Classes
class	AdaptiveMomentEstimation

struct	AdaptiveMomentEstimationData

class	BoundingLayer
	This class represents a layer of bounding neurons. More...

struct	BoxPlot

class	ConjugateGradient

struct	ConjugateGradientData

class	ConvolutionalLayer

struct	ConvolutionalLayerBackPropagation

struct	ConvolutionalLayerForwardPropagation

struct	Correlation
	This structure provides the results obtained from the regression analysis. More...

class	CrossEntropyError
	This class represents the cross entropy error term, used for predicting probabilities. More...

class	DataSet
	This class represents the concept of data set for data modelling problems, such as approximation, classification or forecasting. More...

struct	DataSetBatch

struct	Descriptives
	This structure contains the simplest Descriptives for a set, variable, etc. It includes : More...

class	GeneticAlgorithm

class	GradientDescent

struct	GradientDescentData

class	GrowingInputs
	This concrete class represents a growing inputs algorithm for the InputsSelection as part of the ModelSelection[1] class. More...

class	GrowingNeurons
	This concrete class represents an growing neurons algorithm for the NeuronsSelection as part of the ModelSelection[1] class. More...

struct	Histogram

class	InputsSelection
	This abstract class represents the concept of inputs selection algorithm for a ModelSelection[1]. More...

struct	InputsSelectionResults
	This structure contains the results from the inputs selection. More...

class	Layer
	This abstract class represents the concept of layer of neurons in OpenNN. More...

struct	LayerBackPropagation

struct	LayerBackPropagationLM

struct	LayerForwardPropagation

class	LearningRateAlgorithm
	A learning rate that is adjusted according to an algorithm during training to minimize training time. More...

class	LevenbergMarquardtAlgorithm
	Levenberg-Marquardt Algorithm will always compute the approximate Hessian matrix, which has dimensions n-by-n. More...

struct	LevenbergMarquardtAlgorithmData

class	LongShortTermMemoryLayer

struct	LongShortTermMemoryLayerBackPropagation

struct	LongShortTermMemoryLayerForwardPropagation

class	LossIndex
	This abstract class represents the concept of loss index composed of an error term and a regularization term. More...

struct	LossIndexBackPropagation

struct	LossIndexBackPropagationLM
	A loss index composed of several terms, this structure represent the First Order for this function. More...

class	MeanSquaredError
	This class represents the mean squared error term. More...

class	MinkowskiError
	This class represents the Minkowski error term. More...

class	ModelSelection
	This class represents the concept of model selection[1] algorithm in OpenNN. More...

class	NeuralNetwork

struct	NeuralNetworkBackPropagation

struct	NeuralNetworkBackPropagationLM

struct	NeuralNetworkForwardPropagation

class	NeuronsSelection
	This abstract class represents the concept of neurons selection algorithm for a ModelSelection[1]. More...

struct	NeuronsSelectionResults
	This structure contains the results from the neurons selection. More...

class	NormalizedSquaredError
	This class represents the normalized squared error term. More...

class	NumericalDifferentiation

class	OptimizationAlgorithm

struct	OptimizationAlgorithmData

class	PerceptronLayer
	This class represents a layer of perceptrons. More...

struct	PerceptronLayerBackPropagation

struct	PerceptronLayerBackPropagationLM

struct	PerceptronLayerForwardPropagation

class	PoolingLayer

class	ProbabilisticLayer
	This class represents a layer of probabilistic neurons. More...

struct	ProbabilisticLayerBackPropagation

struct	ProbabilisticLayerBackPropagationLM

struct	ProbabilisticLayerForwardPropagation

class	PruningInputs
	This concrete class represents a pruning inputs algorithm for the InputsSelection as part of the ModelSelection[1] class. More...

struct	QuasiNewtonMehtodData

class	QuasiNewtonMethod

class	RecurrentLayer

struct	RecurrentLayerBackPropagation

struct	RecurrentLayerForwardPropagation

class	ResponseOptimization
	This class is used to optimize model response identify the combinations of variable settings jointly optimize a set of responses. More...

struct	ResponseOptimizationResults

class	ScalingLayer
	This class represents a layer of scaling neurons. More...

class	StochasticGradientDescent
	This concrete class represents the stochastic gradient descent optimization algorithm[1] for a loss index of a neural network. More...

struct	StochasticGradientDescentData

class	SumSquaredError
	This class represents the sum squared peformance term functional. More...

class	TestingAnalysis
	This class contains tools for testing neural networks in different learning tasks. More...

struct	TrainingResults
	This structure contains the optimization algorithm results. More...

class	TrainingStrategy
	This class represents the concept of training strategy for a neural network in OpenNN. More...

class	UnscalingLayer
	This class represents a layer of unscaling neurons. More...

class	WeightedSquaredError
	This class represents the weighted squared error term. More...

Typedefs
typedef float	type

Enumerations
enum class	CorrelationMethod { Linear , Logistic , Logarithmic , Exponential , Power }
	This enumeration represents the different regression methods provided by OpenNN. More...

enum class	Scaler { NoScaling , MinimumMaximum , MeanStandardDeviation , StandardDeviation , Logarithm }
	Enumeration of available methods for scaling and unscaling the data. More...

Functions
Correlation	linear_correlation (const ThreadPoolDevice *thread_pool_device, const Tensor< type, 1 > &x, const Tensor< type, 1 > &y)

Correlation	logarithmic_correlation (const ThreadPoolDevice *thread_pool_device, const Tensor< type, 1 > &x, const Tensor< type, 1 > &y)

Correlation	exponential_correlation (const ThreadPoolDevice *thread_pool_device, const Tensor< type, 1 > &x, const Tensor< type, 1 > &y)

Correlation	power_correlation (const ThreadPoolDevice *thread_pool_device, const Tensor< type, 1 > &x, const Tensor< type, 1 > &y)

Correlation	logistic_correlation_vector_vector (const ThreadPoolDevice *thread_pool_device, const Tensor< type, 1 > &x, const Tensor< type, 1 > &y)

Correlation	logistic_correlation_vector_matrix (const ThreadPoolDevice *thread_pool_device, const Tensor< type, 1 > &x, const Tensor< type, 2 > &y)

Correlation	logistic_correlation_matrix_vector (const ThreadPoolDevice *thread_pool_device, const Tensor< type, 2 > &x, const Tensor< type, 1 > &y)

Correlation	logistic_correlation_matrix_matrix (const ThreadPoolDevice *thread_pool_device, const Tensor< type, 2 > &x, const Tensor< type, 2 > &y)

Correlation	correlation (const ThreadPoolDevice *thread_pool_device, const Tensor< type, 2 > &x, const Tensor< type, 2 > &y)

pair< Tensor< type, 1 >, Tensor< type, 1 > >	filter_missing_values_vector_vector (const Tensor< type, 1 > &x, const Tensor< type, 1 > &y)
	Filter the missing values of two vectors. More...

pair< Tensor< type, 2 >, Tensor< type, 2 > >	filter_missing_values_matrix_matrix (const Tensor< type, 2 > &x, const Tensor< type, 2 > &y)

Tensor< type, 1 >	autocorrelations (const ThreadPoolDevice *thread_pool_device, const Tensor< type, 1 > &x, const Index &lags_number)

Tensor< type, 1 >	cross_correlations (const ThreadPoolDevice *thread_pool_device, const Tensor< type, 1 > &x, const Tensor< type, 1 > &y, const Index &maximum_lags_number)

Tensor< type, 2 >	get_correlation_values (const Tensor< Correlation, 2 > &correlations)

pair< Tensor< type, 1 >, Tensor< type, 1 > >	filter_missing_values_vector_matrix (const Tensor< type, 1 > &, const Tensor< type, 1 > &)

pair< Tensor< type, 1 >, Tensor< type, 1 > >	filter_missing_values_matrix_vector (const Tensor< type, 1 > &, const Tensor< type, 1 > &)

