#include <Tree.h>

Inheritance diagram for Tree:

Public Types
enum	TrainingMode { BEST_ITERATIVE_SPILT =0, BEST_RANDOM_SPLIT, NUM_TRAINING_MODES }

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

Public Member Functions
	Tree (const UINT numSplittingSteps=100, const UINT minNumSamplesPerNode=5, const UINT maxDepth=10, const bool removeFeaturesAtEachSpilt=false, const TrainingMode trainingMode=BEST_ITERATIVE_SPILT)

virtual	~Tree (void)

virtual bool	clear () override

virtual bool	print () const override

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

virtual Node *	deepCopyTree () const

const Node *	getTree () const

UINT	getTrainingMode () const

UINT	getNumSplittingSteps () const

UINT	getMinNumSamplesPerNode () const

UINT	getMaxDepth () const

UINT	getPredictedNodeID () const

bool	getRemoveFeaturesAtEachSpilt () const

bool	setTrainingMode (const TrainingMode trainingMode)

bool	setNumSplittingSteps (const UINT numSplittingSteps)

bool	setMinNumSamplesPerNode (const UINT minNumSamplesPerNode)

bool	setMaxDepth (const UINT maxDepth)

bool	setRemoveFeaturesAtEachSpilt (const bool removeFeaturesAtEachSpilt)

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_ (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_ (UnlabelledData &trainingData)

virtual bool	train (MatrixFloat data)

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	reset ()

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 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)

Protected Attributes
TrainingMode	trainingMode

UINT	numSplittingSteps

UINT	minNumSamplesPerNode

UINT	maxDepth

bool	removeFeaturesAtEachSpilt

Node *	tree

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

static std::string	getGRTRevison ()

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

bool	loadBaseSettingsFromFile (std::fstream &file)

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 Tree.h.

Constructor & Destructor Documentation

GRT_BEGIN_NAMESPACE Tree::Tree	(	const UINT	numSplittingSteps = `100`,
		const UINT	minNumSamplesPerNode = `5`,
		const UINT	maxDepth = `10`,
		const bool	removeFeaturesAtEachSpilt = `false`,
		const TrainingMode	trainingMode = `BEST_ITERATIVE_SPILT`
	)

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
removeFeaturesAtEachSpilt	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

Definition at line 26 of file Tree.cpp.

Tree::~Tree ( void )

virtual

Default Destructor

Definition at line 36 of file Tree.cpp.

Member Function Documentation

bool Tree::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 MLBase.

Definition at line 41 of file Tree.cpp.

Node * Tree::deepCopyTree ( ) const

virtual

Deep copies the tree, returning a pointer to the new 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 74 of file Tree.cpp.

UINT Tree::getMaxDepth ( ) const

Gets the maximum depth of the tree.

Returns: returns the maximum depth of the tree

Definition at line 99 of file Tree.cpp.

UINT Tree::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 95 of file Tree.cpp.

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

overridevirtual

This function adds the current model to the formatted stream. This function should be overwritten by the derived class.

Parameters

file	a reference to the stream the model will be added to

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

Reimplemented from MLBase.

Definition at line 63 of file Tree.cpp.

UINT Tree::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 91 of file Tree.cpp.

UINT Tree::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 103 of file Tree.cpp.

bool Tree::getRemoveFeaturesAtEachSpilt ( ) const

Gets if a feature is removed at each spilt 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 112 of file Tree.cpp.

UINT Tree::getTrainingMode ( ) const

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

Returns: returns the training mode

Definition at line 87 of file Tree.cpp.

const Node * Tree::getTree ( ) const

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

Returns: returns a const pointer to the tree

Definition at line 83 of file Tree.cpp.

bool Tree::print ( ) const

overridevirtual

Prints the tree to std::cout.

Returns: returns true if the model was printed

Reimplemented from MLBase.

Definition at line 52 of file Tree.cpp.

bool Tree::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 143 of file Tree.cpp.

bool Tree::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 134 of file Tree.cpp.

bool Tree::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 125 of file Tree.cpp.

bool Tree::setRemoveFeaturesAtEachSpilt ( const bool removeFeaturesAtEachSpilt )

Sets if a feature is removed at each spilt 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

removeFeaturesAtEachSpilt 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 152 of file Tree.cpp.

bool Tree::setTrainingMode ( const 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 116 of file Tree.cpp.

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

Public Types

Public Member Functions

Protected Attributes

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

Member Function Documentation