Inheritance diagram for ClassificationData:

Public Member Functions
	ClassificationData (UINT numDimensions=0, std::string datasetName="NOT_SET", std::string infoText="")

	ClassificationData (const ClassificationData &rhs)

virtual	~ClassificationData ()

ClassificationData &	operator= (const ClassificationData &rhs)

ClassificationSample &	operator[] (const UINT &i)

const ClassificationSample &	operator[] (const UINT &i) const

void	clear ()

bool	setNumDimensions (UINT numDimensions)

bool	setDatasetName (std::string datasetName)

bool	setInfoText (std::string infoText)

bool	setClassNameForCorrespondingClassLabel (const std::string className, const UINT classLabel)

bool	setAllowNullGestureClass (const bool allowNullGestureClass)

bool	addSample (const UINT classLabel, const VectorFloat &sample)

bool	removeSample (const UINT index)

bool	removeLastSample ()

bool	reserve (const UINT M)

bool	addClass (const UINT classLabel, const std::string className="NOT_SET")

UINT	removeClass (const UINT classLabel)

UINT	eraseAllSamplesWithClassLabel (const UINT classLabel)

bool	relabelAllSamplesWithClassLabel (const UINT oldClassLabel, const UINT newClassLabel)

bool	setExternalRanges (const Vector< MinMax > &externalRanges, const bool useExternalRanges=false)

bool	enableExternalRangeScaling (const bool useExternalRanges)

bool	scale (const Float minTarget, const Float maxTarget)

bool	scale (const Vector< MinMax > &ranges, const Float minTarget, const Float maxTarget)

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

bool	load (const std::string &filename)

bool	saveDatasetToFile (const std::string &filename) const

bool	loadDatasetFromFile (const std::string &filename)

bool	saveDatasetToCSVFile (const std::string &filename) const

bool	loadDatasetFromCSVFile (const std::string &filename, const UINT classLabelColumnIndex=0)

bool	printStats () const

bool	sortClassLabels ()

bool	merge (const ClassificationData &data)

	GRT_DEPRECATED_MSG ("partition(...) is deprecated, use split(...) instead", ClassificationData partition(const UINT partitionPercentage, const bool useStratifiedSampling=false))

ClassificationData	split (const UINT splitPercentage, const bool useStratifiedSampling=false)

bool	spiltDataIntoKFolds (const UINT K, const bool useStratifiedSampling=false)

ClassificationData	getTrainingFoldData (const UINT foldIndex) const

ClassificationData	getTestFoldData (const UINT foldIndex) const

ClassificationData	getClassData (const UINT classLabel) const

ClassificationData	getBootstrappedDataset (const UINT numSamples=0, const bool balanceDataset=false) const

RegressionData	reformatAsRegressionData () const

UnlabelledData	reformatAsUnlabelledData () const

std::string	getDatasetName () const

std::string	getInfoText () const

std::string	getStatsAsString () const

UINT	getNumDimensions () const

UINT	getNumSamples () const

UINT	getNumClasses () const

UINT	getMinimumClassLabel () const

UINT	getMaximumClassLabel () const

UINT	getClassLabelIndexValue (const UINT classLabel) const

std::string	getClassNameForCorrespondingClassLabel (const UINT classLabel) const

Vector< MinMax >	getRanges () const

Vector< UINT >	getClassLabels () const

Vector< UINT >	getNumSamplesPerClass () const

Vector< ClassTracker >	getClassTracker () const

MatrixFloat	getClassHistogramData (const UINT classLabel, const UINT numBins) const

Vector< MatrixFloat >	getHistogramData (const UINT numBins) const

Vector< ClassificationSample >	getClassificationData () const

VectorFloat	getClassProbabilities () const

VectorFloat	getClassProbabilities (const Vector< UINT > &classLabels) const

VectorFloat	getMean () const

VectorFloat	getStdDev () const

MatrixFloat	getClassMean () const

MatrixFloat	getClassStdDev () const

MatrixFloat	getCovarianceMatrix () const

Vector< UINT >	getClassDataIndexes (const UINT classLabel) const

MatrixDouble	getDataAsMatrixDouble () const

MatrixFloat	getDataAsMatrixFloat () 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

Static Public Member Functions
static bool	generateGaussDataset (const std::string filename, const UINT numSamples=10000, const UINT numClasses=10, const UINT numDimensions=3, const Float range=10, const Float sigma=1)

static ClassificationData	generateGaussDataset (const UINT numSamples=10000, const UINT numClasses=10, const UINT numDimensions=3, const Float range=10, const Float sigma=1)

static ClassificationData	generateGaussLinearDataset (const UINT numSamples=10000, const UINT numClasses=10, const UINT numDimensions=3, const Float range=10, const Float sigma=1)