Index	count_tokens (string &str, const char &separator)

Index	count_tokens (const string &s, const char &c)

Tensor< string, 1 >	get_tokens (const string &str, const char &separator)

void	fill_tokens (const string &str, const char &separator, Tensor< string, 1 > &tokens)

Tensor< type, 1 >	to_type_vector (const string &str, const char &separator)
	Returns a new vector with the elements of this string vector casted to type. More...

bool	is_numeric_string (const string &str)

bool	is_constant_string (const Tensor< string, 1 > &str)

bool	is_constant_numeric (const Tensor< type, 1 > &str)

bool	is_date_time_string (const string &str)

time_t	date_to_timestamp (const string &date, const Index &gmt)

bool	contains_substring (const string &str, const string &sub_str)

void	trim (string &str)

void	erase (string &s, const char &c)

string	get_trimmed (const string &str)

string	prepend (const string &pre, const string &str)

bool	is_numeric_string_vector (const Tensor< string, 1 > &v)

bool	has_numbers (const Tensor< string, 1 > &v)

bool	has_strings (const Tensor< string, 1 > &v)

bool	is_not_numeric (const Tensor< string, 1 > &v)

bool	is_mixed (const Tensor< string, 1 > &v)

void	replace_substring (Tensor< string, 1 > &vector, const string &find_what, const string &replace_with)

void	replace (string &source, const string &find_what, const string &replace_with)

void	scale_minimum_maximum_binary (Tensor< type, 2 > &matrix, const type &value_1, const type &value_2, const Index &column_index)

void	scale_mean_standard_deviation (Tensor< type, 2 > &matrix, const Index &column_index, const Descriptives &column_descriptives)

void	scale_standard_deviation (Tensor< type, 2 > &matrix, const Index &column_index, const Descriptives &column_descriptives)

void	scale_minimum_maximum (Tensor< type, 2 > &matrix, const Index &column_index, const Descriptives &column_descriptives, const type &min_range, const type &max_range)

Tensor< type, 1 >	scale_minimum_maximum (const Tensor< type, 1 > &x)

Tensor< type, 2 >	scale_minimum_maximum (const Tensor< type, 2 > &x)

void	scale_logarithmic (Tensor< type, 2 > &matrix, const Index &column_index)

void	unscale_minimum_maximum (Tensor< type, 2 > &matrix, const Index &column_index, const Descriptives &column_descriptives, const type &min_range, const type &max_range)

void	unscale_mean_standard_deviation (Tensor< type, 2 > &matrix, const Index &column_index, const Descriptives &column_descriptives)

void	unscale_standard_deviation (Tensor< type, 2 > &matrix, const Index &column_index, const Descriptives &column_descriptives)

void	unscale_logarithmic (Tensor< type, 2 > &matrix, const Index &column_index)

type	minimum (const Tensor< type, 1 > &vector)

Index	minimum (const Tensor< Index, 1 > &vector)

type	minimum (const Tensor< type, 1 > &vector, const Tensor< Index, 1 > &indices)

type	maximum (const Tensor< type, 1 > &vector)

type	maximum (const Tensor< type, 1 > &vector, const Tensor< Index, 1 > &indices)

Index	maximum (const Tensor< Index, 1 > &vector)

Tensor< type, 1 >	columns_maximums (const Tensor< type, 2 > &matrix, const Tensor< Index, 1 > &rows_indices, const Tensor< Index, 1 > &columns_indices)

type	mean (const Tensor< type, 1 > &vector, const Index &begin, const Index &end)

type	mean (const Tensor< type, 1 > &vector)

type	variance (const Tensor< type, 1 > &vector)

type	variance (const Tensor< type, 1 > &vector, const Tensor< Index, 1 > &indices)

type	standard_deviation (const Tensor< type, 1 > &vector)

type	standard_deviation (const Tensor< type, 1 > &vector, const Tensor< Index, 1 > &indices)

Tensor< type, 1 >	standard_deviation (const Tensor< type, 1 > &vector, const Index &period)

type	asymmetry (const Tensor< type, 1 > &vector)

type	kurtosis (const Tensor< type, 1 > &vector)

type	median (const Tensor< type, 1 > &vector)

Tensor< type, 1 >	quartiles (const Tensor< type, 1 > &vector)

Tensor< type, 1 >	quartiles (const Tensor< type, 1 > &vector, const Tensor< Index, 1 > &indices)

BoxPlot	box_plot (const Tensor< type, 1 > &vector)

BoxPlot	box_plot (const Tensor< type, 1 > &vector, const Tensor< Index, 1 > &indices)

Histogram	histogram (const Tensor< type, 1 > &vector, const Index &bins_number)

Histogram	histogram_centered (const Tensor< type, 1 > &vector, const type &center, const Index &bins_number)

Histogram	histogram (const Tensor< bool, 1 > &v)

Tensor< Index, 1 >	total_frequencies (const Tensor< Histogram, 1 > &histograms)

Tensor< Histogram, 1 >	histograms (const Tensor< type, 2 > &matrix, const Index &bins_number)

Tensor< Descriptives, 1 >	descriptives (const Tensor< type, 2 > &matrix)

Tensor< Descriptives, 1 >	descriptives (const Tensor< type, 2 > &matrix, const Tensor< Index, 1 > &row_indices, const Tensor< Index, 1 > &columns_indices)

Tensor< type, 1 >	columns_minimums (const Tensor< type, 2 > &matrix, const Tensor< Index, 1 > &rows_indices, const Tensor< Index, 1 > &columns_indices)

Tensor< type, 1 >	columns_maximums (const Tensor< type, 2 > &matrix, const Tensor< Index, 1 > &columns_indices)

type	range (const Tensor< type, 1 > &vector)

Descriptives	descriptives (const Tensor< type, 1 > &vector)

Index	perform_distribution_distance_analysis (const Tensor< type, 1 > &vector)

Tensor< type, 1 >	mean (const Tensor< type, 2 > &matrix)

Tensor< type, 1 >	mean (const Tensor< type, 2 > &matrix, const Tensor< Index, 1 > &columns_indices)

Tensor< type, 1 >	mean (const Tensor< type, 2 > &matrix, const Tensor< Index, 1 > &row_indices, const Tensor< Index, 1 > &columns_indices)

type	mean (const Tensor< type, 2 > &matrix, const Index &column_index)

Tensor< type, 1 >	median (const Tensor< type, 2 > &matrix)

type	median (const Tensor< type, 2 > &matrix, const Index &column_index)

Tensor< type, 1 >	median (const Tensor< type, 2 > &matrix, const Tensor< Index, 1 > &columns_indices)

Tensor< type, 1 >	median (const Tensor< type, 2 > &matrix, const Tensor< Index, 1 > &row_indices, const Tensor< Index, 1 > &columns_indices)

type	normal_distribution_distance (const Tensor< type, 1 > &vector)

type	half_normal_distribution_distance (const Tensor< type, 1 > &vector)

type	uniform_distribution_distance (const Tensor< type, 1 > &vector)

type	normality_parameter (const Tensor< type, 1 > &vector)

Tensor< type, 1 >	variation_percentage (const Tensor< type, 1 > &vector)

Index	minimal_index (const Tensor< type, 1 > &vector)
	Returns the index of the smallest element in the vector. More...

Index	maximal_index (const Tensor< type, 1 > &vector)
	Returns the index of the largest element in the vector. More...

Tensor< Index, 1 >	minimal_indices (const Tensor< type, 1 > &vector, const Index &number)

Tensor< Index, 1 >	maximal_indices (const Tensor< type, 1 > &vector, const Index &number)

Tensor< Index, 1 >	minimal_indices (const Tensor< type, 2 > &matrix)
	Returns the row and column indices corresponding to the entry with minimum value. More...

