#include <ClusterTree.h>

Inheritance diagram for ClusterTree:

Public Member Functions
	ClusterTree (const UINT numSplittingSteps=100, const UINT minNumSamplesPerNode=5, const UINT maxDepth=10, const bool removeFeaturesAtEachSplit=false, const Tree::TrainingMode trainingMode=Tree::BEST_ITERATIVE_SPILT, const bool useScaling=false, const Float minRMSErrorPerNode=0.01)

	ClusterTree (const ClusterTree &rhs)

virtual	~ClusterTree (void)

ClusterTree &	operator= (const ClusterTree &rhs)

virtual bool	deepCopyFrom (const Clusterer *cluster) override

virtual bool	train_ (MatrixFloat &trainingData) override

virtual bool	predict_ (VectorFloat &inputVector) override

virtual bool	clear () override

virtual bool	print () const override

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

virtual bool	loadModelFromFile (std::fstream &file) override

ClusterTreeNode *	deepCopyTree () const

const ClusterTreeNode *	getTree () const

UINT	getPredictedClusterLabel () const

Float	getMinRMSErrorPerNode () const

Tree::TrainingMode	getTrainingMode () const

UINT	getNumSplittingSteps () const

UINT	getMinNumSamplesPerNode () const

UINT	getMaxDepth () const

UINT	getPredictedNodeID () const

bool	getRemoveFeaturesAtEachSplit () const

bool	setTrainingMode (const Tree::TrainingMode trainingMode)

bool	setNumSplittingSteps (const UINT numSplittingSteps)

bool	setMinNumSamplesPerNode (const UINT minNumSamplesPerNode)

bool	setMaxDepth (const UINT maxDepth)

bool	setRemoveFeaturesAtEachSplit (const bool removeFeaturesAtEachSplit)

bool	setMinRMSErrorPerNode (const Float minRMSErrorPerNode)

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

virtual	~Clusterer (void)

bool	copyBaseVariables (const Clusterer *clusterer)

virtual bool	train_ (ClassificationData &trainingData) override

virtual bool	train_ (UnlabelledData &trainingData) override

virtual bool	reset () override

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	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
ClusterTreeNode *	buildTree (const MatrixFloat &trainingData, ClusterTreeNode *parent, Vector< UINT > features, UINT &clusterLabel, UINT nodeID)

bool	computeBestSplit (const MatrixFloat &trainingData, const Vector< UINT > &features, UINT &featureIndex, Float &threshold, Float &minError)

bool	computeBestSplitBestIterativeSplit (const MatrixFloat &trainingData, const Vector< UINT > &features, UINT &featureIndex, Float &threshold, Float &minError)

bool	computeBestSplitBestRandomSplit (const MatrixFloat &trainingData, const Vector< UINT > &features, UINT &featureIndex, Float &threshold, Float &minError)

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
Node *	tree

UINT	minNumSamplesPerNode

UINT	maxDepth

UINT	numSplittingSteps

bool	removeFeaturesAtEachSplit

Tree::TrainingMode	trainingMode

Float	minRMSErrorPerNode

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.

Definition at line 40 of file ClusterTree.h.

Constructor & Destructor Documentation

ClusterTree::ClusterTree	(	const UINT	numSplittingSteps = `100`,
		const UINT	minNumSamplesPerNode = `5`,
		const UINT	maxDepth = `10`,
		const bool	removeFeaturesAtEachSplit = `false`,
		const Tree::TrainingMode	trainingMode = `Tree::BEST_ITERATIVE_SPILT`,
		const bool	useScaling = `false`,
		const Float	minRMSErrorPerNode = `0.01`
	)

Default Constructor

Parameters

numSplittingSteps	sets the number of steps that will be used to search for the best spliting value for each node. Default value = 100
minNumSamplesPerNode	sets the minimum number of samples that are allowed per node, if the number of samples is below that, the node will become a leafNode. Default value = 5
maxDepth	sets the maximum depth of the tree. Default value = 10
removeFeaturesAtEachSplit	sets if a feature is removed at each spilt so it can not be used again. Default value = false
trainingMode	sets the training mode, this should be one of the TrainingMode enums. Default value = BEST_ITERATIVE_SPILT
useScaling	sets if the training and real-time data should be scaled between [0 1]. Default value = false
minRMSErrorPerNode	sets the minimum RMS error that allowed per node, if the RMS error is below that, the node will become a leafNode. Default value = 0.01

Definition at line 36 of file ClusterTree.cpp.

