#include <toolkits/ml_data_2/iterators/ml_data_iterator_base.hpp>

Public Member Functions
virtual	~ml_data_iterator_base ()

virtual void	reset ()
	Resets the iterator to the start of the sframes in ml_data.

virtual bool	done () const
	Returns true if the iteration is done, false otherwise.

size_t	row_index () const

size_t	unsliced_row_index () const
	Returns the absolute row index.

template<typename Entry >
GL_HOT_INLINE void	fill_observation (std::vector< Entry > &x) const

void	fill_untranslated_values (std::vector< flexible_type > &x) const GL_HOT_INLINE_FLATTEN

void	fill_observation (SparseVector &x) const GL_HOT_INLINE_FLATTEN

void	fill_observation (DenseVector &x) const GL_HOT_INLINE_FLATTEN

template<typename DenseRowXpr >
GL_HOT_INLINE_FLATTEN void	fill_eigen_row (DenseRowXpr &&x) const

void	fill_observation (composite_row_container &crc) GL_HOT_INLINE_FLATTEN

double	target_value () const GL_HOT_INLINE_FLATTEN

size_t	target_index () const GL_HOT_INLINE_FLATTEN

ml_data_row_reference	get_reference () const

const ml_data &	ml_data_source () const

ml_data_internal::entry_value	_raw_row_entry (size_t raw_index) const GL_HOT_INLINE_FLATTEN

Protected Member Functions
ml_data_internal::entry_value_iterator	current_data_iter () const GL_HOT_INLINE_FLATTEN

size_t	current_block_row_index () const GL_HOT_INLINE_FLATTEN

void	advance_row () GL_HOT_INLINE_FLATTEN

void	setup_block_containing_current_row_index () GL_HOT_NOINLINE
	Loads the block containing the row index row_index.

void	load_next_block () GL_HOT_NOINLINE

Protected Attributes
bool	add_side_information = false

size_t	iter_row_index_start = -1

size_t	iter_row_index_end = -1

size_t	current_row_index = -1

size_t	current_block_index = -1

size_t	current_in_block_index

size_t	global_row_start

size_t	max_row_size

size_t	num_dimensions

Detailed Description

Just a simple iterator on the ml_data class. It's just a convenience structure that keeps track of everything relevant for the toolkits.

Definition at line 38 of file ml_data_iterator_base.hpp.

Constructor & Destructor Documentation

◆ ~ml_data_iterator_base()

virtual turi::v2::ml_data_iterator_base::~ml_data_iterator_base ( )

inlinevirtual

Yup, need this.

Definition at line 62 of file ml_data_iterator_base.hpp.

Member Function Documentation

◆ _raw_row_entry()

ml_data_internal::entry_value turi::v2::ml_data_iterator_base::_raw_row_entry ( size_t raw_index ) const

inline

Return the raw value of the internal row storage. Used by some of the internal ml_data processing routines.

Definition at line 346 of file ml_data_iterator_base.hpp.

◆ advance_row()

void turi::v2::ml_data_iterator_base::advance_row ( )

inlineprotected

Advance to the next row.

Definition at line 430 of file ml_data_iterator_base.hpp.

◆ current_block_row_index()

size_t turi::v2::ml_data_iterator_base::current_block_row_index ( ) const

inlineprotected

Return a pointer to the current location in the data.

Definition at line 417 of file ml_data_iterator_base.hpp.

◆ current_data_iter()

ml_data_internal::entry_value_iterator turi::v2::ml_data_iterator_base::current_data_iter ( ) const

inlineprotected

Return a pointer to the current location in the data.

Definition at line 407 of file ml_data_iterator_base.hpp.

◆ fill_eigen_row()

template<typename DenseRowXpr >

GL_HOT_INLINE_FLATTEN void turi::v2::ml_data_iterator_base::fill_eigen_row ( DenseRowXpr && x ) const

inline

Fill a row of an Eigen Dense Vector, from the current location in the iteration.

Note: The 0th category is used as a reference category.