Tensor< Index, 1 >	maximal_indices (const Tensor< type, 2 > &matrix)
	Returns the row and column indices corresponding to the entry with maximum value. More...

Tensor< Index, 2 >	maximal_columns_indices (const Tensor< type, 2 > &matrix, const Index &maximum_number)

Tensor< type, 1 >	percentiles (const Tensor< type, 1 > &vector)
	Returns a vector with the percentiles of a vector given. More...

Index	count_nan (const Tensor< type, 1 > &vector)

type	minimum (const Tensor< type, 2 > &)

type	maximum (const Tensor< type, 2 > &)

Histogram	histogram (const Tensor< Index, 1 > &, const Index &=10)

Tensor< Index, 1 >	maximal_indices ()

Tensor< Tensor< Index, 1 >, 1 >	minimal_maximal_indices ()

Tensor< type, 1 >	means_by_categories (const Tensor< type, 2 > &matrix)

void	initialize_sequential (Tensor< type, 1 > &vector)

void	multiply_rows (Tensor< type, 2 > &matrix, const Tensor< type, 1 > &vector)

void	divide_columns (Tensor< type, 2 > &matrix, const Tensor< type, 1 > &vector)

bool	is_zero (const Tensor< type, 1 > &tensor)

bool	is_zero (const Tensor< type, 1 > &tensor, const type &limit)

bool	is_false (const Tensor< bool, 1 > &tensor)

bool	is_binary (const Tensor< type, 2 > &matrix)

bool	is_constant (const Tensor< type, 1 > &vector)

bool	is_equal (const Tensor< type, 2 > &matrix, const type &value, const type &tolerance)

bool	are_equal (const Tensor< type, 1 > &vector_1, const Tensor< type, 1 > &vector_2, const type &tolerance)

bool	are_equal (const Tensor< type, 2 > &matrix_1, const Tensor< type, 2 > &matrix_2, const type &tolerance)

void	save_csv (const Tensor< type, 2 > &data, const string &filename)

Tensor< Index, 1 >	calculate_rank_greater (const Tensor< type, 1 > &vector)

Tensor< Index, 1 >	calculate_rank_less (const Tensor< type, 1 > &vector)

void	scrub_missing_values (Tensor< type, 2 > &matrix, const type &value)

Tensor< type, 2 >	kronecker_product (const Tensor< type, 1 > &vector, const Tensor< type, 1 > &other_vector)

type	l1_norm (const ThreadPoolDevice *thread_pool_device, const Tensor< type, 1 > &vector)

void	l1_norm_gradient (const ThreadPoolDevice *thread_pool_device, const Tensor< type, 1 > &vector, Tensor< type, 1 > &gradient)

void	l1_norm_hessian (const ThreadPoolDevice *, const Tensor< type, 1 > &, Tensor< type, 2 > &hessian)

type	l2_norm (const ThreadPoolDevice *thread_pool_device, const Tensor< type, 1 > &vector)
	Returns the l2 norm of a vector. More...

void	l2_norm_gradient (const ThreadPoolDevice *thread_pool_device, const Tensor< type, 1 > &vector, Tensor< type, 1 > &gradient)

void	l2_norm_hessian (const ThreadPoolDevice *thread_pool_device, const Tensor< type, 1 > &vector, Tensor< type, 2 > &hessian)

void	sum_diagonal (Tensor< type, 2 > &matrix, const type &value)

Tensor< type, 1 >	perform_Householder_QR_decomposition (const Tensor< type, 2 > &A, const Tensor< type, 1 > &b)
	Uses Eigen to solve the system of equations by means of the Householder QR decomposition. More...

void	fill_submatrix (const Tensor< type, 2 > &matrix, const Tensor< Index, 1 > &rows_indices, const Tensor< Index, 1 > &columns_indices, type *submatrix_pointer)

Index	count_NAN (const Tensor< type, 1 > &x)

void	check_size (const Tensor< type, 1 > &vector, const Index &size, const string &log)

void	check_dimensions (const Tensor< type, 2 > &matrix, const Index &rows_number, const Index &columns_number, const string &log)

void	check_columns_number (const Tensor< type, 2 > &matrix, const Index &columns_number, const string &log)

Tensor< type, 2 >	assemble_vector_vector (const Tensor< type, 1 > &x, const Tensor< type, 1 > &y)

Tensor< type, 2 >	assemble_vector_matrix (const Tensor< type, 1 > &x, const Tensor< type, 2 > &y)

Tensor< type, 2 >	assemble_matrix_vector (const Tensor< type, 2 > &x, const Tensor< type, 1 > &y)

Tensor< type, 2 >	assemble_matrix_matrix (const Tensor< type, 2 > &x, const Tensor< type, 2 > &y)

bool	is_less_than (const Tensor< type, 1 > &column, const type &value)
	Returns true if any value is less or equal than a given value, and false otherwise. More...

Detailed Description

This concrete class represents the adaptive moment estimation (Adam) training algorithm, based on adaptive estimates of lower-order moments. For more information visit:

[1] C. Barranquero "High performance optimization algorithms for neural networks." https://www.opennn.net/files/high_performance_optimization_algorithms_for_neural_networks.pdf .

[2] D. P. Kingma and J. L. Ba, "Adam: A Method for Stochastic Optimization." arXiv preprint arXiv:1412.6980v8 (2014).

Typedef Documentation

◆ type

typedef float type

Definition at line 50 of file config.h.

Enumeration Type Documentation

◆ CorrelationMethod

enum class CorrelationMethod

strong

This enumeration represents the different regression methods provided by OpenNN.

Definition at line 35 of file correlations.h.

◆ Scaler

enum class Scaler

strong

Enumeration of available methods for scaling and unscaling the data.

Definition at line 32 of file scaling.h.

Function Documentation

◆ are_equal() [1/2]

bool are_equal	(	const Tensor< type, 1 > &	vector_1,
		const Tensor< type, 1 > &	vector_2,
		const type &	tolerance
	)

Definition at line 138 of file tensor_utilities.cpp.

◆ are_equal() [2/2]

bool are_equal	(	const Tensor< type, 2 > &	matrix_1,
		const Tensor< type, 2 > &	matrix_2,
		const type &	tolerance
	)

Definition at line 151 of file tensor_utilities.cpp.

◆ assemble_matrix_matrix()

Tensor< type, 2 > assemble_matrix_matrix	(	const Tensor< type, 2 > &	x,
		const Tensor< type, 2 > &	y
	)

Definition at line 515 of file tensor_utilities.cpp.

◆ assemble_matrix_vector()

Tensor< type, 2 > assemble_matrix_vector	(	const Tensor< type, 2 > &	x,
		const Tensor< type, 1 > &	y
	)

Definition at line 494 of file tensor_utilities.cpp.

◆ assemble_vector_matrix()

Tensor< type, 2 > assemble_vector_matrix	(	const Tensor< type, 1 > &	x,
		const Tensor< type, 2 > &	y
	)

Definition at line 473 of file tensor_utilities.cpp.

◆ assemble_vector_vector()

Tensor< type, 2 > assemble_vector_vector	(	const Tensor< type, 1 > &	x,
		const Tensor< type, 1 > &	y
	)

Definition at line 456 of file tensor_utilities.cpp.

◆ asymmetry()

type asymmetry ( const Tensor< type, 1 > & vector )

Returns the asymmetry of the elements in the vector.

Parameters

vector Vector to be evaluated.

Definition at line 1034 of file statistics.cpp.

◆ autocorrelations()

Tensor< type, 1 > autocorrelations	(	const ThreadPoolDevice *	thread_pool_device,
		const Tensor< type, 1 > &	x,
		const Index &	lags_number
	)

Calculates autocorrelation for a given number of maximum lags.

