Compact Tuple sketch. More...

#include <tuple_sketch.hpp>

Inheritance diagram for compact_tuple_sketch< Summary, Allocator >:

Public Member Functions
	compact_tuple_sketch (const Base &other, bool ordered)
	Copy constructor.

	compact_tuple_sketch (const compact_tuple_sketch &other)=default
	Copy constructor.

	compact_tuple_sketch (compact_tuple_sketch &&) noexcept
	Move constructor.

compact_tuple_sketch &	operator= (const compact_tuple_sketch &other)=default
	Copy assignment.

compact_tuple_sketch &	operator= (compact_tuple_sketch &&other)=default
	Move assignment.

	compact_tuple_sketch (const theta_sketch_alloc< AllocU64 > &other, const Summary &summary, bool ordered=true)
	Constructor from Theta sketch.

virtual Allocator	get_allocator () const

virtual bool	is_empty () const

virtual bool	is_ordered () const

virtual uint64_t	get_theta64 () const

virtual uint32_t	get_num_retained () const

virtual uint16_t	get_seed_hash () const

template<typename Predicate >
compact_tuple_sketch	filter (const Predicate &predicate) const
	Produces a Compact Tuple sketch from this sketch by applying a given predicate to each entry.

template<typename SerDe = serde<Summary>>
void	serialize (std::ostream &os, const SerDe &sd=SerDe()) const
	This method serializes the sketch into a given stream in a binary form.

template<typename SerDe = serde<Summary>>
vector_bytes	serialize (unsigned header_size_bytes=0, const SerDe &sd=SerDe()) const
	This method serializes the sketch as a vector of bytes.

virtual iterator	begin ()
	Iterator over entries in this sketch.

virtual iterator	end ()
	Iterator pointing past the valid range.

virtual const_iterator	begin () const
	Const iterator over entries in this sketch.

virtual const_iterator	end () const
	Const iterator pointing past the valid range.

Public Member Functions inherited from tuple_sketch< Summary, Allocator >
double	get_estimate () const

double	get_lower_bound (uint8_t num_std_devs, uint32_t num_subset_entries) const
	Returns the approximate lower error bound given a number of standard deviations over an arbitrary number of items stored in the sketch.

double	get_lower_bound (uint8_t num_std_devs) const
	Returns the approximate lower error bound given a number of standard deviations.

double	get_upper_bound (uint8_t num_std_devs, uint32_t num_subset_entries) const
	Returns the approximate upper error bound given a number of standard deviations over an arbitrary number of items stored in the sketch.

double	get_upper_bound (uint8_t num_std_devs) const
	Returns the approximate upper error bound given a number of standard deviations.

bool	is_estimation_mode () const

double	get_theta () const

string< Allocator >	to_string (bool print_items=false) const
	Provides a human-readable summary of this sketch as a string.

Static Public Member Functions
template<typename Sketch , typename Predicate >
static compact_tuple_sketch	filter (const Sketch &sketch, const Predicate &predicate)
	Produces a Compact Tuple sketch from a given sketch (Update or Compact) by applying a given predicate to each entry.

template<typename SerDe = serde<Summary>>
static compact_tuple_sketch	deserialize (std::istream &is, uint64_t seed=DEFAULT_SEED, const SerDe &sd=SerDe(), const Allocator &allocator=Allocator())
	This method deserializes a sketch from a given stream.

template<typename SerDe = serde<Summary>>
static compact_tuple_sketch	deserialize (const void *bytes, size_t size, uint64_t seed=DEFAULT_SEED, const SerDe &sd=SerDe(), const Allocator &allocator=Allocator())
	This method deserializes a sketch from a given array of bytes.

Protected Member Functions
template<typename SerDe , typename SS = Summary, typename std::enable_if< std::is_arithmetic< SS >::value, int >::type = 0>
size_t	get_serialized_size_summaries_bytes (const SerDe &sd) const
	Computes size needed to serialize summaries in the sketch.

template<typename SerDe , typename SS = Summary, typename std::enable_if<!std::is_arithmetic< SS >::value, int >::type = 0>
size_t	get_serialized_size_summaries_bytes (const SerDe &sd) const
	Computes size needed to serialize summaries in the sketch.

Detailed Description

template<typename Summary, typename Allocator = std::allocator<Summary>>
class datasketches::compact_tuple_sketch< Summary, Allocator >

Compact Tuple sketch.

This is an immutable form of the Tuple sketch, the form that can be serialized and deserialized.