Example:

Eigen::MatrixXd X;

...

it.fill_eigen_row(X.row(row_idx));

Parameters

[in,out] x An eigen row expression.

Definition at line 269 of file ml_data_iterator_base.hpp.

◆ fill_observation() [1/4]

template<typename Entry >

GL_HOT_INLINE void turi::v2::ml_data_iterator_base::fill_observation ( std::vector< Entry > & x ) const

inline

Fill an observation vector, represented as an ml_data_entry struct. (column_index, index, value) pairs, from the current location in the iteration. For each column:

Categotical: Returns (col_id, v, 1) Numeric : Returns (col_id, 0, v) Vector : Returns (col_id, i, v) for each (i,v) in vector.

Example use is given by the following code:

std::vector<ml_data_entry> x;

for(ml_data_iterator it(data); !it.is_done(); ++it) { it.fill_observation(x); double y = it.target_value(); ... }

Definition at line 107 of file ml_data_iterator_base.hpp.

◆ fill_observation() [2/4]

void turi::v2::ml_data_iterator_base::fill_observation ( SparseVector & x ) const

inline

Fill an observation vector, represented as an Eigen Sparse Vector, from the current location in the iteration.

Note: A reference category is used in this version of the function.; For performance reasons, this function does not check for new categories during predict time. That must be checked externally.

This function returns a flattened version of the vector provided by the std::pair version of fill_observation.

Example

Warning: This only works when the SFrame is "mapped" to integer keys.

For a dataset with a 3 column SFrame

Row 1: 1.0 0(categorical) <9.1, 2.4> Row 2: 2.0 1(categorical) <1.0, 4.5>

with index = {1,2,2}

the SparseVector format would return

Row 1: < (0, 1.0), (1, 1) ,(3, 9.1) ,(4, 2.4)> Row 2: < (0, 2.0), (2, 1) ,(3, 1.0) ,(4, 4.5)>

Note: The '0'th category is used as reference.

Parameters

[in,out] x Data containing everything!

Definition at line 184 of file ml_data_iterator_base.hpp.

◆ fill_observation() [3/4]

void turi::v2::ml_data_iterator_base::fill_observation ( DenseVector & x ) const

inline

Fill an observation vector, represented as an Eigen Dense Vector, from the current location in the iteration.

Note: The 0th category is used as a reference category.; For performance reasons, this function does not check for new categories during predict time. That must be checked externally.

This function returns a flattened version of the vector provided by the std::pair version of fill_observation.

Example

Warning: This only works when the SFrame is "mapped" to intger keys.

For a dataset with a 3 column SFrame

Row 1: 1.0 0(categorical) <9.1, 2.4> Row 2: 2.0 1(categorical) <1.0, 4.5>

with index = {1,2,2}

the DenseVector format would return

Row 1: <1.0, 0, 1, 9.1, 2.4> Row 2: <2.0, 1, 0, 1.0, 4.5>

Parameters

[in,out] x Data containing everything!

Definition at line 232 of file ml_data_iterator_base.hpp.

◆ fill_observation() [4/4]

void turi::v2::ml_data_iterator_base::fill_observation ( composite_row_container & crc )

inline

Fill a composite row container. The composite row container must have its specification set; this specification is used to then fill the observation.

Definition at line 285 of file ml_data_iterator_base.hpp.

◆ fill_untranslated_values()

void turi::v2::ml_data_iterator_base::fill_untranslated_values ( std::vector< flexible_type > & x ) const

inline

Fill an observation vector with the untranslated columns, if any have been specified at setup time. These columns are simply mapped back to their sarray counterparts.

The metadata surrounding the original column indices are

Definition at line 133 of file ml_data_iterator_base.hpp.

◆ get_reference()

ml_data_row_reference turi::v2::ml_data_iterator_base::get_reference ( ) const

inline

Return a row reference instead of the actual observation. The row reference can be used to fill the observation vectors just like the iterator can, and can easily be passed around by value.

Definition at line 323 of file ml_data_iterator_base.hpp.

◆ load_next_block()

void turi::v2::ml_data_iterator_base::load_next_block ( )

protected

Loads the next block, resetting all the values so iteration will be supported over the next row.