Parameters

x	Vector containing the data.
lags_number	Maximum lags number.

Definition at line 603 of file correlations.cpp.

◆ box_plot() [1/2]

BoxPlot box_plot ( const Tensor< type, 1 > & vector )

Returns the box and whispers for a vector.

Parameters

vector Vector to be evaluated.

Definition at line 1372 of file statistics.cpp.

◆ box_plot() [2/2]

BoxPlot box_plot	(	const Tensor< type, 1 > &	vector,
		const Tensor< Index, 1 > &	indices
	)

Returns the box and whispers for the elements of the vector that correspond to the given indices.

Parameters

vector	Vector to be evaluated.
indices	Indices of the elements of the vector to be evaluated.

Definition at line 1402 of file statistics.cpp.

◆ calculate_rank_greater()

Tensor< Index, 1 > calculate_rank_greater ( const Tensor< type, 1 > & vector )

Todo:: It does not work well.

Definition at line 205 of file tensor_utilities.cpp.

◆ calculate_rank_less()

Tensor< Index, 1 > calculate_rank_less ( const Tensor< type, 1 > & vector )

Definition at line 220 of file tensor_utilities.cpp.

◆ check_columns_number()

void check_columns_number	(	const Tensor< type, 2 > &	matrix,
		const Index &	columns_number,
		const string &	log
	)

Definition at line 443 of file tensor_utilities.cpp.

◆ check_dimensions()

void check_dimensions	(	const Tensor< type, 2 > &	matrix,
		const Index &	rows_number,
		const Index &	columns_number,
		const string &	log
	)

Definition at line 419 of file tensor_utilities.cpp.

◆ check_size()

void check_size	(	const Tensor< type, 1 > &	vector,
		const Index &	size,
		const string &	log
	)

Definition at line 405 of file tensor_utilities.cpp.

◆ columns_maximums() [1/2]

Tensor< type, 1 > OpenNN::columns_maximums	(	const Tensor< type, 2 > &	matrix,
		const Tensor< Index, 1 > &	columns_indices
	)

Returns the maximums values of given columns. The format is a vector of type values. The size of that vector is equal to the number of given columns.

Parameters

matrix	Used matrix.
columns_indices	Indices of the columns for which the descriptives are to be computed.

Definition at line 1964 of file statistics.cpp.

◆ columns_maximums() [2/2]

Tensor< type, 1 > columns_maximums	(	const Tensor< type, 2 > &	matrix,
		const Tensor< Index, 1 > &	rows_indices,
		const Tensor< Index, 1 > &	columns_indices
	)

Returns the maximums values of given columns. The format is a vector of type values. The size of that vector is equal to the number of given columns.

Parameters

matrix	Used matrix.
rows_indices	Indices of the rows for which the maximums are to be computed.
columns_indices	Indices of the columns for which the maximums are to be computed.

Definition at line 691 of file statistics.cpp.

◆ columns_minimums()

Tensor< type, 1 > columns_minimums	(	const Tensor< type, 2 > &	matrix,
		const Tensor< Index, 1 > &	rows_indices,
		const Tensor< Index, 1 > &	columns_indices
	)

Returns the minimums values of given columns. The format is a vector of type values. The size of that vector is equal to the number of given columns.

Parameters

matrix	Used matrix.
rows_indices	Indices of the rows for which the minimums are to be computed.
columns_indices	Indices of the columns for which the minimums are to be computed.

Definition at line 1893 of file statistics.cpp.

◆ contains_substring()

bool contains_substring	(	const string &	str,
		const string &	sub_str
	)

Returns true if the string contains the given substring, false otherwise.

Parameters

str	String.
sub_str	Substring to search.

Definition at line 691 of file opennn_strings.cpp.

◆ correlation()

Correlation correlation	(	const ThreadPoolDevice *	thread_pool_device,
		const Tensor< type, 2 > &	x,
		const Tensor< type, 2 > &	y
	)

Definition at line 425 of file correlations.cpp.

◆ count_nan()

Index count_nan ( const Tensor< type, 1 > & vector )

Returns the number of nans in the vector.

Parameters

vector Vector to count the NANs

Definition at line 3239 of file statistics.cpp.

◆ count_NAN()

Index count_NAN ( const Tensor< type, 1 > & x )

Definition at line 392 of file tensor_utilities.cpp.

◆ count_tokens() [1/2]

Index count_tokens	(	const string &	s,
		const char &	c
	)

Definition at line 51 of file opennn_strings.cpp.

◆ count_tokens() [2/2]

Index OpenNN::count_tokens	(	string &	str,
		const char &	separator
	)

Returns the number of strings delimited by separator. If separator does not match anywhere in the string, this method returns 0.

Parameters

str	String to be tokenized.

Definition at line 18 of file opennn_strings.cpp.

◆ cross_correlations()

Tensor< type, 1 > cross_correlations	(	const ThreadPoolDevice *	thread_pool_device,
		const Tensor< type, 1 > &	x,
		const Tensor< type, 1 > &	y,
		const Index &	maximum_lags_number
	)

Calculates the cross-correlation between two vectors.

Parameters

x	Vector containing data.
y	Vector for computing the linear correlation with this vector.
maximum_lags_number	Maximum lags for which cross-correlation is calculated.

Definition at line 632 of file correlations.cpp.

◆ date_to_timestamp()

time_t date_to_timestamp	(	const string &	date,
		const Index &	gmt
	)

Transforms human date into timestamp.

Parameters

date	Date in string fortmat to be converted.
gmt	Greenwich Mean Time.

Definition at line 308 of file opennn_strings.cpp.

◆ descriptives() [1/3]

Descriptives descriptives ( const Tensor< type, 1 > & vector )

Returns the minimum, maximum, mean and standard deviation of the elements in the vector.

Parameters

vector Vector to be evaluated.

Definition at line 2012 of file statistics.cpp.

◆ descriptives() [2/3]

Tensor< Descriptives, 1 > descriptives ( const Tensor< type, 2 > & matrix )

Returns the basic descriptives of the columns. The format is a vector of descriptives structures. The size of that vector is equal to the number of columns in this matrix.

Parameters

matrix Used matrix.

Definition at line 1764 of file statistics.cpp.

◆ descriptives() [3/3]

Tensor< Descriptives, 1 > descriptives	(	const Tensor< type, 2 > &	matrix,
		const Tensor< Index, 1 > &	row_indices,
		const Tensor< Index, 1 > &	columns_indices
	)

Returns the basic descriptives of given columns for given rows. The format is a vector of descriptives structures. The size of that vector is equal to the number of given columns.

Parameters

row_indices	Indices of the rows for which the descriptives are to be computed.
columns_indices	Indices of the columns for which the descriptives are to be computed.

Definition at line 1808 of file statistics.cpp.

◆ divide_columns()

void divide_columns	(	Tensor< type, 2 > &	matrix,
		const Tensor< type, 1 > &	vector
	)

Definition at line 40 of file tensor_utilities.cpp.

◆ erase()

void erase	(	string &	s,
		const char &	c
	)

Definition at line 719 of file opennn_strings.cpp.

◆ exponential_correlation()

Correlation exponential_correlation	(	const ThreadPoolDevice *	thread_pool_device,
		const Tensor< type, 1 > &	x,
		const Tensor< type, 1 > &	y
	)

Calculate the coefficients of a exponential regression (a, b) and the correlation among the variables

Parameters

x	Vector of the independent variable.
y	Vector of the dependent variable.

Definition at line 166 of file correlations.cpp.

◆ fill_submatrix()

void fill_submatrix	(	const Tensor< type, 2 > &	matrix,
		const Tensor< Index, 1 > &	rows_indices,
		const Tensor< Index, 1 > &	columns_indices,
		type *	submatrix_pointer
	)

Definition at line 363 of file tensor_utilities.cpp.

