#include <Clusterer.h>

Inheritance diagram for Clusterer:

Public Types
typedef std::map< std::string, Clusterer ()() >	StringClustererMap

Public Types inherited from MLBase
enum	BaseTypes { BASE_TYPE_NOT_SET =0, CLASSIFIER, REGRESSIFIER, CLUSTERER }

Public Member Functions
	Clusterer (void)

virtual	~Clusterer (void)

virtual bool	deepCopyFrom (const Clusterer *clusterer)

bool	copyBaseVariables (const Clusterer *clusterer)

virtual bool	train_ (MatrixFloat &trainingData)

virtual bool	train_ (ClassificationData &trainingData)

virtual bool	train_ (UnlabelledData &trainingData)

virtual bool	reset ()

virtual bool	clear ()

bool	getConverged () const

UINT	getNumClusters () const

UINT	getPredictedClusterLabel () const

Float	getMaximumLikelihood () const

Float	getBestDistance () const

VectorFloat	getClusterLikelihoods () const

VectorFloat	getClusterDistances () const

Vector< UINT >	getClusterLabels () const

std::string	getClustererType () const

bool	setNumClusters (const UINT numClusters)

Clusterer *	createNewInstance () const

Clusterer *	deepCopy () const

const Clusterer &	getBaseClusterer () const

Public Member Functions inherited from MLBase
	MLBase (void)

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 (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_ (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	saveModelToFile (std::string filename) const

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

virtual bool	loadModelFromFile (std::string filename)

virtual bool	loadModelFromFile (std::fstream &file)

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

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

virtual std::string	getModelAsString () const

DataType	getInputType () const

DataType	getOutputType () const

UINT	getBaseType () const

UINT	getNumInputFeatures () const

UINT	getNumInputDimensions () const

UINT	getNumOutputDimensions () const

UINT	getMinNumEpochs () const

UINT	getMaxNumEpochs () const

UINT	getValidationSetSize () const

UINT	getNumTrainingIterationsToConverge () const

Float	getMinChange () const

Float	getLearningRate () const

Float	getRootMeanSquaredTrainingError () const

Float	getTotalSquaredTrainingError () const

Float	getValidationSetAccuracy () const

VectorFloat	getValidationSetPrecision () const

VectorFloat	getValidationSetRecall () const

bool	getUseValidationSet () const

bool	getRandomiseTrainingOrder () const

bool	getTrained () const

bool	getModelTrained () const

bool	getScalingEnabled () const

bool	getIsBaseTypeClassifier () const

bool	getIsBaseTypeRegressifier () const

bool	getIsBaseTypeClusterer () const

bool	enableScaling (const bool useScaling)

bool	setMaxNumEpochs (const UINT maxNumEpochs)

bool	setMinNumEpochs (const UINT minNumEpochs)

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	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 (void)

virtual	~GRTBase (void)

bool	copyGRTBaseVariables (const GRTBase *GRTBase)

std::string	getClassType () 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)

GRTBase *	getGRTBasePointer ()

const GRTBase *	getGRTBasePointer () 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 Clusterer *	createInstanceFromString (std::string const &ClustererType)

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
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 Member Functions inherited from GRTBase
Float	SQR (const Float &x) const

Static Protected Member Functions
static StringClustererMap *	getMap ()

Protected Attributes
std::string	clustererType

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

DataType	inputType

DataType	outputType

UINT	baseType

UINT	numInputDimensions

UINT	numOutputDimensions

UINT	numTrainingIterationsToConverge

UINT	minNumEpochs

UINT	maxNumEpochs

UINT	validationSetSize

Float	learningRate

Float	minChange

Float	rootMeanSquaredTrainingError

Float	totalSquaredTrainingError

Float	validationSetAccuracy

bool	useValidationSet

bool	randomiseTrainingOrder

VectorFloat	validationSetPrecision

VectorFloat	validationSetRecall

Random	random

std::vector< TrainingResult >	trainingResults

TrainingResultsObserverManager	trainingResultsObserverManager

TestResultsObserverManager	testResultsObserverManager

Protected Attributes inherited from GRTBase
std::string	classType

DebugLog	debugLog

ErrorLog	errorLog

InfoLog	infoLog

TrainingLog	trainingLog

TestingLog	testingLog

WarningLog	warningLog

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.