ClusterTree::ClusterTree ( const ClusterTree & rhs )

Defines the copy constructor.

Parameters

rhs	the instance from which all the data will be copied into this instance

Definition at line 48 of file ClusterTree.cpp.

ClusterTree::~ClusterTree ( void )

virtual

Default Destructor

Definition at line 55 of file ClusterTree.cpp.

Member Function Documentation

bool ClusterTree::clear ( )

overridevirtual

This overrides the clear function in the Regressifier base class. It will completely clear the ML module, removing any trained model and setting all the base variables to their default values.

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

Reimplemented from Clusterer.

Definition at line 202 of file ClusterTree.cpp.

bool ClusterTree::deepCopyFrom ( const Clusterer * cluster )

overridevirtual

This is required for the Gesture Recognition Pipeline for when the pipeline.setRegressifier(...) method is called. It clones the data from the Base Class Clusterer pointer into this instance

Parameters

cluster a pointer to the Clusterer Base Class, this should be pointing to another ClusterTree instance

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

Reimplemented from Clusterer.

Definition at line 84 of file ClusterTree.cpp.

ClusterTreeNode * ClusterTree::deepCopyTree ( ) const

Deep copies the tree, returning a pointer to the new clusterer tree. The user is in charge of cleaning up the memory so must delete the pointer when they no longer need it. NULL will be returned if the tree could not be copied.

Returns: returns a pointer to a deep copy of the tree

Definition at line 369 of file ClusterTree.cpp.

std::string ClusterTree::getId ( )

static

Gets a string that represents the ClusterTree class.

Returns: returns a string containing the ID of this class

Definition at line 28 of file ClusterTree.cpp.

UINT ClusterTree::getMaxDepth ( ) const

Gets the maximum depth of the tree.

Returns: returns the maximum depth of the tree

Definition at line 402 of file ClusterTree.cpp.

UINT ClusterTree::getMinNumSamplesPerNode ( ) const

Gets the minimum number of samples that are allowed per node, if the number of samples at a node is below this value then the node will automatically become a leaf node.

Returns: returns the minimum number of samples that are allowed per node

Definition at line 398 of file ClusterTree.cpp.

Float ClusterTree::getMinRMSErrorPerNode ( ) const

Gets the minimum root mean squared error value that needs to be exceeded for the tree to continue growing at a specific node. If the RMS error is below this value then the node will be made into a leaf node.

Returns: returns the minimum RMS error per node

Definition at line 386 of file ClusterTree.cpp.

UINT ClusterTree::getNumSplittingSteps ( ) const

Gets the number of steps that will be used to search for the best spliting value for each node.

If the trainingMode is set to BEST_ITERATIVE_SPILT, then the numSplittingSteps controls how many iterative steps there will be per feature. If the trainingMode is set to BEST_RANDOM_SPLIT, then the numSplittingSteps controls how many random searches there will be per feature.

Returns: returns the number of steps that will be used to search for the best spliting value for each node

Definition at line 394 of file ClusterTree.cpp.

UINT ClusterTree::getPredictedClusterLabel ( ) const

Gets the predicted cluster label from the most recent call to predict( ... ). The cluster label will be zero if the model has been trained but no prediction has been run.

Returns: returns the most recent predicted cluster label

Definition at line 382 of file ClusterTree.cpp.

UINT ClusterTree::getPredictedNodeID ( ) const

This function returns the predictedNodeID, this is ID of the leaf node that was reached during the last prediction call

Returns: returns the predictedNodeID, this will be zero if the tree does not exist or predict has not been called

Definition at line 406 of file ClusterTree.cpp.

bool ClusterTree::getRemoveFeaturesAtEachSplit ( ) const

Gets if a feature is removed at each split so it can not be used again.

Returns: returns true if a feature is removed at each spilt so it can not be used again, false otherwise

Definition at line 415 of file ClusterTree.cpp.

Tree::TrainingMode ClusterTree::getTrainingMode ( ) const

Gets the current training mode. This will be one of the TrainingModes enums.