◆ fill_tokens()

void fill_tokens	(	const string &	str,
		const char &	separator,
		Tensor< string, 1 > &	tokens
	)

Splits the string into substrings(tokens) wherever separator occurs, and returns a vector with those strings. If separator does not match anywhere in the string, this method returns a single-element list containing this string.

Parameters

str	String to be tokenized.

Definition at line 117 of file opennn_strings.cpp.

◆ filter_missing_values_matrix_matrix()

pair< Tensor< type, 2 >, Tensor< type, 2 > > filter_missing_values_matrix_matrix	(	const Tensor< type, 2 > &	x,
		const Tensor< type, 2 > &	y
	)

Definition at line 538 of file correlations.cpp.

◆ filter_missing_values_vector_vector()

pair< Tensor< type, 1 >, Tensor< type, 1 > > filter_missing_values_vector_vector	(	const Tensor< type, 1 > &	x,
		const Tensor< type, 1 > &	y
	)

Filter the missing values of two vectors.

Definition at line 503 of file correlations.cpp.

◆ get_correlation_values()

Tensor< type, 2 > get_correlation_values ( const Tensor< Correlation, 2 > & correlations )

Definition at line 668 of file correlations.cpp.

◆ get_tokens()

Tensor< string, 1 > get_tokens	(	const string &	str,
		const char &	separator
	)

Splits the string into substrings(tokens) wherever separator occurs, and returns a vector with those strings. If separator does not match anywhere in the string, this method returns a single-element list containing this string.

Parameters

str	String to be tokenized.

Definition at line 61 of file opennn_strings.cpp.

◆ get_trimmed()

string get_trimmed ( const string & str )

Returns a string that has whitespace removed from the start and the end. This includes the ASCII characters "\t", "\n", "\v", "\f", "\r", and " ".

Parameters

str	String to be checked.

Definition at line 729 of file opennn_strings.cpp.

◆ half_normal_distribution_distance()

type half_normal_distribution_distance ( const Tensor< type, 1 > & vector )

Calculates the distance between the empirical distribution of the vector and the half normal distribution.

Parameters

vector Vector to be evaluated.

Definition at line 2747 of file statistics.cpp.

◆ has_numbers()

bool has_numbers ( const Tensor< string, 1 > & v )

Definition at line 773 of file opennn_strings.cpp.

◆ has_strings()

bool has_strings ( const Tensor< string, 1 > & v )

Definition at line 784 of file opennn_strings.cpp.

◆ histogram() [1/2]

Histogram histogram ( const Tensor< bool, 1 > & v )

This method bins the elements of the vector into a given number of equally spaced containers. It returns a vector of two vectors. The size of both subvectors is the number of bins. The first subvector contains the frequency of the bins. The second subvector contains the center of the bins.

Todo:: isnan is not defined for bool.

Definition at line 1675 of file statistics.cpp.

◆ histogram() [2/2]

Histogram histogram	(	const Tensor< type, 1 > &	vector,
		const Index &	bins_number
	)

This method bins the elements of the vector into a given number of equally spaced containers. It returns a vector of two vectors. The size of both subvectors is the number of bins. The first subvector contains the frequency of the bins. The second subvector contains the center of the bins.

Parameters

vector	Vector to obtain the histogram.
bins_number	Number of bins to split the histogram.

Definition at line 1429 of file statistics.cpp.

◆ histogram_centered()

Histogram histogram_centered	(	const Tensor< type, 1 > &	vector,
		const type &	center,
		const Index &	bins_number
	)

This method bins the elements of the vector into a given number of equally spaced containers. It returns a vector of two vectors. The size of both subvectors is the number of bins. The first subvector contains the frequency of the bins. The second subvector contains the center of the bins.

Parameters

vector
center
bins_number

Definition at line 1574 of file statistics.cpp.

◆ histograms()

Tensor< Histogram, 1 > histograms	(	const Tensor< type, 2 > &	matrix,
		const Index &	bins_number
	)

Calculates a histogram for each column, each having a given number of bins. It returns a vector of vectors. The size of the main vector is the number of columns. Each subvector contains the frequencies and centers of that colums.

Parameters

matrix	Data to calculate histograms
bins_number	Number of bins for each histogram.

Todo:: update this method

Definition at line 1739 of file statistics.cpp.

◆ initialize_sequential()

void initialize_sequential ( Tensor< type, 1 > & vector )

Definition at line 17 of file tensor_utilities.cpp.

◆ is_binary()

bool is_binary ( const Tensor< type, 2 > & matrix )

Definition at line 95 of file tensor_utilities.cpp.

◆ is_constant()

bool is_constant ( const Tensor< type, 1 > & vector )

Definition at line 108 of file tensor_utilities.cpp.

◆ is_constant_numeric()

bool is_constant_numeric ( const Tensor< type, 1 > & str )

Returns true if given numeric vector is constant, false otherwise.

Parameters

str	vector to be checked.

Definition at line 256 of file opennn_strings.cpp.

◆ is_constant_string()

bool is_constant_string ( const Tensor< string, 1 > & str )

Returns true if given string vector is constant, false otherwise.

Parameters

str	vector to be checked.

Definition at line 239 of file opennn_strings.cpp.

◆ is_date_time_string()

bool is_date_time_string ( const string & str )

Returns true if given string is a date, false otherwise.

Parameters

str	String to be checked.

Definition at line 272 of file opennn_strings.cpp.

◆ is_equal()

bool is_equal	(	const Tensor< type, 2 > &	matrix,
		const type &	value,
		const type &	tolerance
	)

Definition at line 124 of file tensor_utilities.cpp.

◆ is_false()

bool is_false ( const Tensor< bool, 1 > & tensor )

Definition at line 82 of file tensor_utilities.cpp.

◆ is_less_than()

bool is_less_than	(	const Tensor< type, 1 > &	column,
		const type &	value
	)

Returns true if any value is less or equal than a given value, and false otherwise.

Definition at line 541 of file tensor_utilities.cpp.

◆ is_mixed()

bool is_mixed ( const Tensor< string, 1 > & v )

Returns true if some the elements in a string list are numeric and some others are not numeric.

Parameters

v	String list to be checked.

Definition at line 811 of file opennn_strings.cpp.

◆ is_not_numeric()

bool is_not_numeric ( const Tensor< string, 1 > & v )

Returns true if none element in a string list is numeric, and false otherwise.

Parameters

v	String list to be checked.

Definition at line 797 of file opennn_strings.cpp.

◆ is_numeric_string()

bool is_numeric_string ( const string & str )

Returns true if the string passed as argument represents a number, and false otherwise.

Parameters

str	String to be checked.

Definition at line 200 of file opennn_strings.cpp.

◆ is_numeric_string_vector()

bool is_numeric_string_vector ( const Tensor< string, 1 > & v )

Returns true if all the elements in a string list are numeric, and false otherwise.

Parameters

v	String list to be checked.

Definition at line 762 of file opennn_strings.cpp.

◆ is_zero() [1/2]

bool is_zero ( const Tensor< type, 1 > & tensor )

Definition at line 57 of file tensor_utilities.cpp.

◆ is_zero() [2/2]

bool is_zero	(	const Tensor< type, 1 > &	tensor,
		const type &	limit
	)

Definition at line 69 of file tensor_utilities.cpp.

◆ kronecker_product()

Tensor< type, 2 > kronecker_product	(	const Tensor< type, 1 > &	vector,
		const Tensor< type, 1 > &	other_vector
	)

Definition at line 241 of file tensor_utilities.cpp.

◆ kurtosis()

type kurtosis ( const Tensor< type, 1 > & vector )

Returns the kurtosis of the elements in the vector.

Parameters

vector Vector to be evaluated.

Definition at line 1086 of file statistics.cpp.