Definition at line 38 of file Clusterer.h.

Member Typedef Documentation

typedef std::map< std::string, Clusterer*(*)() > Clusterer::StringClustererMap

Defines a map between a string (which will contain the name of the Clusterer, such as KMeans) and a function returns a new instance of that Clusterer

Definition at line 190 of file Clusterer.h.

Constructor & Destructor Documentation

Clusterer::Clusterer ( void )

Default Clusterer Constructor

Definition at line 65 of file Clusterer.cpp.

Clusterer::~Clusterer ( void )

virtual

Default Clusterer Destructor

Definition at line 79 of file Clusterer.cpp.

Member Function Documentation

bool Clusterer::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 MLBase.

Reimplemented in SelfOrganizingMap, HierarchicalClustering, ClusterTree, KMeans, and GaussianMixtureModels.

Definition at line 141 of file Clusterer.cpp.

bool Clusterer::copyBaseVariables ( const Clusterer * clusterer )

This copies the Clusterer base class variables from the Clusterer pointer to this instance.

Parameters

clusterer a pointer to a Clusterer from which the values will be copied to this instance

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

Definition at line 86 of file Clusterer.cpp.

Clusterer * Clusterer::createInstanceFromString ( std::string const & ClustererType )

static

Creates a new Clusterer instance based on the input string (which should contain the name of a valid Clusterer such as KMeans).

Parameters

string const &ClustererType: the name of the Clusterer

Returns: Clusterer*: a pointer to the new instance of the Clusterer

Definition at line 28 of file Clusterer.cpp.

Clusterer * Clusterer::createNewInstance ( ) const

Creates a new Clusterer instance based on the current clustererType string value.

Returns: Clusterer*: a pointer to the new instance of the Clusterer

Definition at line 36 of file Clusterer.cpp.

Clusterer * Clusterer::deepCopy ( ) const

This creates a new Clusterer instance and deep copies the variables and models from this instance into the deep copy. The function will then return a pointer to the new instance. It is up to the user who calls this function to delete the dynamic instance when they are finished using it.

Returns: returns a pointer to a new Clusterer instance which is a deep copy of this instance

Definition at line 40 of file Clusterer.cpp.

virtual bool Clusterer::deepCopyFrom ( const Clusterer * clusterer )

inlinevirtual

This is the base deep copy function for the Clusterer modules. This function should be overwritten by the derived class. This deep copies the variables and models from the Clusterer pointer to this Clusterer instance.

Parameters

clusterer a pointer to the Clusterer base class, this should be pointing to another instance of a matching derived class

Returns: returns true if the clone was successfull, false otherwise (the Clusterer base class will always return flase)

Reimplemented in SelfOrganizingMap, HierarchicalClustering, ClusterTree, KMeans, and GaussianMixtureModels.

Definition at line 58 of file Clusterer.h.

const Clusterer & Clusterer::getBaseClusterer ( ) const

Returns a pointer to this Clusterer. This is useful for a derived class so it can get easy access to this base Clusterer.

Returns: Clusterer&: a reference to this Clusterer

Definition at line 261 of file Clusterer.cpp.

Float Clusterer::getBestDistance ( ) const

Returns the current bestDistance value. The bestDistance value is computed during the prediction phase and is either the minimum or maximum distance, depending on the algorithm. This value will return 0 if a prediction has not been made.

Returns: returns the current bestDistance value

Definition at line 243 of file Clusterer.cpp.

VectorFloat Clusterer::getClusterDistances ( ) const

Gets a Vector of the cluster distances from the last prediction, this will be an N-dimensional Vector, where N is the number of clusters in the model. The exact form of these distances depends on the cluster algorithm.

Returns: returns a Vector of the cluster distances from the last prediction, an empty Vector will be returned if the model has not been trained

Definition at line 251 of file Clusterer.cpp.

std::string Clusterer::getClustererType ( ) const

Returns the classifeir type as a string.

Returns: returns the Clusterer type as a string

Definition at line 259 of file Clusterer.cpp.

Vector< UINT > Clusterer::getClusterLabels ( ) const

Gets a Vector of unsigned ints containing the label of each cluster, this will be an K-dimensional Vector, where K is the number of clusters in the model.

