#include <toolkits/ml_data_2/indexing/column_unique_indexer.hpp>

Public Member Functions
	column_unique_indexer ()

void	initialize ()

size_t	map_value_to_index (size_t thread_idx, const flexible_type &feature) GL_HOT

size_t	immutable_map_value_to_index (const flexible_type &feature) const

void	insert_values_into_index (const std::vector< flexible_type > &features)

void	register_real_value (const flexible_type &feature)

void	finalize ()

flexible_type	map_index_to_value (size_t idx) const

std::set< flex_type_enum >	extract_key_types () const

size_t	indexed_column_size () const

size_t	get_version () const

void	save_impl (turi::oarchive &oarc) const

void	load_version (turi::iarchive &iarc, size_t version)

void	set_values (std::vector< flexible_type > &&values)

std::shared_ptr< column_indexer >	create_cleared_copy () const

std::function< flexible_type(const flexible_type &)>	deindexing_lambda () const

std::function< flexible_type(const flexible_type &)>	indexing_lambda () const

Static Public Member Functions
static std::shared_ptr< column_indexer >	factory_create (const std::map< std::string, variant_type > &creation_options)

Public Attributes
std::string	column_name

ml_column_mode	mode

flex_type_enum	original_column_type

std::map< std::string, flexible_type >	options

Detailed Description

column_metadata contains "meta data" concerning indexing of a single column of an SFrame. A collection of meta_data column objects is "all" the metadata required in the ml_data container.

Definition at line 34 of file column_unique_indexer.hpp.

Constructor & Destructor Documentation

◆ column_unique_indexer()

turi::v2::ml_data_internal::column_unique_indexer::column_unique_indexer ( )

Default constructor; does nothing; Initialize from a serialization stream

Member Function Documentation

◆ create_cleared_copy()

std::shared_ptr<column_indexer> turi::v2::ml_data_internal::column_unique_indexer::create_cleared_copy ( ) const

virtual

Create a copy with the index cleared.

Implements turi::v2::ml_data_internal::column_indexer.

◆ deindexing_lambda()

std::function<flexible_type(const flexible_type&)> turi::v2::ml_data_internal::column_unique_indexer::deindexing_lambda ( ) const

virtual

Returns a lambda function that can be used as a lambda function for deindexing a column.

Implements turi::v2::ml_data_internal::column_indexer.

◆ extract_key_types()

std::set<flex_type_enum> turi::v2::ml_data_internal::column_unique_indexer::extract_key_types ( ) const

virtual

Calculates the type of the values held in the index. This may be different from original_column_type – if the original_column_type is a DICT or LIST, this will return a set of the actual types present. If the values are inconsistent, then an error is raised.

This method is useful when a metadata built with a dictionary is also used to map simple categorical variables.

Reimplemented from turi::v2::ml_data_internal::column_indexer.

◆ factory_create()

static std::shared_ptr<column_indexer> turi::v2::ml_data_internal::column_indexer::factory_create ( const std::map< std::string, variant_type > & creation_options )

staticinherited

The factory method for loading and instantiating the proper class

◆ finalize()

void turi::v2::ml_data_internal::column_unique_indexer::finalize ( )

virtual

Call this when all calls to map_value_to_index are completed.

Implements turi::v2::ml_data_internal::column_indexer.

◆ get_version()

size_t turi::v2::ml_data_internal::column_unique_indexer::get_version ( ) const

virtual

Returns the current version used for the serialization.

Implements turi::v2::ml_data_internal::column_indexer.

◆ immutable_map_value_to_index()

size_t turi::v2::ml_data_internal::column_unique_indexer::immutable_map_value_to_index ( const flexible_type & feature ) const

virtual

Returns the index associated with the "feature" value.

Note: Only used if is_categorical is true.

If the value in the feature column was already seen, then the index already associated with that value is returned. If not, size_t(-1) is returned.

Parameters

[in] feature The value in the feature column to map to the index.

Returns: An index associated with the given value. If the index is not present. We return size_t(-1).

Implements turi::v2::ml_data_internal::column_indexer.

◆ indexed_column_size()

size_t turi::v2::ml_data_internal::column_unique_indexer::indexed_column_size ( ) const

inlinevirtual

Returns the size of the column.

Numeric : 1 Categorical : # Unique categories Vector : Size of the vector.

Returns: Column size.

Implements turi::v2::ml_data_internal::column_indexer.

Definition at line 138 of file column_unique_indexer.hpp.

◆ indexing_lambda()

std::function<flexible_type(const flexible_type&)> turi::v2::ml_data_internal::column_unique_indexer::indexing_lambda ( ) const

virtual

Returns a lambda function that can be used as a lambda function for indexing a column.

