Class that provides functionality to read ARFF files. More...

#include <ARFFTools.hpp>

Static Public Member Functions
static Dataset	readARFF (std::istream &stream, bool hasTargets=true, size_t instanceCutoff=-1, std::vector< size_t > selectedCols=std::vector< size_t >(), std::vector< double > selectedTargets=std::vector< double >())
	Sequentially reads a ARFF file. More...

static Dataset	readARFFFromFile (const std::string &filename, bool hasTargets=true, size_t instanceCutoff=-1, std::vector< size_t > selectedCols=std::vector< size_t >(), std::vector< double > selectedTargets=std::vector< double >())
	Wrapper from input type: File. More...

static Dataset	readARFFFromString (const std::string &content, bool hasTargets=true, size_t instanceCutoff=-1, std::vector< size_t > selectedCols=std::vector< size_t >(), std::vector< double > selectedTargets=std::vector< double >())
	Wrapper from input type: String. More...

static void	readARFFSize (std::istream &stream, size_t &numberInstances, size_t &dimension, bool hasTargets, std::vector< double > selectedTargets)
	Reads the size of a ARFF file. More...

static void	readARFFSizeFromFile (const std::string &filename, size_t &numberInstances, size_t &dimension, bool hasTargets=true, std::vector< double > selectedTargets=std::vector< double >())
	Wrapper from input type: File. More...

static void	readARFFSizeFromString (const std::string &content, size_t &numberInstances, size_t &dimension, bool hasTargets=true, std::vector< double > selectedTargets=std::vector< double >())
	Wrapper from input type: String. More...

Detailed Description

Class that provides functionality to read ARFF files.

Member Function Documentation

◆ readARFF()

Dataset sgpp::datadriven::ARFFTools::readARFF	(	std::istream &	stream,
		bool	hasTargets = `true`,
		size_t	instanceCutoff = `-1`,
		std::vector< size_t >	selectedCols = `std::vector<size_t>()`,
		std::vector< double >	selectedTargets = `std::vector<double>()`
	)

static

Sequentially reads a ARFF file.

Parameters

stream	contains the raw data. Note: After this function exists, stream will be at eof. For further use it should be cleared and reset
hasTargets	whether the csv has columns for targets (supervised learning)
instanceCutoff	maximal number of instances to include in the returned Dataset. May not be reached if there are less than instanceCutoff (valid w.r.t. selectedTargets) rows in csv file. If the value is -1 i.e. the maximal value of the (unsigned) size_t, all valid rows are included
selectedCols	which columns are written to the DataMatrix as dimensions. Order matters, i.e. selectedCols = [0, 3, 2] will result in a DataMatrix with dim0 = row0, dim1 = row3, dim2 = row2. If hasTargets=true, the last row must not be specified here as it is written to the target vector, not the DataMatrix. If empty (default) all rows (except possible the target row) will be used in ascending order.
selectedTargets	filter for targets. Only applicable if hasTargets=true. Only rows with target-entry (last column) equal to one of the entries in selectedTarget are written to the dataset. All other rows are skipped. Float-comparison uses 0.001 precision. This parameter is intended to use for classification with integer values as classes. If empty (default) all targets are admissible and all rows are written as rows (instances) in the dataset.

Returns: ARFF as Dataset

References dataset, sgpp::datadriven::Dataset::getData(), sgpp::datadriven::Dataset::getTargets(), python.statsfileInfo::i, python.utils.data_projections::line, readARFFSize(), sgpp::base::DataVector::set(), sgpp::base::DataMatrix::set(), and sgpp::datadriven::StringTokenizer::tokenize().

Referenced by readARFFFromFile(), and readARFFFromString().

◆ readARFFFromFile()

Dataset sgpp::datadriven::ARFFTools::readARFFFromFile	(	const std::string &	filename,
		bool	hasTargets = `true`,
		size_t	instanceCutoff = `-1`,
		std::vector< size_t >	selectedCols = `std::vector<size_t>()`,
		std::vector< double >	selectedTargets = `std::vector<double>()`
	)

static

Wrapper from input type: File.

See readARFF for more details

References python.utils.converter::filename, and readARFF().

Referenced by hpx_main(), main(), and sgpp::datadriven::ArffFileSampleProvider::readFile().

◆ readARFFFromString()

Dataset sgpp::datadriven::ARFFTools::readARFFFromString	(	const std::string &	content,
		bool	hasTargets = `true`,
		size_t	instanceCutoff = `-1`,
		std::vector< size_t >	selectedCols = `std::vector<size_t>()`,
		std::vector< double >	selectedTargets = `std::vector<double>()`
	)

static

Wrapper from input type: String.

See readARFF for more details

References readARFF().

Referenced by sgpp::datadriven::MetaLearner::learnAndTestString(), sgpp::datadriven::MetaLearner::learnReferenceString(), sgpp::datadriven::MetaLearner::learnString(), and sgpp::datadriven::ArffFileSampleProvider::readString().

◆ readARFFSize()

void sgpp::datadriven::ARFFTools::readARFFSize	(	std::istream &	stream,
		size_t &	numberInstances,
		size_t &	dimension,
		bool	hasTargets,
		std::vector< double >	selectedTargets
	)

static

Reads the size of a ARFF file.

Parameters

	stream	contains the raw data. Note: After this function exists, stream will be at eof. For further use it should be cleared and reset
[out]	numberInstances	number of instances in the dataset
[out]	dimension	number of columns (dimensions) in the dataset
	hasTargets	whether the csv has a columns for targets (supervised learning). If true, dimension = number of columns - 1
	selectedTargets	(see readCSVPartial). If this vector is not empty (default) numberIstances reflects only the number of instance which are admissible with respect to selectedTargets. If empty all targets are admissible and all rows are considered as instances.

References python.leja::count, python.statsfileInfo::i, and python.utils.data_projections::line.

Referenced by readARFF(), readARFFSizeFromFile(), and readARFFSizeFromString().

◆ readARFFSizeFromFile()

void sgpp::datadriven::ARFFTools::readARFFSizeFromFile	(	const std::string &	filename,
		size_t &	numberInstances,
		size_t &	dimension,
		bool	hasTargets = `true`,
		std::vector< double >	selectedTargets = `std::vector<double>()`
	)

static

Wrapper from input type: File.

See readARFFSize for more details

References python.utils.converter::filename, and readARFFSize().

◆ readARFFSizeFromString()

void sgpp::datadriven::ARFFTools::readARFFSizeFromString	(	const std::string &	content,
		size_t &	numberInstances,
		size_t &	dimension,
		bool	hasTargets = `true`,
		std::vector< double >	selectedTargets = `std::vector<double>()`
	)

static

Wrapper from input type: String.

See readARFFSize for more details

References readARFFSize().

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

datadriven/src/sgpp/datadriven/tools/ARFFTools.hpp
datadriven/src/sgpp/datadriven/tools/ARFFTools.cpp

Static Public Member Functions

Detailed Description

Member Function Documentation

◆ readARFF()

◆ readARFFFromFile()

◆ readARFFFromString()

◆ readARFFSize()

◆ readARFFSizeFromFile()

◆ readARFFSizeFromString()