Returns: returns a Vector of unsigned ints containing the label of each cluster, an empty Vector will be returned if the model has not been trained

Definition at line 255 of file Clusterer.cpp.

VectorFloat Clusterer::getClusterLikelihoods ( ) const

Gets a Vector of the cluster likelihoods from the last prediction, this will be an N-dimensional Vector, where N is the number of clusters in the model. The exact form of these likelihoods depends on the cluster algorithm.

Returns: returns a Vector of the cluster likelihoods from the last prediction, an empty Vector will be returned if the model has not been trained

Definition at line 247 of file Clusterer.cpp.

bool Clusterer::getConverged ( ) const

Returns true if the training algorithm converged during the most recent training process. This function will return false if the model has not been trained.

Returns: returns true if the training algorithm converged succesfully, false otherwise

Definition at line 229 of file Clusterer.cpp.

Float Clusterer::getMaximumLikelihood ( ) const

Returns the current maximumLikelihood value. The maximumLikelihood value is computed during the prediction phase and is the likelihood of the most likely model. This value will return 0 if a prediction has not been made.

Returns: returns the current maximumLikelihood value

Definition at line 239 of file Clusterer.cpp.

UINT Clusterer::getNumClusters ( ) const

Returns the number of clusters in the model.

Returns: returns the number of clusters

Definition at line 234 of file Clusterer.cpp.

UINT Clusterer::getPredictedClusterLabel ( ) const

Returns the predicted cluster label.

Returns: returns the predicted cluster label

Definition at line 236 of file Clusterer.cpp.

Vector< std::string > Clusterer::getRegisteredClusterers ( )

static

Returns a Vector of the names of all Clusterers that have been registered with the base Clusterer.

Returns: Vector< std::string >: a Vector containing the names of the Clusterers that have been registered with the base Clusterer

Definition at line 54 of file Clusterer.cpp.

bool Clusterer::loadClustererSettingsFromFile ( std::fstream & file )

protected

Loads the core clusterer settings from a file.

Returns: returns true if the base settings were loaded, false otherwise

Definition at line 178 of file Clusterer.cpp.

bool Clusterer::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 MLBase.

Reimplemented in SelfOrganizingMap, HierarchicalClustering, KMeans, and GaussianMixtureModels.

Definition at line 127 of file Clusterer.cpp.

bool Clusterer::saveClustererSettingsToFile ( std::fstream & file ) const

protected

Saves the core clusterer settings to a file.

Returns: returns true if the base settings were saved, false otherwise

Definition at line 156 of file Clusterer.cpp.

bool Clusterer::setNumClusters ( const UINT numClusters )

Sets the number of clusters that will be used the next time a model is trained. This will clear any previous model. The number of clusters must be greater than zero.

Parameters

numClusters the number of clusters, must be greater than zero

Returns: returns true if the value was updated successfully, false otherwise

Definition at line 265 of file Clusterer.cpp.

bool Clusterer::train_ ( MatrixFloat & trainingData )

virtual

This is the main interface for training the clusterer model.

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 MLBase.

Reimplemented in SelfOrganizingMap, HierarchicalClustering, KMeans, GaussianMixtureModels, and ClusterTree.

Definition at line 113 of file Clusterer.cpp.

bool Clusterer::train_ ( ClassificationData & trainingData )

virtual

Override the main ClassificationData train function to pass MatrixFloat data to the Clusterer train function.

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 MLBase.

Reimplemented in SelfOrganizingMap, HierarchicalClustering, KMeans, and GaussianMixtureModels.

Definition at line 117 of file Clusterer.cpp.

bool Clusterer::train_ ( UnlabelledData & trainingData )

virtual

Override the main UnlabelledData train function to pass MatrixFloat data to the Clusterer train function.

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 MLBase.

Reimplemented in SelfOrganizingMap, HierarchicalClustering, KMeans, and GaussianMixtureModels.

Definition at line 122 of file Clusterer.cpp.

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

Public Types

Public Member Functions

Static Public Member Functions

Protected Member Functions

Static Protected Member Functions

Protected Attributes

Detailed Description

Member Typedef Documentation

Constructor & Destructor Documentation

Member Function Documentation