predict (MatrixFloat inputMatrix)

virtual bool	predict_ (MatrixFloat &inputMatrix)

virtual bool	map (VectorFloat inputVector)

virtual bool	map_ (VectorFloat &inputVector)

virtual bool	print () const

virtual bool	save (const std::string &filename) const

virtual bool	load (const std::string &filename)

virtual bool	save (std::fstream &file) const

virtual bool	load (std::fstream &file)

	GRT_DEPRECATED_MSG ("saveModelToFile(std::string filename) is deprecated, use save(const std::string &filename) instead", virtual bool saveModelToFile(const std::string &filename) const )

	GRT_DEPRECATED_MSG ("saveModelToFile(std::fstream &file) is deprecated, use save(std::fstream &file) instead", virtual bool saveModelToFile(std::fstream &file) const )

	GRT_DEPRECATED_MSG ("loadModelFromFile(std::string filename) is deprecated, use load(const std::string &filename) instead", virtual bool loadModelFromFile(const std::string &filename))

	GRT_DEPRECATED_MSG ("loadModelFromFile(std::fstream &file) is deprecated, use load(std::fstream &file) instead", virtual bool loadModelFromFile(std::fstream &file))

virtual bool	getModel (std::ostream &stream) const

virtual std::string	getModelAsString () const

DataType	getInputType () const

DataType	getOutputType () const

BaseType	getType () const

UINT	getNumInputFeatures () const

UINT	getNumInputDimensions () const

UINT	getNumOutputDimensions () const

UINT	getMinNumEpochs () const

UINT	getMaxNumEpochs () const

UINT	getBatchSize () const

UINT	getNumRestarts () const

UINT	getValidationSetSize () const

UINT	getNumTrainingIterationsToConverge () const

Float	getMinChange () const

Float	getLearningRate () const

Float	getRMSTrainingError () const

	GRT_DEPRECATED_MSG ("getRootMeanSquaredTrainingError() is deprecated, use getRMSTrainingError() instead", Float getRootMeanSquaredTrainingError() const )

Float	getTotalSquaredTrainingError () const

Float	getRMSValidationError () const

Float	getValidationSetAccuracy () const

VectorFloat	getValidationSetPrecision () const

VectorFloat	getValidationSetRecall () const

bool	getUseValidationSet () const

bool	getRandomiseTrainingOrder () const

bool	getTrained () const

	GRT_DEPRECATED_MSG ("getModelTrained() is deprecated, use getTrained() instead", bool getModelTrained() const )

bool	getConverged () const

bool	getScalingEnabled () const

bool	getIsBaseTypeClassifier () const

bool	getIsBaseTypeRegressifier () const

bool	getIsBaseTypeClusterer () const

bool	getTrainingLoggingEnabled () const

bool	getTestingLoggingEnabled () const

bool	enableScaling (const bool useScaling)

bool	setMaxNumEpochs (const UINT maxNumEpochs)

bool	setBatchSize (const UINT batchSize)

bool	setMinNumEpochs (const UINT minNumEpochs)

bool	setNumRestarts (const UINT numRestarts)

bool	setMinChange (const Float minChange)

bool	setLearningRate (const Float learningRate)

bool	setUseValidationSet (const bool useValidationSet)

bool	setValidationSetSize (const UINT validationSetSize)

bool	setRandomiseTrainingOrder (const bool randomiseTrainingOrder)

bool	setTrainingLoggingEnabled (const bool loggingEnabled)

bool	setTestingLoggingEnabled (const bool loggingEnabled)

bool	registerTrainingResultsObserver (Observer< TrainingResult > &observer)

bool	registerTestResultsObserver (Observer< TestInstanceResult > &observer)

bool	removeTrainingResultsObserver (const Observer< TrainingResult > &observer)

bool	removeTestResultsObserver (const Observer< TestInstanceResult > &observer)

bool	removeAllTrainingObservers ()

bool	removeAllTestObservers ()

bool	notifyTrainingResultsObservers (const TrainingResult &data)

bool	notifyTestResultsObservers (const TestInstanceResult &data)

MLBase *	getMLBasePointer ()

const MLBase *	getMLBasePointer () const

Vector< TrainingResult >	getTrainingResults () const

Public Member Functions inherited from GRTBase
	GRTBase (const std::string &id="")

virtual	~GRTBase (void)

bool	copyGRTBaseVariables (const GRTBase *GRTBase)

	GRT_DEPRECATED_MSG ("getClassType is deprecated, use getId() instead!", std::string getClassType() const )

std::string	getId () const

std::string	getLastWarningMessage () const

std::string	getLastErrorMessage () const

std::string	getLastInfoMessage () const

bool	setInfoLoggingEnabled (const bool loggingEnabled)

bool	setWarningLoggingEnabled (const bool loggingEnabled)

bool	setErrorLoggingEnabled (const bool loggingEnabled)

bool	setDebugLoggingEnabled (const bool loggingEnabled)