Returns: returns the training mode

Definition at line 390 of file ClusterTree.cpp.

const ClusterTreeNode * ClusterTree::getTree ( ) const

Gets a pointer to the tree. NULL will be returned if the decision tree model has not be trained.

Returns: returns a const pointer to the tree

Definition at line 378 of file ClusterTree.cpp.

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

overridevirtual

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

Parameters

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

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

Definition at line 258 of file ClusterTree.cpp.

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

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

Parameters

rhs	another instance of a ClusterTree

Returns: returns a pointer to this instance of the ClusterTree

Definition at line 60 of file ClusterTree.cpp.

bool ClusterTree::predict_ ( VectorFloat & inputVector )

overridevirtual

This predicts the class of the inputVector. This overrides the predict function in the ML base class.

Parameters

VectorFloat inputVector: the input Vector to predict

Returns: returns true if the prediction was performed, false otherwise

Reimplemented from MLBase.

Definition at line 169 of file ClusterTree.cpp.

bool ClusterTree::print ( ) const

overridevirtual

Prints the tree to std::cout.

Returns: returns true if the model was printed

Reimplemented from MLBase.

Definition at line 216 of file ClusterTree.cpp.

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

overridevirtual

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

Parameters

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

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

Definition at line 222 of file ClusterTree.cpp.

bool ClusterTree::setMaxDepth ( const UINT maxDepth )

Sets the maximum depth of the tree, any node that reaches this depth will automatically become a leaf node. Value must be larger than zero.

Parameters

maxDepth the maximum depth of the tree

Returns: returns true if the parameter was set, false otherwise

Definition at line 446 of file ClusterTree.cpp.

bool ClusterTree::setMinNumSamplesPerNode ( const UINT minNumSamplesPerNode )

Sets the minimum number of samples that are allowed per node, if the number of samples at a node is below this value then the node will automatically become a leaf node. Value must be larger than zero.

Parameters

minNumSamplesPerNode the minimum number of samples that are allowed per node

Returns: returns true if the parameter was set, false otherwise

Definition at line 437 of file ClusterTree.cpp.

bool ClusterTree::setMinRMSErrorPerNode ( const Float minRMSErrorPerNode )

Sets the minimum RMS error that needs to be exceeded for the tree to continue growing at a specific node.

Returns: returns true if the parameter was updated

Definition at line 460 of file ClusterTree.cpp.

bool ClusterTree::setNumSplittingSteps ( const UINT numSplittingSteps )

Sets the number of steps that will be used to search for the best spliting value for each node.

If the trainingMode is set to BEST_ITERATIVE_SPILT, then the numSplittingSteps controls how many iterative steps there will be per feature. If the trainingMode is set to BEST_RANDOM_SPLIT, then the numSplittingSteps controls how many random searches there will be per feature.

A higher value will increase the chances of building a better model, but will take longer to train the model. Value must be larger than zero.

Parameters

numSplittingSteps sets the number of steps that will be used to search for the best spliting value for each node.

Returns: returns true if the parameter was set, false otherwise

Definition at line 428 of file ClusterTree.cpp.

bool ClusterTree::setRemoveFeaturesAtEachSplit ( const bool removeFeaturesAtEachSplit )

Sets if a feature is removed at each split so it can not be used again. If true then the best feature selected at each node will be removed so it can not be used in any children of that node. If false, then the feature that provides the best spilt at each node will be used, regardless of how many times it has been used again.

Parameters

removeFeaturesAtEachSplit if true, then each feature is removed at each spilt so it can not be used again

Returns: returns true if the parameter was set, false otherwise

Definition at line 455 of file ClusterTree.cpp.

bool ClusterTree::setTrainingMode ( const Tree::TrainingMode trainingMode )

Sets the training mode, this should be one of the TrainingModes enums.

Parameters

trainingMode the new trainingMode, this should be one of the TrainingModes enums

Returns: returns true if the trainingMode was set successfully, false otherwise

Definition at line 419 of file ClusterTree.cpp.

bool ClusterTree::train_ ( MatrixFloat & trainingData )

overridevirtual

This trains the ClusterTree model, using the labelled regression data. This overrides the train function in the ML base class.

Parameters

trainingData a reference to the training data

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

Reimplemented from Clusterer.

Definition at line 114 of file ClusterTree.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