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

static std::string	getGRTRevison ()

Additional Inherited Members
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

Detailed Description

Examples:: ClassificationModulesExamples/AdaBoostExample/AdaBoostExample.cpp, ClassificationModulesExamples/ANBCExample/ANBCExample.cpp, ClassificationModulesExamples/BAGExample/BAGExample.cpp, ClassificationModulesExamples/DecisionTreeExample/DecisionTreeExample.cpp, ClassificationModulesExamples/GMMExample/GMMExample.cpp, ClassificationModulesExamples/KNNExample/KNNExample.cpp, ClassificationModulesExamples/MinDistExample/MinDistExample.cpp, ClassificationModulesExamples/RandomForestsExample/RandomForestsExample.cpp, ClassificationModulesExamples/SoftmaxExample/SoftmaxExample.cpp, ClassificationModulesExamples/SVMExample/SVMExample.cpp, ClusteringModulesExamples/KMeansExample/KMeansExample.cpp, and Tutorials/MachineLearning101/MachineLearning101.cpp.

Definition at line 43 of file ClassificationData.h.

Constructor & Destructor Documentation

GRT_BEGIN_NAMESPACE ClassificationData::ClassificationData	(	UINT	numDimensions = `0`,
		std::string	datasetName = `"NOT_SET"`,
		std::string	infoText = `""`
	)

Constructor, sets the name of the dataset and the number of dimensions of the training data. The name of the dataset should not contain any spaces.

Parameters

numDimensions	the number of dimensions of the training data, should be an unsigned integer greater than 0
datasetName	the name of the dataset, should not contain any spaces
infoText	some info about the data in this dataset, this can contain spaces

Definition at line 26 of file ClassificationData.cpp.

ClassificationData::ClassificationData ( const ClassificationData & rhs )

Copy Constructor, copies the ClassificationData from the rhs instance to this instance

Parameters

rhs	another instance of the ClassificationData class from which the data will be copied to this instance

Definition at line 41 of file ClassificationData.cpp.

ClassificationData::~ClassificationData ( )

virtual

Default Destructor

Definition at line 45 of file ClassificationData.cpp.

Member Function Documentation

bool ClassificationData::addClass	(	const UINT	classLabel,
		const std::string	className = `"NOT_SET"`
	)

This function adds the class with the classLabel to the class tracker. If the class tracker already contains the classLabel then the function will return false.

Parameters

classLabel	the class label you want to add to the classTracker
className	the name associated with the new class

Returns: returns true if the classLabel was added, false otherwise

Definition at line 241 of file ClassificationData.cpp.

bool ClassificationData::addSample	(	const UINT	classLabel,
		const VectorFloat &	sample
	)

Adds a new labelled sample to the dataset. The dimensionality of the sample should match the number of dimensions in the ClassificationData. The class label should be greater than zero (as zero is used as the default null rejection class label).

Parameters

classLabel	the class label of the corresponding sample
sample	the new sample you want to add to the dataset. The dimensionality of this sample should match the number of dimensions in the ClassificationData

Returns: true if the sample was correctly added to the dataset, false otherwise

Definition at line 133 of file ClassificationData.cpp.

void ClassificationData::clear ( )

Clears any previous training data and counters

Definition at line 70 of file ClassificationData.cpp.

bool ClassificationData::enableExternalRangeScaling ( const bool useExternalRanges )

Sets if the dataset should be scaled using an external range (if useExternalRanges == true) or the ranges of the dataset (if false). The external ranges need to be set FIRST before calling this function, otherwise it will return false.

Parameters

useExternalRanges sets if these ranges should be used to scale the dataset

Returns: returns true if the useExternalRanges variable was set, false otherwise

Definition at line 352 of file ClassificationData.cpp.

UINT ClassificationData::eraseAllSamplesWithClassLabel ( const UINT classLabel )

Deprecated:: This function is now depreciated! You should use removeClass(const UINT classLabel) instead.

Deletes from the dataset all the samples with a specific class label.

Parameters

classLabel the class label of the samples you wish to delete from the dataset

Returns: the number of samples deleted from the dataset

Definition at line 237 of file ClassificationData.cpp.

bool ClassificationData::generateGaussDataset	(	const std::string	filename,
		const UINT	numSamples = `10000`,
		const UINT	numClasses = `10`,
		const UINT	numDimensions = `3`,
		const Float	range = `10`,
		const Float	sigma = `1`
	)

static

Generates a labeled dataset that can be used for basic training/testing/validation for ClassificationData, saving the dataset to the file specified by filename.

