#include <RegressionData.h>

Public Member Functions
	RegressionData (const UINT numInputDimensions=0, const UINT numTargetDimensions=0, const std::string datasetName="NOT_SET", const std::string infoText="")

	RegressionData (const RegressionData &rhs)

	~RegressionData ()

RegressionData &	operator= (const RegressionData &rhs)

RegressionSample &	operator[] (const UINT &i)

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

void	clear ()

bool	setInputAndTargetDimensions (const UINT numInputDimensions, const UINT numTargetDimensions)

bool	setDatasetName (const std::string &datasetName)

bool	setInfoText (const std::string &infoText)

bool	addSample (const VectorFloat &inputVector, const VectorFloat &targetVector)

bool	removeLastSample ()

bool	reserve (const UINT N)

bool	setExternalRanges (const Vector< MinMax > &externalInputRanges, const Vector< MinMax > &externalTargetRanges, const bool useExternalRanges)

bool	enableExternalRangeScaling (const bool useExternalRanges)

bool	scale (const Float minTarget, const Float maxTarget)

bool	scale (const Vector< MinMax > &inputVectorRanges, const Vector< MinMax > &targetVectorRanges, 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 numInputDimensions, const UINT numTargetDimensions)

bool	printStats () const

bool	merge (const RegressionData &regressionData)

RegressionData	partition (const UINT trainingSizePercentage)

bool	spiltDataIntoKFolds (const UINT K)

RegressionData	getTrainingFoldData (const UINT foldIndex) const

RegressionData	getTestFoldData (const UINT foldIndex) const

UINT	removeDuplicateSamples ()

std::string	getDatasetName () const

std::string	getInfoText () const

std::string	getStatsAsString () const

UINT	getNumInputDimensions () const

UINT	getNumTargetDimensions () const

UINT	getNumSamples () const

Vector< MinMax >	getInputRanges () const

Vector< MinMax >	getTargetRanges () const

Vector< RegressionSample >	getData () const

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 41 of file RegressionData.h.

Constructor & Destructor Documentation

GRT_BEGIN_NAMESPACE RegressionData::RegressionData	(	const UINT	numInputDimensions = `0`,
		const UINT	numTargetDimensions = `0`,
		const std::string	datasetName = `"NOT_SET"`,
		const std::string	infoText = `""`
	)

Constructor, set the number of input dimensions, number of target dimensions, dataset name and the infotext for the dataset. The name of the dataset should not contain any spaces.

Parameters

numInputDimensions	the number of input dimensions of the training data, should be an unsigned integer greater than 0
numTargetDimensions	the number of target 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 25 of file RegressionData.cpp.

RegressionData::RegressionData ( const RegressionData & rhs )

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

Parameters

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

Definition at line 38 of file RegressionData.cpp.

RegressionData::~RegressionData ( )

Default Destructor

Definition at line 42 of file RegressionData.cpp.

Member Function Documentation

bool RegressionData::addSample	(	const VectorFloat &	inputVector,
		const VectorFloat &	targetVector
	)

Adds a new labelled sample to the dataset. The input and target dimensionality of the sample should match that of the dataset.

Parameters

inputVector	the new input Vector you want to add to the dataset. The dimensionality of this sample should match the number of input dimensions in the dataset
targetVector	the new target Vector you want to add to the dataset. The dimensionality of this sample should match the number of target dimensions in the dataset

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

Definition at line 106 of file RegressionData.cpp.

void RegressionData::clear ( )

Clears any previous training data and counters

Definition at line 65 of file RegressionData.cpp.

bool RegressionData::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 156 of file RegressionData.cpp.

Vector< RegressionSample > RegressionData::getData ( ) const

inline

Gets the regression data.

Returns: a Vector of RegressionSample

Definition at line 358 of file RegressionData.h.

std::string RegressionData::getDatasetName ( ) const

inline

Gets the name of the dataset.

Returns: returns the name of the dataset

Definition at line 307 of file RegressionData.h.

std::string RegressionData::getInfoText ( ) const

inline

Gets the infotext for the dataset

Returns: returns the infotext of the dataset

Definition at line 314 of file RegressionData.h.

Vector< MinMax > RegressionData::getInputRanges ( ) const

Gets the input ranges of the dataset.

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

Definition at line 194 of file RegressionData.cpp.

UINT RegressionData::getNumInputDimensions ( ) const

inline

Gets the number of input dimensions of the labelled regression data.

Returns: an unsigned int representing the number of input dimensions in the dataset

Definition at line 323 of file RegressionData.h.

UINT RegressionData::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

Definition at line 337 of file RegressionData.h.

UINT RegressionData::getNumTargetDimensions ( ) const

inline

Gets the number of target dimensions of the labelled regression data.