Constructor & Destructor Documentation

◆ compact_tuple_sketch() [1/4]

template<typename S , typename A >

compact_tuple_sketch	(	const Base &	other,
		bool	ordered
	)

Copy constructor.

Constructs a compact sketch from another sketch (either update or compact)

Parameters

other	sketch to be copied
ordered	if true make the resulting sketch ordered

◆ compact_tuple_sketch() [2/4]

template<typename Summary , typename Allocator = std::allocator<Summary>>

compact_tuple_sketch ( const compact_tuple_sketch< Summary, Allocator > & other )

default

Copy constructor.

Parameters

other sketch to be copied

◆ compact_tuple_sketch() [3/4]

template<typename S , typename A >

compact_tuple_sketch ( compact_tuple_sketch< Summary, Allocator > && other )

noexcept

Move constructor.

Parameters

other sketch to be moved

◆ compact_tuple_sketch() [4/4]

template<typename Summary , typename Allocator = std::allocator<Summary>>

compact_tuple_sketch	(	const theta_sketch_alloc< AllocU64 > &	other,
		const Summary &	summary,
		bool	ordered = `true`
	)

Constructor from Theta sketch.

Parameters

other	Theta sketch to be constructed from
summary	Summary instance to be associated with each entry
ordered	if true make the resulting sketch ordered

Member Function Documentation

◆ operator=() [1/2]

template<typename Summary , typename Allocator = std::allocator<Summary>>

compact_tuple_sketch & operator= ( const compact_tuple_sketch< Summary, Allocator > & other )

default

Copy assignment.

Parameters

other sketch to be copied

Returns: reference to this sketch

◆ operator=() [2/2]

template<typename Summary , typename Allocator = std::allocator<Summary>>

compact_tuple_sketch & operator= ( compact_tuple_sketch< Summary, Allocator > && other )

default

Move assignment.

Parameters

other sketch to be moved

Returns: reference to this sketch

◆ get_allocator()

template<typename S , typename A >

A get_allocator ( ) const

virtual

Returns: allocator

Implements tuple_sketch< Summary, Allocator >.

◆ is_empty()

template<typename S , typename A >

bool is_empty ( ) const

virtual

Returns: true if this sketch represents an empty set (not the same as no retained entries!)

Implements tuple_sketch< Summary, Allocator >.

◆ is_ordered()

template<typename S , typename A >

bool is_ordered ( ) const

virtual

Returns: true if retained entries are ordered

Implements tuple_sketch< Summary, Allocator >.

◆ get_theta64()

template<typename S , typename A >

uint64_t get_theta64 ( ) const

virtual

Returns: theta as a positive integer between 0 and LLONG_MAX

Implements tuple_sketch< Summary, Allocator >.

◆ get_num_retained()

template<typename S , typename A >

uint32_t get_num_retained ( ) const

virtual

Returns: the number of retained entries in the sketch

Implements tuple_sketch< Summary, Allocator >.

◆ get_seed_hash()

template<typename S , typename A >

uint16_t get_seed_hash ( ) const

virtual

Returns: hash of the seed that was used to hash the input

Implements tuple_sketch< Summary, Allocator >.

◆ filter() [1/2]

template<typename Summary , typename Allocator = std::allocator<Summary>>

template<typename Predicate >

compact_tuple_sketch filter ( const Predicate & predicate ) const

Produces a Compact Tuple sketch from this sketch by applying a given predicate to each entry.

Parameters

predicate should return true for the entries to keep

Returns: compact sketch with the entries retained according to the predicate

◆ filter() [2/2]

template<typename Summary , typename Allocator = std::allocator<Summary>>

template<typename Sketch , typename Predicate >

static compact_tuple_sketch filter	(	const Sketch &	sketch,
		const Predicate &	predicate
	)

static

Produces a Compact Tuple sketch from a given sketch (Update or Compact) by applying a given predicate to each entry.

Parameters

sketch	input sketch
predicate	should return true for the entries to keep

Returns: compact sketch with the entries retained according to the predicate

◆ serialize() [1/2]

template<typename S , typename A >

template<typename SerDe >

void serialize	(	std::ostream &	os,
		const SerDe &	sd = `SerDe()`
	)		const

This method serializes the sketch into a given stream in a binary form.

Parameters

os	output stream
sd	instance of a SerDe

◆ serialize() [2/2]

template<typename Summary , typename Allocator = std::allocator<Summary>>

template<typename SerDe = serde<Summary>>

vector_bytes serialize	(	unsigned	header_size_bytes = `0`,
		const SerDe &	sd = `SerDe()`
	)		const

This method serializes the sketch as a vector of bytes.