Samples in the dataset will be generated based on K randomly select models, with Gaussian noise. K is set by the numClasses argument.

The Gaussian clusters are selected at random, therefore the returned dataset may or may not be linearly seperable, depending on the random clusters.

The range of each dimension will be [-range range]. Sigma controls the amount of Gaussian noise added.

Parameters

filename	the name of the file the dataset will be saved to
numSamples	the total number of samples in the dataset
numClasses	the number of classes in the dataset
numDimensions	the number of dimensions in the dataset
range	the range the data will be sampled from, range will be [-range range] for each dimension
sigma	the amount of Gaussian noise

Returns: returns true if the dataset was created successfully, false otherwise

Definition at line 1511 of file ClassificationData.cpp.

ClassificationData ClassificationData::generateGaussDataset	(	const UINT	numSamples = `10000`,
		const UINT	numClasses = `10`,
		const UINT	numDimensions = `3`,
		const Float	range = `10`,
		const Float	sigma = `1`
	)

static

Generates a labeled dataset that can be used for basic training/testing/validation for ClassificationData and returns it directly.

Samples in the dataset will be generated based on K randomly select models, with Gaussian noise. K is set by the numClasses argument.

The Gaussian clusters are selected at random, therefore the returned dataset may or may not be linearly separable, depending on the random clusters.

The range of each dimension will be [-range range]. Sigma controls the amount of Gaussian noise added.

Parameters

numSamples	the total number of samples in the dataset
numClasses	the number of classes in the dataset
numDimensions	the number of dimensions in the dataset
range	the range the data will be sampled from, range will be [-range range] for each dimension
sigma	the amount of Gaussian noise

Returns: returns the new dataset

Definition at line 1520 of file ClassificationData.cpp.

ClassificationData ClassificationData::generateGaussLinearDataset	(	const UINT	numSamples = `10000`,
		const UINT	numClasses = `10`,
		const UINT	numDimensions = `3`,
		const Float	range = `10`,
		const Float	sigma = `1`
	)

static

Generates a labeled dataset that can be used for basic training/testing/validation for ClassificationData and returns it directly.

Samples in the dataset will be generated based on K randomly select models, with Gaussian noise. K is set by the numClasses argument.

The range of each dimension will be [-range range]. Sigma controls the amount of Gaussian noise added.

The Gaussian clusters are encouraged to be linearly separable by setting the centroids of each class on a regularly spaced grid. If there are too many classes or the sigma noise of each class is too high then the resulting data may NOT be linearly separable.

Parameters

numSamples	the total number of samples in the dataset
numClasses	the number of classes in the dataset
numDimensions	the number of dimensions in the dataset
range	the range the data will be sampled from, range will be [-range range] for each dimension
sigma	the amount of Gaussian noise

Returns: returns the new dataset

Definition at line 1559 of file ClassificationData.cpp.

ClassificationData ClassificationData::getBootstrappedDataset	(	const UINT	numSamples = `0`,
		const bool	balanceDataset = `false`
	)		const

Gets a bootstrapped dataset from the current dataset. If the numSamples parameter is set to zero, then the size of the bootstrapped dataset will match the size of the current dataset, otherwise the size of the bootstrapped dataset will match the numSamples parameter.

Parameters

numSamples	the size of the bootstrapped dataset
balanceDataset	if true will use stratified sampling to balance the dataset returned, otherwise will use random sampling

Returns: returns a bootstrapped ClassificationData

Definition at line 1048 of file ClassificationData.cpp.

ClassificationData ClassificationData::getClassData ( const UINT classLabel ) const

Returns the all the data with the class label set by classLabel. The classLabel should be a valid classLabel, otherwise the dataset returned will be empty.

Parameters

classLabel the class label of the class you want the data for

Returns: returns a dataset containing all the data with the matching classLabel

Definition at line 1025 of file ClassificationData.cpp.

Vector< UINT > ClassificationData::getClassDataIndexes ( const UINT classLabel ) const

Gets the indexes for all the samples in the current dataset belonging to the classLabel.

Parameters

classLabel the classLabel of the class you want the indexes for

Returns: a Vector< UINT > containing the indexes for all the samples in the current dataset belonging to the classLabel

Definition at line 1457 of file ClassificationData.cpp.