GRTBase *	getGRTBasePointer ()

const GRTBase *	getGRTBasePointer () const

Float	scale (const Float &x, const Float &minSource, const Float &maxSource, const Float &minTarget, const Float &maxTarget, const bool constrain=false)

Float	SQR (const Float &x) const

Public Member Functions inherited from Observer< TrainingResult >
virtual void	notify (const TrainingResult &data)

Public Member Functions inherited from Observer< TestInstanceResult >
virtual void	notify (const TestInstanceResult &data)

Static Public Member Functions
static std::string	getId ()

Static Public Member Functions inherited from Clusterer
static Clusterer *	create (std::string const &id)

static Vector< std::string >	getRegisteredClusterers ()

Static Public Member Functions inherited from GRTBase
static std::string	getGRTVersion (bool returnRevision=true)

static std::string	getGRTRevison ()

Protected Member Functions
UINT	estep (const MatrixFloat &data)

void	mstep (const MatrixFloat &data)

Float	calculateTheta (const MatrixFloat &data)

Float	SQR (const Float a)

Protected Member Functions inherited from Clusterer
bool	saveClustererSettingsToFile (std::fstream &file) const

bool	loadClustererSettingsFromFile (std::fstream &file)

Protected Member Functions inherited from MLBase
bool	saveBaseSettingsToFile (std::fstream &file) const

bool	loadBaseSettingsFromFile (std::fstream &file)

Protected Attributes
bool	computeTheta

UINT	numTrainingSamples
	Number of training examples.

UINT	nchg
	Number of values changes.

Float	finalTheta

MatrixFloat	clusters

Vector< UINT >	assign

Vector< UINT >	count

VectorFloat	thetaTracker

Protected Attributes inherited from Clusterer
UINT	numClusters
	Number of clusters in the model.

UINT	predictedClusterLabel
	Stores the predicted cluster label from the most recent predict( )

Float	maxLikelihood

Float	bestDistance

VectorFloat	clusterLikelihoods

VectorFloat	clusterDistances

Vector< UINT >	clusterLabels

bool	converged

Vector< MinMax >	ranges

Protected Attributes inherited from MLBase
bool	trained

bool	useScaling

bool	converged

DataType	inputType

DataType	outputType

BaseType	baseType

UINT	numInputDimensions

UINT	numOutputDimensions

UINT	numTrainingIterationsToConverge

UINT	minNumEpochs

UINT	maxNumEpochs

UINT	batchSize

UINT	validationSetSize

UINT	numRestarts

Float	learningRate

Float	minChange

Float	rmsTrainingError

Float	rmsValidationError

Float	totalSquaredTrainingError

Float	validationSetAccuracy

bool	useValidationSet

bool	randomiseTrainingOrder

VectorFloat	validationSetPrecision

VectorFloat	validationSetRecall

Random	random

Vector< TrainingResult >	trainingResults

TrainingResultsObserverManager	trainingResultsObserverManager

TestResultsObserverManager	testResultsObserverManager

TrainingLog	trainingLog

TestingLog	testingLog

Protected Attributes inherited from GRTBase
std::string	classId
	Stores the name of the class (e.g., MinDist)

DebugLog	debugLog

ErrorLog	errorLog

InfoLog	infoLog

WarningLog	warningLog

Additional Inherited Members
Public Types inherited from Clusterer
typedef std::map< std::string, Clusterer ()() >	StringClustererMap

Public Types inherited from MLBase
enum	BaseType { BASE_TYPE_NOT_SET =0, CLASSIFIER, REGRESSIFIER, CLUSTERER, PRE_PROCSSING, POST_PROCESSING, FEATURE_EXTRACTION, CONTEXT }

Static Protected Member Functions inherited from Clusterer
static StringClustererMap *	getMap ()

Detailed Description

GRT MIT License Copyright (c) <2012> <Nicholas Gillian, Media Lab, MIT>

Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:

The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

Examples:: ClusteringModulesExamples/KMeansExample/KMeansExample.cpp.

Definition at line 41 of file KMeans.h.

Constructor & Destructor Documentation

KMeans::KMeans	(	const UINT	numClusters = `10`,
		const UINT	minNumEpochs = `5`,
		const UINT	maxNumEpochs = `1000`,
		const Float	minChange = `1.0e-5`,
		const bool	computeTheta = `true`
	)

Default Constructor.

Definition at line 34 of file KMeans.cpp.

KMeans::KMeans ( const KMeans & rhs )

Defines how the data from the rhs KMeans should be copied to this KMeans

Parameters

rhs	another instance of a KMeans

Definition at line 50 of file KMeans.cpp.