◆ l1_norm()

type l1_norm	(	const ThreadPoolDevice *	thread_pool_device,
		const Tensor< type, 1 > &	vector
	)

Definition at line 261 of file tensor_utilities.cpp.

◆ l1_norm_gradient()

void l1_norm_gradient	(	const ThreadPoolDevice *	thread_pool_device,
		const Tensor< type, 1 > &	vector,
		Tensor< type, 1 > &	gradient
	)

Definition at line 271 of file tensor_utilities.cpp.

◆ l1_norm_hessian()

void l1_norm_hessian	(	const ThreadPoolDevice *	,
		const Tensor< type, 1 > &	,
		Tensor< type, 2 > &	hessian
	)

Definition at line 277 of file tensor_utilities.cpp.

◆ l2_norm()

type l2_norm	(	const ThreadPoolDevice *	thread_pool_device,
		const Tensor< type, 1 > &	vector
	)

Returns the l2 norm of a vector.

Definition at line 285 of file tensor_utilities.cpp.

◆ l2_norm_gradient()

void l2_norm_gradient	(	const ThreadPoolDevice *	thread_pool_device,
		const Tensor< type, 1 > &	vector,
		Tensor< type, 1 > &	gradient
	)

Definition at line 306 of file tensor_utilities.cpp.

◆ l2_norm_hessian()

void l2_norm_hessian	(	const ThreadPoolDevice *	thread_pool_device,
		const Tensor< type, 1 > &	vector,
		Tensor< type, 2 > &	hessian
	)

Definition at line 321 of file tensor_utilities.cpp.

◆ linear_correlation()

Correlation linear_correlation	(	const ThreadPoolDevice *	thread_pool_device,
		const Tensor< type, 1 > &	x,
		const Tensor< type, 1 > &	y
	)

Calculate the coefficients of a linear regression (a, b) and the correlation among the variables.

Parameters

x	Vector of the independent variable.
y	Vector of the dependent variable.

Definition at line 21 of file correlations.cpp.

◆ logarithmic_correlation()

Correlation logarithmic_correlation	(	const ThreadPoolDevice *	thread_pool_device,
		const Tensor< type, 1 > &	x,
		const Tensor< type, 1 > &	y
	)

Calculate the coefficients of a logarithmic regression (a, b) and the correlation among the variables

Parameters

x	Vector of the independent variable.
y	Vector of the dependent variable.

Todo:: check

Definition at line 117 of file correlations.cpp.

◆ logistic_correlation_matrix_matrix()

Correlation logistic_correlation_matrix_matrix	(	const ThreadPoolDevice *	thread_pool_device,
		const Tensor< type, 2 > &	x,
		const Tensor< type, 2 > &	y
	)

Definition at line 375 of file correlations.cpp.

◆ logistic_correlation_matrix_vector()

Correlation logistic_correlation_matrix_vector	(	const ThreadPoolDevice *	thread_pool_device,
		const Tensor< type, 2 > &	x,
		const Tensor< type, 1 > &	y
	)

Definition at line 368 of file correlations.cpp.

◆ logistic_correlation_vector_matrix()

Correlation logistic_correlation_vector_matrix	(	const ThreadPoolDevice *	thread_pool_device,
		const Tensor< type, 1 > &	x,
		const Tensor< type, 2 > &	y
	)

Definition at line 316 of file correlations.cpp.

◆ logistic_correlation_vector_vector()

Correlation logistic_correlation_vector_vector	(	const ThreadPoolDevice *	thread_pool_device,
		const Tensor< type, 1 > &	x,
		const Tensor< type, 1 > &	y
	)

Calculate the coefficients of a logistic regression (a, b) and the correlation among the variables

Parameters

x	Vector of the independent variable.
y	Vector of the dependent variable.

Definition at line 267 of file correlations.cpp.

◆ maximal_columns_indices()

Tensor< Index, 2 > maximal_columns_indices	(	const Tensor< type, 2 > &	matrix,
		const Index &	maximum_number
	)

Returns a matrix in which each of the columns contain the maximal indices of each of the columns of the original matrix.

Definition at line 3126 of file statistics.cpp.

◆ maximal_index()

Index maximal_index ( const Tensor< type, 1 > & vector )

Returns the index of the largest element in the vector.

Definition at line 2949 of file statistics.cpp.

◆ maximal_indices() [1/2]

Tensor< Index, 1 > maximal_indices	(	const Tensor< type, 1 > &	vector,
		const Index &	number
	)

Returns the indices of the largest elements in the vector.

Parameters

number Number of maximal indices to be computed.

Todo:: Clean variables names minim, vector_!!!

Definition at line 3021 of file statistics.cpp.

◆ maximal_indices() [2/2]

Tensor< Index, 1 > maximal_indices ( const Tensor< type, 2 > & matrix )

Returns the row and column indices corresponding to the entry with maximum value.

Definition at line 3096 of file statistics.cpp.

◆ maximum() [1/3]

Index maximum ( const Tensor< Index, 1 > & vector )

Returns the largest element of a index vector.

Parameters

vector Vector to obtain the maximum value.

Definition at line 664 of file statistics.cpp.

◆ maximum() [2/3]

type maximum ( const Tensor< type, 1 > & vector )

Returns the largest element in the vector.

Parameters

vector Vector to obtain the maximum value.

Definition at line 614 of file statistics.cpp.

◆ maximum() [3/3]

type maximum	(	const Tensor< type, 1 > &	vector,
		const Tensor< Index, 1 > &	indices
	)

Returns the largest element in the vector.

Parameters

vector	Vector to obtain the maximum value.
indices	Vector of used indices.

Definition at line 638 of file statistics.cpp.

◆ mean() [1/6]

type mean ( const Tensor< type, 1 > & vector )

Returns the mean of the elements in the vector.

Parameters

vector Vector to be evaluated.

Definition at line 796 of file statistics.cpp.

◆ mean() [2/6]

type mean	(	const Tensor< type, 1 > &	vector,
		const Index &	begin,
		const Index &	end
	)

Returns the mean of the subvector defined by a start and end elements.

Parameters

vector	Vector to be evaluated.
begin	Start element.
end	End element.

Definition at line 763 of file statistics.cpp.

◆ mean() [3/6]

Tensor< type, 1 > mean ( const Tensor< type, 2 > & matrix )

Returns a vector with the mean values of all the matrix columns. The size is equal to the number of columns in the matrix.

Parameters

matrix Matrix used.

Definition at line 2177 of file statistics.cpp.

◆ mean() [4/6]

type mean	(	const Tensor< type, 2 > &	matrix,
		const Index &	column_index
	)

Returns a vector with the mean values of all the matrix columns. The size is equal to the number of columns in the matrix.

Definition at line 2379 of file statistics.cpp.

◆ mean() [5/6]

Tensor< type, 1 > mean	(	const Tensor< type, 2 > &	matrix,
		const Tensor< Index, 1 > &	columns_indices
	)

Returns a vector with the mean values of given columns. The size of the vector is equal to the size of the column indices vector.

Parameters

columns_indices Indices of columns.

Definition at line 2223 of file statistics.cpp.

◆ mean() [6/6]

Tensor< type, 1 > mean	(	const Tensor< type, 2 > &	matrix,
		const Tensor< Index, 1 > &	row_indices,
		const Tensor< Index, 1 > &	columns_indices
	)

Returns a vector with the mean values of given columns for given rows. The size of the vector is equal to the size of the column indices vector.

Parameters

matrix	Matrix used.
row_indices	Indices of rows.
columns_indices	Indices of columns.

Definition at line 2258 of file statistics.cpp.

◆ median() [1/5]

type median ( const Tensor< type, 1 > & vector )

Returns the median of the elements in the vector

Parameters

vector Vector to be evaluated.

Definition at line 1137 of file statistics.cpp.