MatrixFloat ClassificationData::getClassHistogramData	(	const UINT	classLabel,
		const UINT	numBins
	)		const

Computes a histogram for a specific class.

Parameters

classLabel	the class label of the class you want to compute the histogram data for
numBins	the number of bins in the histogram

Returns: a MatrixFloat of histogram data where each row represents a dimension and each column represents a histogram bin

Definition at line 1305 of file ClassificationData.cpp.

Vector< ClassificationSample > ClassificationData::getClassificationData ( ) const

inline

Gets the classification data.

Returns: a Vector of LabelledClassificationSamples

Definition at line 553 of file ClassificationData.h.

UINT ClassificationData::getClassLabelIndexValue ( const UINT classLabel ) const

Gets the index of the class label from the class tracker.

Parameters

classLabel the class label you want to access the index for

Returns: an unsigned int representing the index of the class label in the class tracker

Definition at line 1185 of file ClassificationData.cpp.

Vector< UINT > ClassificationData::getClassLabels ( ) const

Gets the class label associated with class[i].

Returns: returns a Vector of UINTs, where each element represents a class label.

Definition at line 1252 of file ClassificationData.cpp.

MatrixFloat ClassificationData::getClassMean ( ) const

Gets the mean values for each class in the dataset. This is returned in an [K N] matrix, where K is the number of classes in the dataset and N is the number of dimensions in the dataset.

Returns: a MatrixFloat with the mean values for each class in the dataset

Definition at line 1351 of file ClassificationData.cpp.

std::string ClassificationData::getClassNameForCorrespondingClassLabel ( const UINT classLabel ) const

Gets the name of the class with a given class label. If the class label does not exist then the string "CLASS_LABEL_NOT_FOUND" will be returned.

Parameters

classLabel the class label you want to access the name for

Returns: a string containing the name of the given class label or the string "CLASS_LABEL_NOT_FOUND" if the class label does not exist

Definition at line 1195 of file ClassificationData.cpp.

MatrixFloat ClassificationData::getClassStdDev ( ) const

Gets the standard deviation values for each class in the dataset. This is returned in an [K N] matrix, where K is the number of classes in the dataset and N is the number of dimensions in the dataset.

Returns: a MatrixFloat with the standard deviation values for each class in the dataset

Definition at line 1375 of file ClassificationData.cpp.

Vector< ClassTracker > ClassificationData::getClassTracker ( ) const

inline

Gets the class tracker for each class in the dataset.

Returns: a Vector of ClassTracker, one for each class in the dataset

Definition at line 528 of file ClassificationData.h.

MatrixFloat ClassificationData::getCovarianceMatrix ( ) const

Gets the covariance matrix across all the classes in the dataset. This is returned in an [N N] matrix, where N is the number of dimensions in the dataset.

Returns: a MatrixFloat with the covariance values for the dataset

Definition at line 1400 of file ClassificationData.cpp.

MatrixDouble ClassificationData::getDataAsMatrixDouble ( ) const

Gets the data as a MatrixDouble. This returns just the data, not the labels. This will be an M by N MatrixDouble, where M is the number of samples and N is the number of dimensions.

Returns: a MatrixDouble containing the data from the current dataset.

Definition at line 1482 of file ClassificationData.cpp.

MatrixFloat ClassificationData::getDataAsMatrixFloat ( ) const

Gets the data as a MatrixFloat. This returns just the data, not the labels. This will be an M by N MatrixFloat, where M is the number of samples and N is the number of dimensions.

Returns: a MatrixFloat containing the data from the current dataset.

Definition at line 1497 of file ClassificationData.cpp.

std::string ClassificationData::getDatasetName ( ) const

inline

Gets the name of the dataset.

Returns: returns the name of the dataset

Definition at line 435 of file ClassificationData.h.

Vector< MatrixFloat > ClassificationData::getHistogramData ( const UINT numBins ) const

Computes a histogram for each class in the dataset.

Parameters

numBins the number of bins in the histogram

Returns: a Vector of MatrixFloat, each element represents a class and is a MatrixFloat of histogram data where each row represents a dimension and each column represents a histogram bin

Definition at line 1417 of file ClassificationData.cpp.

std::string ClassificationData::getInfoText ( ) const

inline

Gets the infotext for the dataset

Returns: returns the infotext of the dataset

Definition at line 442 of file ClassificationData.h.

UINT ClassificationData::getMaximumClassLabel ( ) const

Gets the maximum class label in the dataset. If there are no values in the dataset then the value 0 will be returned.

Returns: an unsigned int representing the maximum class label in the dataset

Definition at line 1173 of file ClassificationData.cpp.