Returns: an unsigned int representing the number of target dimensions in the dataset

Definition at line 330 of file RegressionData.h.

Vector< MinMax > RegressionData::getTargetRanges ( ) const

Gets the target ranges of the dataset.

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

Definition at line 213 of file RegressionData.cpp.

RegressionData RegressionData::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 413 of file RegressionData.cpp.

RegressionData RegressionData::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 386 of file RegressionData.cpp.

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

Load the 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

Definition at line 489 of file RegressionData.cpp.

bool RegressionData::loadDatasetFromCSVFile	(	const std::string &	filename,
		const UINT	numInputDimensions,
		const UINT	numTargetDimensions
	)

Loads the labelled regression data from a CSV file. Each row represents a sample, the first N columns should represent the input Vector data with the remaining T columns representing the target sample. The user must specify the length of the input Vector (N) and the length of the target Vector (T).

Parameters

filename	the name of the file the data will be saved to
umInputDimensions	the length of an input Vector
numTargetDimensions	the length of a target Vector

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

Definition at line 692 of file RegressionData.cpp.

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

Loads the labelled regression 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 544 of file RegressionData.cpp.

bool RegressionData::merge ( const RegressionData & regressionData )

Adds the data in the regressionData set to the current instance of the RegressionData. The number of dimensions in both datasets must match.

Parameters

regressionData the dataset to add to this dataset

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

Definition at line 303 of file RegressionData.cpp.

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

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

Parameters

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

Returns: a reference to this instance of RegressionData

Definition at line 44 of file RegressionData.cpp.

RegressionSample& RegressionData::operator[] ( const UINT & i )

inline

Array Subscript Operator, returns the LabelledRegressionSample 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 RegressionSample

Definition at line 82 of file RegressionData.h.

const RegressionSample& RegressionData::operator[] ( const UINT & i ) const

inline

Const Array Subscript Operator, returns the LabelledRegressionSample 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 RegressionSample

Definition at line 93 of file RegressionData.h.

RegressionData RegressionData::partition ( const UINT trainingSizePercentage )

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

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

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

Definition at line 262 of file RegressionData.cpp.

bool RegressionData::removeLastSample ( )

Removes the last training sample added to the dataset.

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

Definition at line 120 of file RegressionData.cpp.

bool RegressionData::reserve ( const UINT N )

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

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

Parameters

N	the new memory size

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

Definition at line 135 of file RegressionData.cpp.

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

Saves the 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 478 of file RegressionData.cpp.

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

Saves the labelled regression data to a CSV file. This will save the input Vector as the first N columns and the target data as the following T columns. 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 665 of file RegressionData.cpp.

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

Saves the labelled regression 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 500 of file RegressionData.cpp.

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

Scales the dataset to the new target range.

Parameters

minTarget	the minimum target the dataset will be scaled to
maxTarget	the maximum target the dataset will be scaled to

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

Definition at line 164 of file RegressionData.cpp.

bool RegressionData::scale	(	const Vector< MinMax > &	inputVectorRanges,
		const Vector< MinMax > &	targetVectorRanges,
		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.

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

Definition at line 170 of file RegressionData.cpp.

bool RegressionData::setDatasetName ( const 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.

Parameters

datasetName the new dataset name (must not include any spaces)

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

Definition at line 89 of file RegressionData.cpp.

bool RegressionData::setExternalRanges	(	const Vector< MinMax > &	externalInputRanges,
		const Vector< MinMax > &	externalTargetRanges,
		const bool	useExternalRanges
	)

Sets the external input and target ranges of the dataset, also sets if the dataset should be scaled using these values. The dimensionality of the externalRanges Vector should match the numInputDimensions and numTargetDimensions of this dataset.

Parameters

externalInputRanges	an N dimensional Vector containing the min and max values of the expected input ranges of the dataset
externalTargetRanges	an N dimensional Vector containing the min and max values of the expected target 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 144 of file RegressionData.cpp.

bool RegressionData::setInfoText ( const 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 101 of file RegressionData.cpp.

bool RegressionData::setInputAndTargetDimensions	(	const UINT	numInputDimensions,
		const UINT	numTargetDimensions
	)

Sets the number of input and target dimensions in the training data. These should be unsigned integers 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 numInputDimensions and numTargetDimensions variables was set in the constructor or some data was already loaded from a file

Parameters

numInputDimensions	the number of input dimensions of the training data. Must be an unsigned integer greater than zero
numTargetDimensions	the number of target dimensions of the training data. Must be an unsigned integer greater than zero

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

Definition at line 73 of file RegressionData.cpp.

bool RegressionData::spiltDataIntoKFolds ( const UINT K )

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

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

Definition at line 327 of file RegressionData.cpp.

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

Public Member Functions

Detailed Description

Constructor & Destructor Documentation

Member Function Documentation