KMeans::~KMeans ( )

virtual

Default Destructor

Definition at line 68 of file KMeans.cpp.

Member Function Documentation

bool KMeans::clear ( )

virtual

This function clears the Clusterer module, removing any trained model and setting all the base variables to their default values.

Returns: returns true if the derived class was cleared succesfully, false otherwise

Reimplemented from Clusterer.

Definition at line 490 of file KMeans.cpp.

bool KMeans::deepCopyFrom ( const Clusterer * clusterer )

virtual

This deep copies the variables and models from the Clusterer pointer to this KMeans instance. This overrides the base deep copy function for the Clusterer modules.

Parameters

clusterer a pointer to the Clusterer base class, this should be pointing to another KMeans instance

Returns: returns true if the clone was successfull, false otherwise

Reimplemented from Clusterer.

Definition at line 91 of file KMeans.cpp.

std::string KMeans::getId ( )

static

Gets a string that represents the KMeans class.

Returns: returns a string containing the ID of this class

Definition at line 28 of file KMeans.cpp.

bool KMeans::loadModelFromFile ( std::fstream & file )

virtual

This loads a trained KMeans model from a file. This overrides the loadModelFromFile function in the base class.

Parameters

file	a reference to the file the KMeans model will be loaded from

Returns: returns true if the model was loaded successfully, false otherwise

Definition at line 436 of file KMeans.cpp.

KMeans & KMeans::operator= ( const KMeans & rhs )

Defines how the data from the rhs KMeans should be copied to this KMeans

Parameters

rhs	another instance of a KMeans

Returns: returns a reference to this instance of the KMeans

Definition at line 71 of file KMeans.cpp.

bool KMeans::predict_ ( VectorFloat & inputVector )

virtual

This is the main prediction interface for all reference VectorFloat data. It overrides the predict_ function in the ML base class.

Parameters

inputVector a reference to the input Vector for prediction

Returns: returns true if the prediction was completed succesfully, false otherwise (the base class always returns false)

Reimplemented from MLBase.

Definition at line 190 of file KMeans.cpp.

bool KMeans::reset ( )

virtual

This resets the Clusterer. This overrides the reset function in the MLBase base class.

Returns: returns true if the Clusterer was reset, false otherwise

Reimplemented from Clusterer.

Definition at line 477 of file KMeans.cpp.

bool KMeans::saveModelToFile ( std::fstream & file ) const

virtual

This saves the trained KMeans model to a file. This overrides the saveModelToFile function in the base class.

Parameters

file	a reference to the file the KMeans model will be saved to

Returns: returns true if the model was saved successfully, false otherwise

Definition at line 408 of file KMeans.cpp.

bool KMeans::setClusters ( const MatrixFloat & clusters )

This function lets you set the models clusters. You can use this to initalize the cluster values for the training algorithm. If you do that, then you should call the trainModel to run the training algorithm so the cluster values do not get reset.

Parameters

const MatrixFloat &clusters: the initial cluster values that will be used to train the KMeans model

Returns: returns true if the model was loaded successfully, false otherwise

Definition at line 509 of file KMeans.cpp.

bool KMeans::train_ ( MatrixFloat & data )

virtual

This is the main training interface for referenced MatrixFloat data. It overrides the train_ function in the ML base class.

Parameters

trainingData a reference to the training data that will be used to train the ML model

Returns: returns true if the model was successfully trained, false otherwise

Reimplemented from Clusterer.

Definition at line 153 of file KMeans.cpp.

bool KMeans::train_ ( ClassificationData & trainingData )

virtual

This is the main training interface for reference ClassificationData data. It overrides the train_ function in the ML base class.

Parameters

trainingData a reference to the training data that will be used to train the ML model

Returns: returns true if the model was successfully trained, false otherwise

Reimplemented from Clusterer.

Definition at line 114 of file KMeans.cpp.

bool KMeans::train_ ( UnlabelledData & trainingData )

virtual

This is the main training interface for reference UnlabelledData data. It overrides the train_ function in the ML base class.

Parameters

trainingData a reference to the training data that will be used to train the ML model

Returns: returns true if the model was successfully trained, false otherwise

Reimplemented from Clusterer.

Definition at line 138 of file KMeans.cpp.

bool KMeans::trainModel ( MatrixFloat & data )

This is the main training algorithm for training a KMeans model. You should only call this function if you have manually set the clusters, otherwise you should use any of the train or train_ in functions.

Parameters

trainingData the training data that will be used to train the ML model

Returns: returns true if the model was successfully trained, false otherwise

Definition at line 249 of file KMeans.cpp.

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

Public Member Functions

Static Public Member Functions

Protected Member Functions

Protected Attributes

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

Member Function Documentation