VectorFloat ClassificationData::getMean ( ) const

Gets the mean values across all classes in the dataset.

Returns: a Vector containing the mean values across the entire dataset.

Definition at line 1276 of file ClassificationData.cpp.

UINT ClassificationData::getMinimumClassLabel ( ) const

Gets the minimum class label in the dataset. If there are no values in the dataset then the value 99999 will be returned.

Returns: an unsigned int representing the minimum class label in the dataset

Definition at line 1160 of file ClassificationData.cpp.

UINT ClassificationData::getNumClasses ( ) const

inline

Gets the number of classes.

Returns: an unsigned int representing the number of classes

Definition at line 470 of file ClassificationData.h.

UINT ClassificationData::getNumDimensions ( ) const

inline

Gets the number of dimensions of the labelled classification data.

Returns: an unsigned int representing the number of dimensions in the classification data

Definition at line 456 of file ClassificationData.h.

UINT ClassificationData::getNumSamples ( ) const

inline

Gets the number of samples in the classification data across all the classes.

Returns: an unsigned int representing the total number of samples in the classification data

Examples:: ClassificationModulesExamples/AdaBoostExample/AdaBoostExample.cpp, ClassificationModulesExamples/ANBCExample/ANBCExample.cpp, ClassificationModulesExamples/BAGExample/BAGExample.cpp, ClassificationModulesExamples/DecisionTreeExample/DecisionTreeExample.cpp, ClassificationModulesExamples/GMMExample/GMMExample.cpp, ClassificationModulesExamples/KNNExample/KNNExample.cpp, ClassificationModulesExamples/MinDistExample/MinDistExample.cpp, ClassificationModulesExamples/RandomForestsExample/RandomForestsExample.cpp, ClassificationModulesExamples/SoftmaxExample/SoftmaxExample.cpp, and ClassificationModulesExamples/SVMExample/SVMExample.cpp.

Definition at line 463 of file ClassificationData.h.

Vector< UINT > ClassificationData::getNumSamplesPerClass ( ) const

Gets the number of samples in each class.

Returns: returns a Vector of UINTs, where each element represents the number of samples in that class.

Definition at line 1264 of file ClassificationData.cpp.

Vector< MinMax > ClassificationData::getRanges ( ) const

Gets the ranges of the classification data.

Returns: a Vector of minimum and maximum values for each dimension of the data

Definition at line 1231 of file ClassificationData.cpp.

std::string ClassificationData::getStatsAsString ( ) const

Gets the stats of the dataset as a string

Returns: returns the stats of this dataset as a string

Definition at line 1206 of file ClassificationData.cpp.

VectorFloat ClassificationData::getStdDev ( ) const

Gets the standard deviation values across all classes in the dataset.

Returns: a Vector containing the standard deviation values across all classes in the dataset.

Definition at line 1290 of file ClassificationData.cpp.

ClassificationData ClassificationData::getTestFoldData ( const UINT foldIndex ) const

Returns the test dataset for the k-th fold for cross validation. The spiltDataIntoKFolds(UINT K) function should have been called once before using this function. The foldIndex should be in the range [0 K-1], where K is the number of folds the data was spilt into.

Parameters

foldIndex the index of the fold you want the test data for, this should be in the range [0 K-1], where K is the number of folds the data was spilt into

Returns: returns a test dataset

Definition at line 994 of file ClassificationData.cpp.

ClassificationData ClassificationData::getTrainingFoldData ( const UINT foldIndex ) const

Returns the training dataset for the k-th fold for cross validation. The spiltDataIntoKFolds(UINT K) function should have been called once before using this function. The foldIndex should be in the range [0 K-1], where K is the number of folds the data was spilt into.

Parameters

foldIndex the index of the fold you want the training data for, this should be in the range [0 K-1], where K is the number of folds the data was spilt into

Returns: returns a training dataset

Definition at line 958 of file ClassificationData.cpp.

ClassificationData::GRT_DEPRECATED_MSG	(	"partition(...) is	deprecated,
		use split(...) instead"	,
		ClassificationData	partitionconst UINT partitionPercentage, const bool useStratifiedSampling=false
	)

Deprecated:: use split(...) instead

Parameters

partitionPercentage	sets the percentage of data which remains in this instance, the remaining percentage of data is then returned as the testing/validation dataset
useStratifiedSampling	sets if the dataset should be broken into homogeneous groups first before randomly being spilt, default value is false

Returns: a new ClassificationData instance, containing the remaining data not kept but this instance

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

Load the classification data from a file. If the file format ends in '.csv' then the function will try and load the data from a csv format. If this fails then it will try and load the data as a custom GRT file.