◆ median() [2/5]

Tensor< type, 1 > median ( const Tensor< type, 2 > & matrix )

Returns a vector with the median values of all the matrix columns. The size is equal to the number of columns in the matrix.

Definition at line 2438 of file statistics.cpp.

◆ median() [3/5]

type median	(	const Tensor< type, 2 > &	matrix,
		const Index &	column_index
	)

Returns a vector with the median values of all the matrix columns. The size is equal to the number of columns in the matrix.

Definition at line 2485 of file statistics.cpp.

◆ median() [4/5]

Tensor< type, 1 > median	(	const Tensor< type, 2 > &	matrix,
		const Tensor< Index, 1 > &	columns_indices
	)

Returns a vector with the median values of given columns. The size of the vector is equal to the size of the column indices vector.

Parameters

columns_indices Indices of columns.

Definition at line 2543 of file statistics.cpp.

◆ median() [5/5]

Tensor< type, 1 > median	(	const Tensor< type, 2 > &	matrix,
		const Tensor< Index, 1 > &	row_indices,
		const Tensor< Index, 1 > &	columns_indices
	)

Returns a vector with the median values of given columns for given rows. The size of the vector is equal to the size of the column indices vector.

Parameters

row_indices	Indices of rows.
columns_indices	Indices of columns.

Definition at line 2582 of file statistics.cpp.

◆ minimal_index()

Index minimal_index ( const Tensor< type, 1 > & vector )

Returns the index of the smallest element in the vector.

Definition at line 2925 of file statistics.cpp.

◆ minimal_indices() [1/2]

Tensor< Index, 1 > minimal_indices	(	const Tensor< type, 1 > &	vector,
		const Index &	number
	)

Returns the indices of the smallest elements in the vector.

Parameters

number Number of minimal indices to be computed.

Definition at line 2974 of file statistics.cpp.

◆ minimal_indices() [2/2]

Tensor< Index, 1 > minimal_indices ( const Tensor< type, 2 > & matrix )

Returns the row and column indices corresponding to the entry with minimum value.

Definition at line 3067 of file statistics.cpp.

◆ minimum() [1/3]

Index minimum ( const Tensor< Index, 1 > & vector )

Returns the smallest element of a index vector.

Parameters

vector Vector to obtain the minimum value.

Definition at line 563 of file statistics.cpp.

◆ minimum() [2/3]

type minimum ( const Tensor< type, 1 > & vector )

Returns the smallest element of a type vector.

Parameters

vector Vector to obtain the minimum value.

Definition at line 540 of file statistics.cpp.

◆ minimum() [3/3]

type minimum	(	const Tensor< type, 1 > &	vector,
		const Tensor< Index, 1 > &	indices
	)

Returns the smallest element of a type vector.

Parameters

vector	Vector to obtain the minimum value.
indices	Vector of used indices.

Definition at line 587 of file statistics.cpp.

◆ multiply_rows()

void multiply_rows	(	Tensor< type, 2 > &	matrix,
		const Tensor< type, 1 > &	vector
	)

Definition at line 23 of file tensor_utilities.cpp.

◆ normal_distribution_distance()

type normal_distribution_distance ( const Tensor< type, 1 > & vector )

Calculates the distance between the empirical distribution of the vector and the normal distribution.

Parameters

vector Vector to be evaluated.

Definition at line 2699 of file statistics.cpp.

◆ normality_parameter()

type normality_parameter ( const Tensor< type, 1 > & vector )

Todo:

Definition at line 2841 of file statistics.cpp.

◆ percentiles()

Tensor< type, 1 > percentiles ( const Tensor< type, 1 > & vector )

Returns a vector with the percentiles of a vector given.

Aempirical method

Definition at line 3164 of file statistics.cpp.

◆ perform_distribution_distance_analysis()

Index perform_distribution_distance_analysis ( const Tensor< type, 1 > & vector )

Calculates the distance between the empirical distribution of the vector and the normal, half-normal and uniform cumulative distribution. It returns 0, 1 or 2 if the closest distribution is the normal, half-normal or the uniform, respectively.

Todo:: review.

Definition at line 2089 of file statistics.cpp.

◆ perform_Householder_QR_decomposition()

Tensor< type, 1 > perform_Householder_QR_decomposition	(	const Tensor< type, 2 > &	A,
		const Tensor< type, 1 > &	b
	)

Uses Eigen to solve the system of equations by means of the Householder QR decomposition.

Definition at line 347 of file tensor_utilities.cpp.

◆ power_correlation()

Correlation power_correlation	(	const ThreadPoolDevice *	thread_pool_device,
		const Tensor< type, 1 > &	x,
		const Tensor< type, 1 > &	y
	)

Calculate the coefficients of a power regression (a, b) and the correlation among the variables

Parameters

x	Vector of the independent variable.
y	Vector of the dependent variable.

Definition at line 213 of file correlations.cpp.

◆ prepend()

string prepend	(	const string &	pre,
		const string &	str
	)

Prepends the string pre to the beginning of the string str and returns the whole string.

Parameters

pre	String to be prepended.
str	original string.

Definition at line 749 of file opennn_strings.cpp.

◆ quartiles() [1/2]

Tensor< type, 1 > quartiles ( const Tensor< type, 1 > & vector )

Returns the quartiles of the elements in the vector.

Parameters

vector Vector to be evaluated.

Definition at line 1189 of file statistics.cpp.

◆ quartiles() [2/2]

Tensor< type, 1 > quartiles	(	const Tensor< type, 1 > &	vector,
		const Tensor< Index, 1 > &	indices
	)

Returns the quartiles of the elements of the vector that correspond to the given indices.

Parameters

vector	Vector to be evaluated.
indices	Indices of the elements of the vector to be evaluated.

Definition at line 1276 of file statistics.cpp.

◆ range()

type range ( const Tensor< type, 1 > & vector )

Definition at line 2000 of file statistics.cpp.

◆ replace()

void replace	(	string &	source,
		const string &	find_what,
		const string &	replace_with
	)

Definition at line 861 of file opennn_strings.cpp.

◆ replace_substring()

void replace_substring	(	Tensor< string, 1 > &	vector,
		const string &	find_what,
		const string &	replace_with
	)

Replaces a substring by another one in each element of this vector.

Parameters

find_what	String to be replaced.
replace_with	String to be put instead.

Definition at line 843 of file opennn_strings.cpp.

◆ save_csv()

void save_csv	(	const Tensor< type, 2 > &	data,
		const string &	filename
	)

Definition at line 164 of file tensor_utilities.cpp.

◆ scale_logarithmic()

void scale_logarithmic	(	Tensor< type, 2 > &	matrix,
		const Index &	column_index
	)

Definition at line 161 of file scaling.cpp.

◆ scale_mean_standard_deviation()

void scale_mean_standard_deviation	(	Tensor< type, 2 > &	matrix,
		const Index &	column_index,
		const Descriptives &	column_descriptives
	)

Scales the given input variables with given mean and standard deviation values. It updates the input variable of the matrix matrix.

Parameters

column_descriptives	vector of descriptives structures for the input variables.
column_index	Index of the input to be scaled.

Definition at line 48 of file scaling.cpp.

◆ scale_minimum_maximum() [1/3]

Tensor< type, 1 > scale_minimum_maximum ( const Tensor< type, 1 > & x )

Definition at line 108 of file scaling.cpp.

◆ scale_minimum_maximum() [2/3]

Tensor< type, 2 > scale_minimum_maximum ( const Tensor< type, 2 > & x )

Definition at line 130 of file scaling.cpp.

◆ scale_minimum_maximum() [3/3]

void scale_minimum_maximum	(	Tensor< type, 2 > &	matrix,
		const Index &	column_index,
		const Descriptives &	column_descriptives,
		const type &	min_range,
		const type &	max_range
	)

Scales the given input variable with given minimum and maximum values. It updates the input variables of the matrix matrix.