◆ ml_data_source()

const ml_data& turi::v2::ml_data_iterator_base::ml_data_source ( ) const

inline

Return the data this iterator is working with.

Definition at line 339 of file ml_data_iterator_base.hpp.

◆ row_index()

size_t turi::v2::ml_data_iterator_base::row_index ( ) const

inline

Returns the current index of the sframe row, respecting all slicing operations on the original ml_data.

Definition at line 81 of file ml_data_iterator_base.hpp.

◆ target_index()

size_t turi::v2::ml_data_iterator_base::target_index ( ) const

inline

Returns the current categorical target index, if present, or 0 if not present.

Definition at line 309 of file ml_data_iterator_base.hpp.

◆ target_value()

double turi::v2::ml_data_iterator_base::target_value ( ) const

inline

Returns the current target value, if present, or 1 if not present. If the target column is supposed to be a categorical value, then use categorical_target_index().

Definition at line 298 of file ml_data_iterator_base.hpp.

Member Data Documentation

◆ add_side_information

bool turi::v2::ml_data_iterator_base::add_side_information = false

protected

The options used for this iterator.

Definition at line 366 of file ml_data_iterator_base.hpp.

◆ current_block_index

size_t turi::v2::ml_data_iterator_base::current_block_index = -1

protected

Index of the currently loaded block.

Definition at line 375 of file ml_data_iterator_base.hpp.

◆ current_in_block_index

size_t turi::v2::ml_data_iterator_base::current_in_block_index

protected

The current index pointed to inside the block.

Definition at line 379 of file ml_data_iterator_base.hpp.

◆ current_row_index

size_t turi::v2::ml_data_iterator_base::current_row_index = -1

protected

Current row index for this iterator.

Definition at line 374 of file ml_data_iterator_base.hpp.

◆ global_row_start

size_t turi::v2::ml_data_iterator_base::global_row_start

protected

The absolute values of the global row starting locations.

Definition at line 383 of file ml_data_iterator_base.hpp.

◆ iter_row_index_end

size_t turi::v2::ml_data_iterator_base::iter_row_index_end = -1

protected

Ending row index for this iterator.

Definition at line 373 of file ml_data_iterator_base.hpp.

◆ iter_row_index_start

size_t turi::v2::ml_data_iterator_base::iter_row_index_start = -1

protected

Starting row index for this iterator.

Definition at line 372 of file ml_data_iterator_base.hpp.

◆ max_row_size

size_t turi::v2::ml_data_iterator_base::max_row_size

protected

The maximum row size across all rows in the given ml_data object. Each row's size is defined to be the number of unpacked features in that row. For example, this is useful when one needs to preallocate a vector to be the largest size needed for any row that will be given by this iterator.

Definition at line 391 of file ml_data_iterator_base.hpp.

◆ num_dimensions

size_t turi::v2::ml_data_iterator_base::num_dimensions

protected

The total sum of column sizes.

Definition at line 395 of file ml_data_iterator_base.hpp.

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

toolkits/ml_data_2/iterators/ml_data_iterator_base.hpp

Public Member Functions

Protected Member Functions

Protected Attributes

Detailed Description

Constructor & Destructor Documentation

◆ ~ml_data_iterator_base()

Member Function Documentation

◆ _raw_row_entry()

◆ advance_row()

◆ current_block_row_index()

◆ current_data_iter()

◆ fill_eigen_row()

◆ fill_observation() [1/4]

◆ fill_observation() [2/4]

Example

◆ fill_observation() [3/4]

Example

◆ fill_observation() [4/4]

◆ fill_untranslated_values()

◆ get_reference()

◆ load_next_block()

◆ ml_data_source()

◆ row_index()

◆ target_index()

◆ target_value()

Member Data Documentation

◆ add_side_information

◆ current_block_index

◆ current_in_block_index

◆ current_row_index

◆ global_row_start

◆ iter_row_index_end

◆ iter_row_index_start

◆ max_row_size

◆ num_dimensions