Parameters

filename the name of the file the data will be loaded from

Returns: true if the data was loaded successfully, false otherwise

Examples:: ClassificationModulesExamples/AdaBoostExample/AdaBoostExample.cpp, ClassificationModulesExamples/ANBCExample/ANBCExample.cpp, ClassificationModulesExamples/BAGExample/BAGExample.cpp, ClassificationModulesExamples/DecisionTreeExample/DecisionTreeExample.cpp, ClassificationModulesExamples/GMMExample/GMMExample.cpp, ClassificationModulesExamples/KNNExample/KNNExample.cpp, ClassificationModulesExamples/MinDistExample/MinDistExample.cpp, ClassificationModulesExamples/RandomForestsExample/RandomForestsExample.cpp, ClassificationModulesExamples/SoftmaxExample/SoftmaxExample.cpp, ClassificationModulesExamples/SVMExample/SVMExample.cpp, ClusteringModulesExamples/KMeansExample/KMeansExample.cpp, and Tutorials/MachineLearning101/MachineLearning101.cpp.

Definition at line 389 of file ClassificationData.cpp.

bool ClassificationData::loadDatasetFromCSVFile	(	const std::string &	filename,
		const UINT	classLabelColumnIndex = `0`
	)

Loads the labelled classification data from a CSV file. This assumes the data is formatted with each row representing a sample. The class label should be the first column followed by the sample data as the following N columns, where N is the number of dimensions in the data. If the class label is not the first column, you should set the 2nd argument (UINT classLabelColumnIndex) to the column index that contains the class label.

Parameters

filename	the name of the file the data will be loaded from
classLabelColumnIndex	the index of the column containing the class label. Default value = 0

Returns: true if the data was loaded successfully, false otherwise

Definition at line 603 of file ClassificationData.cpp.

bool ClassificationData::loadDatasetFromFile ( const std::string & filename )

Loads the labelled classification data from a custom file format.

Parameters

filename the name of the file the data will be loaded from

Returns: true if the data was loaded successfully, false otherwise

Definition at line 443 of file ClassificationData.cpp.

bool ClassificationData::merge ( const ClassificationData & data )

Adds the data to the current instance of the ClassificationData. The number of dimensions in both datasets must match. The names of the classes from the data will be added to the current instance.

Parameters

data	the dataset to add to this dataset

Returns: returns true if the datasets were merged, false otherwise

Definition at line 819 of file ClassificationData.cpp.

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

Sets the equals operator, copies the data from the rhs instance to this instance

Parameters

rhs	another instance of the ClassificationData class from which the data will be copied to this instance

Returns: a reference to this instance of ClassificationData

Definition at line 48 of file ClassificationData.cpp.

ClassificationSample& ClassificationData::operator[] ( const UINT & i )

inline

Array Subscript Operator, returns the ClassificationSample at index i. It is up to the user to ensure that i is within the range of [0 totalNumSamples-1]

Parameters

i	the index of the training sample you want to access. Must be within the range of [0 totalNumSamples-1]

Returns: a reference to the i'th ClassificationSample

Definition at line 82 of file ClassificationData.h.

const ClassificationSample& ClassificationData::operator[] ( const UINT & i ) const

inline

Const Array Subscript Operator, returns the ClassificationSample at index i. It is up to the user to ensure that i is within the range of [0 totalNumSamples-1]

Parameters

i	the index of the training sample you want to access. Must be within the range of [0 totalNumSamples-1]

Returns: a const reference to the i'th ClassificationSample

Definition at line 93 of file ClassificationData.h.

bool ClassificationData::printStats ( ) const

Prints the dataset info (such as its name and infoText) and the stats (such as the number of examples, number of dimensions, number of classes, etc.) to the std out.

Returns: returns true if the dataset info and stats were printed successfully, false otherwise

Examples:: Tutorials/MachineLearning101/MachineLearning101.cpp.

Definition at line 693 of file ClassificationData.cpp.

RegressionData ClassificationData::reformatAsRegressionData ( ) const

Reformats the ClassificationData as RegressionData to enable regression algorithms like the MLP to be used as a classifier. This sets the number of targets in the regression data equal to the number of classes in the classification data. The output target ouput of each regression sample will therefore be all zeros, except for the index matching the class label which will be 1. For this to work, the labelled classification data cannot have any samples with a class label of 0!

Returns: a new RegressionData instance, containing the reformated classification data

Definition at line 1108 of file ClassificationData.cpp.