Parameters

column_descriptives	vector with the descriptives of the input variable.
column_index	Index of the input to be scaled.

Definition at line 88 of file scaling.cpp.

◆ scale_minimum_maximum_binary()

void scale_minimum_maximum_binary	(	Tensor< type, 2 > &	matrix,
		const type &	value_1,
		const type &	value_2,
		const Index &	column_index
	)

Definition at line 14 of file scaling.cpp.

◆ scale_standard_deviation()

void scale_standard_deviation	(	Tensor< type, 2 > &	matrix,
		const Index &	column_index,
		const Descriptives &	column_descriptives
	)

Scales the given input variables with given standard deviation values. It updates the input variable of the matrix matrix.

Parameters

inputs_statistics	vector of descriptives structures for the input variables.
column_index	Index of the input to be scaled.

Definition at line 72 of file scaling.cpp.

◆ scrub_missing_values()

void scrub_missing_values	(	Tensor< type, 2 > &	matrix,
		const type &	value
	)

Definition at line 235 of file tensor_utilities.cpp.

◆ standard_deviation() [1/3]

type standard_deviation ( const Tensor< type, 1 > & vector )

Returns the standard deviation of the elements in the vector.

Parameters

vector Vector to be evaluated.

Definition at line 939 of file statistics.cpp.

◆ standard_deviation() [2/3]

Tensor< type, 1 > standard_deviation	(	const Tensor< type, 1 > &	vector,
		const Index &	period
	)

Definition at line 1000 of file statistics.cpp.

◆ standard_deviation() [3/3]

type standard_deviation	(	const Tensor< type, 1 > &	vector,
		const Tensor< Index, 1 > &	indices
	)

Returns the standard deviation of the elements in the vector.

Parameters

vector Vector to be evaluated.

Definition at line 971 of file statistics.cpp.

◆ sum_diagonal()

void sum_diagonal	(	Tensor< type, 2 > &	matrix,
		const type &	value
	)

Definition at line 336 of file tensor_utilities.cpp.

◆ to_type_vector()

Tensor< type, 1 > to_type_vector	(	const string &	str,
		const char &	separator
	)

Returns a new vector with the elements of this string vector casted to type.

Definition at line 169 of file opennn_strings.cpp.

◆ total_frequencies()

Tensor< Index, 1 > total_frequencies ( const Tensor< Histogram, 1 > & histograms )

Returns a vector containing the sum of the frequencies of the bins to which this vector belongs.

Parameters

histograms Used histograms.

Definition at line 1716 of file statistics.cpp.

◆ trim()

void trim ( string & str )

Removes whitespaces from the start and the end of the string passed as argument. This includes the ASCII characters "\t", "\n", "\v", "\f", "\r", and " ".

Parameters

str	String to be checked.

Definition at line 705 of file opennn_strings.cpp.

◆ uniform_distribution_distance()

type uniform_distribution_distance ( const Tensor< type, 1 > & vector )

Calculates the distance between the empirical distribution of the vector and the uniform distribution.

Parameters

vector Vector to be evaluated.

Definition at line 2795 of file statistics.cpp.

◆ unscale_logarithmic()

void unscale_logarithmic	(	Tensor< type, 2 > &	matrix,
		const Index &	column_index
	)

Unscales the given input variables with given logarithmic values. It updates the input variable of the matrix matrix.

Parameters

inputs_statistics	vector of descriptives structures for the input variables.
column_index	Index of the input to be scaled.

Definition at line 259 of file scaling.cpp.

◆ unscale_mean_standard_deviation()

void unscale_mean_standard_deviation	(	Tensor< type, 2 > &	matrix,
		const Index &	column_index,
		const Descriptives &	column_descriptives
	)

Uncales the given input variables with given mean and standard deviation values. It updates the input variable of the matrix matrix.

Parameters

column_descriptives	vector of descriptives structures for the input variables.
column_index	Index of the input to be scaled.

Definition at line 216 of file scaling.cpp.

◆ unscale_minimum_maximum()

void unscale_minimum_maximum	(	Tensor< type, 2 > &	matrix,
		const Index &	column_index,
		const Descriptives &	column_descriptives,
		const type &	min_range,
		const type &	max_range
	)

Unscales the given input variable with given minimum and maximum values. It updates the input variables of the matrix matrix.

Parameters

column_descriptives	vector with the descriptives of the input variable.
column_index	Index of the input to be scaled.

Definition at line 191 of file scaling.cpp.

◆ unscale_standard_deviation()

void unscale_standard_deviation	(	Tensor< type, 2 > &	matrix,
		const Index &	column_index,
		const Descriptives &	column_descriptives
	)

Unscales the given input variables with given standard deviation values. It updates the input variable of the matrix matrix.

Parameters

inputs_statistics	vector of descriptives structures for the input variables.
column_index	Index of the input to be scaled.

Definition at line 237 of file scaling.cpp.

◆ variance() [1/2]

type variance ( const Tensor< type, 1 > & vector )

Returns the variance of the elements in the vector.

Parameters

vector Vector to be evaluated.

Definition at line 840 of file statistics.cpp.

◆ variance() [2/2]

type variance	(	const Tensor< type, 1 > &	vector,
		const Tensor< Index, 1 > &	indices
	)

Returns the variance of the elements in the vector.

Parameters

vector Vector to be evaluated.

Definition at line 888 of file statistics.cpp.

◆ variation_percentage()

Tensor< type, 1 > variation_percentage ( const Tensor< type, 1 > & vector )

Definition at line 2905 of file statistics.cpp.

Classes

Typedefs

Enumerations

Functions

Detailed Description

Typedef Documentation

◆ type

Enumeration Type Documentation

◆ CorrelationMethod

◆ Scaler

Function Documentation

◆ are_equal() [1/2]

◆ are_equal() [2/2]

◆ assemble_matrix_matrix()

◆ assemble_matrix_vector()

◆ assemble_vector_matrix()

◆ assemble_vector_vector()

◆ asymmetry()

◆ autocorrelations()

◆ box_plot() [1/2]

◆ box_plot() [2/2]

◆ calculate_rank_greater()

◆ calculate_rank_less()

◆ check_columns_number()

◆ check_dimensions()

◆ check_size()

◆ columns_maximums() [1/2]

◆ columns_maximums() [2/2]

◆ columns_minimums()

◆ contains_substring()

◆ correlation()

◆ count_nan()

◆ count_NAN()

◆ count_tokens() [1/2]

◆ count_tokens() [2/2]

◆ cross_correlations()

◆ date_to_timestamp()

◆ descriptives() [1/3]

◆ descriptives() [2/3]

◆ descriptives() [3/3]

◆ divide_columns()

◆ erase()

◆ exponential_correlation()

◆ fill_submatrix()

◆ fill_tokens()

◆ filter_missing_values_matrix_matrix()

◆ filter_missing_values_vector_vector()

◆ get_correlation_values()

◆ get_tokens()

◆ get_trimmed()

◆ half_normal_distribution_distance()

◆ has_numbers()

◆ has_strings()

◆ histogram() [1/2]

◆ histogram() [2/2]

◆ histogram_centered()

◆ histograms()

◆ initialize_sequential()

◆ is_binary()

◆ is_constant()

◆ is_constant_numeric()

◆ is_constant_string()

◆ is_date_time_string()

◆ is_equal()

◆ is_false()

◆ is_less_than()

◆ is_mixed()

◆ is_not_numeric()

◆ is_numeric_string()

◆ is_numeric_string_vector()

◆ is_zero() [1/2]

◆ is_zero() [2/2]

◆ kronecker_product()

◆ kurtosis()

◆ l1_norm()

◆ l1_norm_gradient()

◆ l1_norm_hessian()

◆ l2_norm()

◆ l2_norm_gradient()

◆ l2_norm_hessian()