An optional header can be reserved in front of the sketch. It is a blank space of a given size. This header is used in Datasketches PostgreSQL extension.

Parameters

header_size_bytes	space to reserve in front of the sketch
sd	instance of a SerDe

Returns: serialized sketch as a vector of bytes

◆ begin() [1/2]

template<typename S , typename A >

auto begin ( )

virtual

Iterator over entries in this sketch.

Returns: begin iterator

Implements tuple_sketch< Summary, Allocator >.

◆ end() [1/2]

template<typename S , typename A >

auto end ( )

virtual

Iterator pointing past the valid range.

Not to be incremented or dereferenced.

Returns: end iterator

Implements tuple_sketch< Summary, Allocator >.

◆ begin() [2/2]

template<typename S , typename A >

auto begin ( ) const

virtual

Const iterator over entries in this sketch.

Returns: begin const iterator

Implements tuple_sketch< Summary, Allocator >.

◆ end() [2/2]

template<typename S , typename A >

auto end ( ) const

virtual

Const iterator pointing past the valid range.

Not to be incremented or dereferenced.

Returns: end const iterator

Implements tuple_sketch< Summary, Allocator >.

◆ deserialize() [1/2]

template<typename Summary , typename Allocator = std::allocator<Summary>>

template<typename SerDe = serde<Summary>>

static compact_tuple_sketch deserialize	(	std::istream &	is,
		uint64_t	seed = `DEFAULT_SEED`,
		const SerDe &	sd = `SerDe()`,
		const Allocator &	allocator = `Allocator()`
	)

static

This method deserializes a sketch from a given stream.

Parameters

is	input stream
seed	the seed for the hash function that was used to create the sketch
sd	instance of a SerDe
allocator	instance of an Allocator

Returns: an instance of a sketch

◆ deserialize() [2/2]

template<typename Summary , typename Allocator = std::allocator<Summary>>

template<typename SerDe = serde<Summary>>

static compact_tuple_sketch deserialize	(	const void *	bytes,
		size_t	size,
		uint64_t	seed = `DEFAULT_SEED`,
		const SerDe &	sd = `SerDe()`,
		const Allocator &	allocator = `Allocator()`
	)

static

This method deserializes a sketch from a given array of bytes.

Parameters

bytes	pointer to the array of bytes
size	the size of the array
seed	the seed for the hash function that was used to create the sketch
sd	instance of a SerDe
allocator	instance of an Allocator

Returns: an instance of the sketch

◆ get_serialized_size_summaries_bytes() [1/2]

template<typename Summary , typename Allocator = std::allocator<Summary>>

template<typename SerDe , typename SS = Summary, typename std::enable_if< std::is_arithmetic< SS >::value, int >::type = 0>

size_t get_serialized_size_summaries_bytes ( const SerDe & sd ) const

protected

Computes size needed to serialize summaries in the sketch.

This version is for fixed-size arithmetic types (integral and floating point).

Returns: size in bytes needed to serialize summaries in this sketch

◆ get_serialized_size_summaries_bytes() [2/2]

template<typename Summary , typename Allocator = std::allocator<Summary>>

template<typename SerDe , typename SS = Summary, typename std::enable_if<!std::is_arithmetic< SS >::value, int >::type = 0>

size_t get_serialized_size_summaries_bytes ( const SerDe & sd ) const

protected

Computes size needed to serialize summaries in the sketch.

This version is for all other types and can be expensive since every item needs to be looked at.

Returns: size in bytes needed to serialize summaries in this sketch

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

tuple/include/tuple_sketch.hpp
tuple/include/tuple_sketch_impl.hpp

Public Member Functions

Static Public Member Functions

Protected Member Functions

Detailed Description

Constructor & Destructor Documentation

◆ compact_tuple_sketch() [1/4]

◆ compact_tuple_sketch() [2/4]

◆ compact_tuple_sketch() [3/4]

◆ compact_tuple_sketch() [4/4]

Member Function Documentation

◆ operator=() [1/2]

◆ operator=() [2/2]

◆ get_allocator()

◆ is_empty()

◆ is_ordered()

◆ get_theta64()

◆ get_num_retained()

◆ get_seed_hash()

◆ filter() [1/2]

◆ filter() [2/2]

◆ serialize() [1/2]

◆ serialize() [2/2]

◆ begin() [1/2]

◆ end() [1/2]

◆ begin() [2/2]

◆ end() [2/2]

◆ deserialize() [1/2]

◆ deserialize() [2/2]

◆ get_serialized_size_summaries_bytes() [1/2]

◆ get_serialized_size_summaries_bytes() [2/2]