UnlabelledData ClassificationData::reformatAsUnlabelledData ( ) const

Reformats the ClassificationData as UnlabelledData so the data can be used to train unsupervised training algorithms such as K-Means Clustering and Gaussian Mixture Models.

Returns: a new UnlabelledData instance, containing the reformated classification data

Definition at line 1143 of file ClassificationData.cpp.

bool ClassificationData::relabelAllSamplesWithClassLabel	(	const UINT	oldClassLabel,
		const UINT	newClassLabel
	)

Relabels all the samples with the class label A with the new class label B.

Parameters

oldClassLabel	the class label of the samples you want to relabel
newClassLabel	the class label the samples will be relabelled with

Returns: returns true if the samples were correctly relablled, false otherwise

Definition at line 294 of file ClassificationData.cpp.

UINT ClassificationData::removeClass ( const UINT classLabel )

Deletes from the dataset all the samples with a specific class label.

Parameters

classLabel the class label of the samples you wish to delete from the dataset

Returns: the number of samples deleted from the dataset

Definition at line 260 of file ClassificationData.cpp.

bool ClassificationData::removeLastSample ( )

Removes the last training sample added to the dataset.

Returns: true if the last sample was removed, false otherwise

Definition at line 218 of file ClassificationData.cpp.

bool ClassificationData::removeSample ( const UINT index )

Removes the training sample at the specific index from the dataset.

Parameters

index the index of the training sample that should be removed

Returns: true if the index is valid and the sample was removed, false otherwise

Definition at line 183 of file ClassificationData.cpp.

bool ClassificationData::reserve ( const UINT M )

Reserves that the Vector capacity be at least enough to contain M elements.

If M is greater than the current Vector capacity, the function causes the container to reallocate its storage increasing its capacity to M (or greater).

Parameters

M	the new memory size

Returns: true if the memory was reserved successfully, false otherwise

Definition at line 228 of file ClassificationData.cpp.

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

Saves the classification data to a file. If the file format ends in '.csv' then the data will be saved as comma-seperated-values, otherwise it will be saved to a custom GRT file (which contains the csv data with an additional header).

Parameters

filename the name of the file the data will be saved to

Returns: true if the data was saved successfully, false otherwise

Definition at line 378 of file ClassificationData.cpp.

bool ClassificationData::saveDatasetToCSVFile ( const std::string & filename ) const

Saves the labelled classification data to a CSV file. This will save the class label as the first column and the sample data as the following N columns, where N is the number of dimensions in the data. Each row will represent a sample.

Parameters

filename the name of the file the data will be saved to

Returns: true if the data was saved successfully, false otherwise

Definition at line 580 of file ClassificationData.cpp.

bool ClassificationData::saveDatasetToFile ( const std::string & filename ) const

Saves the labelled classification data to a custom file format.

Parameters

filename the name of the file the data will be saved to

Returns: true if the data was saved successfully, false otherwise

Definition at line 400 of file ClassificationData.cpp.

bool ClassificationData::scale	(	const Float	minTarget,
		const Float	maxTarget
	)

Scales the dataset to the new target range.

Parameters

minTarget	the minimum range that the target data should be scaled to
maxTarget	the maximum range that the target data should be scaled to

Returns: true if the data was scaled correctly, false otherwise

Definition at line 360 of file ClassificationData.cpp.

bool ClassificationData::scale	(	const Vector< MinMax > &	ranges,
		const Float	minTarget,
		const Float	maxTarget
	)

Scales the dataset to the new target range, using the Vector of ranges as the min and max source ranges.

Parameters

ranges	a vector containing the new ranges
minTarget	the minimum range that the target data should be scaled to
maxTarget	the maximum range that the target data should be scaled to

Returns: true if the data was scaled correctly, false otherwise

Definition at line 365 of file ClassificationData.cpp.

bool ClassificationData::setAllowNullGestureClass ( const bool allowNullGestureClass )

Sets if the user can add samples to the dataset with the label matching the GRT_DEFAULT_NULL_CLASS_LABEL. If the allowNullGestureClass is set to true, then the user can add labels matching the default null class label (which is normally 0). If the allowNullGestureClass is set to false, then the user will not be able to add samples that have a class label matching the default null class label.

Parameters

allowNullGestureClass flag that indicates if the null gesture class should be allowed

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

Definition at line 128 of file ClassificationData.cpp.

bool ClassificationData::setClassNameForCorrespondingClassLabel	(	const std::string	className,
		const UINT	classLabel
	)

Sets the name of the class with the given class label. There should not be any spaces in the className. Will return true if the name is set, or false if the class label does not exist.