Does not add any new index values.

Implements turi::v2::ml_data_internal::column_indexer.

◆ initialize()

void turi::v2::ml_data_internal::column_unique_indexer::initialize ( )

virtual

Initialize the index mapping and setup. There are certain internal parallel things that need to be set up before map_value_to_index works. Call this before looping over map_value_to_index, then call finalize() when done.

Implements turi::v2::ml_data_internal::column_indexer.

◆ insert_values_into_index()

void turi::v2::ml_data_internal::column_unique_indexer::insert_values_into_index ( const std::vector< flexible_type > & features )

virtual

Some of the ml_data tests currently depend on the order of insertion into the index, which is now done in parallel and thus not deterministic. This function allows the user to remove that randomness by inserting all indices in a specified order.

NOTE: This function is not thread safe; only call it from one thread.

Reimplemented from turi::v2::ml_data_internal::column_indexer.

◆ load_version()

void turi::v2::ml_data_internal::column_unique_indexer::load_version	(	turi::iarchive &	iarc,
		size_t	version
	)

virtual

Load the object.

Implements turi::v2::ml_data_internal::column_indexer.

◆ map_index_to_value()

flexible_type turi::v2::ml_data_internal::column_unique_indexer::map_index_to_value ( size_t idx ) const

virtual

Returns the feature "value" associated an index.

Note: Only used if is_categorical is true.

Parameters

Reimplemented from turi::v2::ml_data_internal::column_indexer.

◆ map_value_to_index()

size_t turi::v2::ml_data_internal::column_unique_indexer::map_value_to_index	(	size_t	thread_idx,
		const flexible_type &	feature
	)

virtual

Returns the index associated with the "feature" value.

Note: Only used if is_categorical is true.

If the value in the feature column was already seen, then the index already associated with that value is returned. If not, a new unique index is added and associated with this feature value.

This method is completely threadsafe and is meant to be called by multiple threads in contention.

Parameters

[in] feature The value in the feature column to map to the index.

Returns: An index (possibly new) associated with the given value.

Implements turi::v2::ml_data_internal::column_indexer.

◆ register_real_value()

void turi::v2::ml_data_internal::column_unique_indexer::register_real_value ( const flexible_type & feature )

When a new value is encountered in translating the data, it should be dealt with through map_value_to_index above if it is categorical, or through register_real_value below if it is numeric. This function handles things like checking the size of the numeric vectors (all must be the same) and setting the column size.

Note that the statistics collection functions below are not always called; hence the error checks in register_real_value can't go there.

◆ save_impl()

void turi::v2::ml_data_internal::column_unique_indexer::save_impl ( turi::oarchive & oarc ) const

virtual

Serialize the object (save).

Implements turi::v2::ml_data_internal::column_indexer.

◆ set_values()

void turi::v2::ml_data_internal::column_unique_indexer::set_values ( std::vector< flexible_type > && values )

virtual

Set data directly.

Implements turi::v2::ml_data_internal::column_indexer.

Member Data Documentation

◆ column_name

std::string turi::v2::ml_data_internal::column_indexer::column_name

inherited

The name of the column.

Definition at line 174 of file column_indexer.hpp.

◆ mode

ml_column_mode turi::v2::ml_data_internal::column_indexer::mode

inherited

The mode of the column;

Definition at line 178 of file column_indexer.hpp.

◆ options

std::map<std::string, flexible_type> turi::v2::ml_data_internal::column_indexer::options

inherited

A map of the options passed in to ml_data. May include options for the indexers.

Definition at line 187 of file column_indexer.hpp.

◆ original_column_type

flex_type_enum turi::v2::ml_data_internal::column_indexer::original_column_type

inherited

Original column type

Definition at line 182 of file column_indexer.hpp.

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

toolkits/ml_data_2/indexing/column_unique_indexer.hpp

Public Member Functions

Static Public Member Functions

Public Attributes

Detailed Description

Constructor & Destructor Documentation

◆ column_unique_indexer()

Member Function Documentation

◆ create_cleared_copy()

◆ deindexing_lambda()

◆ extract_key_types()

◆ factory_create()

◆ finalize()

◆ get_version()

◆ immutable_map_value_to_index()

◆ indexed_column_size()

◆ indexing_lambda()

◆ initialize()

◆ insert_values_into_index()

◆ load_version()

◆ map_index_to_value()

◆ map_value_to_index()

◆ register_real_value()

◆ save_impl()

◆ set_values()

Member Data Documentation

◆ column_name

◆ mode

◆ options

◆ original_column_type