Parameters

className	the className for which the label should be updated
classLabel	the updated class label

Returns: returns true if the name is set, or false if the class label does not exist

Definition at line 115 of file ClassificationData.cpp.

bool ClassificationData::setDatasetName ( std::string datasetName )

Sets the name of the dataset. There should not be any spaces in the name. Will return true if the name is set, or false otherwise.

Returns: returns true if the name is set, or false otherwise

Definition at line 98 of file ClassificationData.cpp.

bool ClassificationData::setExternalRanges	(	const Vector< MinMax > &	externalRanges,
		const bool	useExternalRanges = `false`
	)

Sets the external ranges of the dataset, also sets if the dataset should be scaled using these values. The dimensionality of the externalRanges Vector should match the number of dimensions of this dataset.

Parameters

externalRanges	an N dimensional Vector containing the min and max values of the expected ranges of the dataset.
useExternalRanges	sets if these ranges should be used to scale the dataset, default value is false.

Returns: returns true if the external ranges were set, false otherwise

Definition at line 342 of file ClassificationData.cpp.

bool ClassificationData::setInfoText ( std::string infoText )

Sets the info string. This can be any string with information about how the training data was recorded for example.

Parameters

infoText the infoText

Returns: true if the infoText was correctly updated, false otherwise

Definition at line 110 of file ClassificationData.cpp.

bool ClassificationData::setNumDimensions ( UINT numDimensions )

Sets the number of dimensions in the training data. This should be an unsigned integer greater than zero. This will clear any previous training data and counters. This function needs to be called before any new samples can be added to the dataset, unless the numDimensions variable was set in the constructor or some data was already loaded from a file

Parameters

numDimensions the number of dimensions of the training data. Must be an unsigned integer greater than zero

Returns: true if the number of dimensions was correctly updated, false otherwise

Definition at line 78 of file ClassificationData.cpp.

bool ClassificationData::sortClassLabels ( )

Sorts the class labels (in the class tracker) in ascending order.

Returns: returns true if the labels were sorted successfully, false otherwise

Definition at line 700 of file ClassificationData.cpp.

bool ClassificationData::spiltDataIntoKFolds	(	const UINT	K,
		const bool	useStratifiedSampling = `false`
	)

This function prepares the dataset for k-fold cross validation and should be called prior to calling the getTrainingFold(UINT foldIndex) or getTestingFold(UINT foldIndex) functions. It will spilt the dataset into K-folds, as long as K < M, where M is the number of samples in the dataset.

Parameters

K	the number of folds the dataset will be split into, K should be less than the number of samples in the dataset
useStratifiedSampling	sets if the dataset should be broken into homogeneous groups first before randomly being spilt, default value is false

Returns: returns true if the dataset was split correctly, false otherwise

Definition at line 853 of file ClassificationData.cpp.

ClassificationData ClassificationData::split	(	const UINT	splitPercentage,
		const bool	useStratifiedSampling = `false`
	)

Splits the dataset into a training dataset (which is kept by this instance of the ClassificationData) and a testing/validation dataset (which is returned as a new instance of a ClassificationData).

Parameters

splitPercentage	sets the percentage of data which remains in this instance, the remaining percentage of data is then returned as the testing/validation dataset
useStratifiedSampling	sets if the dataset should be broken into homogeneous groups first before randomly being spilt, default value is false

Returns: a new ClassificationData instance, containing the remaining data not kept but this instance

Examples:: ClassificationModulesExamples/AdaBoostExample/AdaBoostExample.cpp, ClassificationModulesExamples/ANBCExample/ANBCExample.cpp, ClassificationModulesExamples/BAGExample/BAGExample.cpp, ClassificationModulesExamples/DecisionTreeExample/DecisionTreeExample.cpp, ClassificationModulesExamples/GMMExample/GMMExample.cpp, ClassificationModulesExamples/KNNExample/KNNExample.cpp, ClassificationModulesExamples/MinDistExample/MinDistExample.cpp, ClassificationModulesExamples/RandomForestsExample/RandomForestsExample.cpp, ClassificationModulesExamples/SoftmaxExample/SoftmaxExample.cpp, ClassificationModulesExamples/SVMExample/SVMExample.cpp, and Tutorials/MachineLearning101/MachineLearning101.cpp.

Definition at line 711 of file ClassificationData.cpp.

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

Public Member Functions

Static Public Member Functions

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

Member Function Documentation