Compact Theta sketch. More...

#include <theta_sketch.hpp>

Inheritance diagram for compact_theta_sketch_alloc< Allocator >:

Public Member Functions
template<typename Other >
	compact_theta_sketch_alloc (const Other &other, bool ordered)
	Copy constructor. More...

	compact_theta_sketch_alloc (const compact_theta_sketch_alloc &other)=default
	Copy constructor. More...

	compact_theta_sketch_alloc (compact_theta_sketch_alloc &&other) noexcept=default
	Move constructor. More...

compact_theta_sketch_alloc &	operator= (const compact_theta_sketch_alloc &other)=default
	Copy assignment. More...

compact_theta_sketch_alloc &	operator= (compact_theta_sketch_alloc &&other)=default
	Move assignment. More...

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

size_t	get_serialized_size_bytes (bool compressed=false) const
	Computes size in bytes required to serialize the current state of the sketch. More...

void	serialize (std::ostream &os) const
	This method serializes the sketch into a given stream in a binary form. More...

vector_bytes	serialize (unsigned header_size_bytes=0) const
	This method serializes the sketch as a vector of bytes. More...

void	serialize_compressed (std::ostream &os) const
	This method serializes the sketch into a given stream in a compressed binary form. More...

vector_bytes	serialize_compressed (unsigned header_size_bytes=0) const
	This method serializes the sketch as a vector of bytes. More...

virtual iterator	begin ()
	Iterator over hash values in this sketch. More...

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

virtual const_iterator	begin () const
	Const iterator over hash values in this sketch. More...

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

Public Member Functions inherited from base_theta_sketch_alloc< std::allocator< uint64_t > >
double	get_estimate () const

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

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

bool	is_estimation_mode () const

double	get_theta () const

virtual string< std::allocator< uint64_t > >	to_string (bool print_items=false) const
	Provides a human-readable summary of this sketch as a string. More...

Static Public Member Functions
static size_t	get_max_serialized_size_bytes (uint8_t lg_k)
	Computes maximum serialized size in bytes. More...

static compact_theta_sketch_alloc	deserialize (std::istream &is, uint64_t seed=DEFAULT_SEED, const Allocator &allocator=Allocator())
	This method deserializes a sketch from a given stream. More...

static compact_theta_sketch_alloc	deserialize (const void *bytes, size_t size, uint64_t seed=DEFAULT_SEED, const Allocator &allocator=Allocator())
	This method deserializes a sketch from a given array of bytes. More...

Detailed Description

template<typename Allocator = std::allocator<uint64_t>>
class datasketches::compact_theta_sketch_alloc< Allocator >

Compact Theta sketch.

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

Constructor & Destructor Documentation

◆ compact_theta_sketch_alloc() [1/3]

compact_theta_sketch_alloc	(	const Other &	other,
		bool	ordered
	)

Copy constructor.

Constructs a compact sketch from any other type of Theta sketch

Parameters

other	sketch to be constructed from
ordered	if true make the resulting sketch ordered

◆ compact_theta_sketch_alloc() [2/3]

compact_theta_sketch_alloc ( const compact_theta_sketch_alloc< Allocator > & other )

default

Copy constructor.

Parameters

other sketch to be copied

◆ compact_theta_sketch_alloc() [3/3]

compact_theta_sketch_alloc ( compact_theta_sketch_alloc< Allocator > && other )

defaultnoexcept

Move constructor.

Parameters

other sketch to be moved

Member Function Documentation

◆ operator=() [1/2]

compact_theta_sketch_alloc& operator= ( const compact_theta_sketch_alloc< Allocator > & other )

default

Copy assignment.

Parameters

other sketch to be copied

Returns: reference to this sketch

◆ operator=() [2/2]

compact_theta_sketch_alloc& operator= ( compact_theta_sketch_alloc< Allocator > && other )

default

Move assignment.

Parameters

other sketch to be moved

Returns: reference to this sketch

◆ get_allocator()

A get_allocator

virtual

Returns: allocator

Implements base_theta_sketch_alloc< std::allocator< uint64_t > >.

◆ is_empty()

bool is_empty

virtual

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

Implements base_theta_sketch_alloc< std::allocator< uint64_t > >.

◆ is_ordered()

bool is_ordered

virtual

Returns: true if retained entries are ordered

Implements base_theta_sketch_alloc< std::allocator< uint64_t > >.

◆ get_theta64()

uint64_t get_theta64

virtual

Returns: theta as a positive integer between 0 and LLONG_MAX

Implements base_theta_sketch_alloc< std::allocator< uint64_t > >.

◆ get_num_retained()

uint32_t get_num_retained

virtual

Returns: the number of retained entries in the sketch

Implements base_theta_sketch_alloc< std::allocator< uint64_t > >.

◆ get_seed_hash()

uint16_t get_seed_hash

virtual

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

Implements base_theta_sketch_alloc< std::allocator< uint64_t > >.

◆ get_max_serialized_size_bytes()

size_t get_max_serialized_size_bytes ( uint8_t lg_k )

static

Computes maximum serialized size in bytes.

Parameters

lg_k	nominal number of entries in the sketch

◆ get_serialized_size_bytes()

size_t get_serialized_size_bytes ( bool compressed = false ) const

Computes size in bytes required to serialize the current state of the sketch.

Computing compressed size is expensive. It takes iterating over all retained hashes, and the actual serialization will have to look at them again.

Parameters

compressed if true compressed size is returned (if applicable)

◆ serialize() [1/2]

void serialize ( std::ostream & os ) const

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

Parameters

os	output stream

◆ serialize() [2/2]

auto serialize ( unsigned header_size_bytes = 0 ) const

This method serializes the sketch as a vector of bytes.

An optional header can be reserved in front of the sketch. It is an uninitialized 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

◆ serialize_compressed() [1/2]

void serialize_compressed ( std::ostream & os ) const

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

Compression is applied to ordered sketches except empty and single item. For unordered, empty and single item sketches this method is equivalent to serialize()

Parameters

os	output stream

◆ serialize_compressed() [2/2]

auto serialize_compressed ( unsigned header_size_bytes = 0 ) const

This method serializes the sketch as a vector of bytes.

An optional header can be reserved in front of the sketch. It is an uninitialized space of a given size. This header is used in Datasketches PostgreSQL extension. Compression is applied to ordered sketches except empty and single item. For unordered, empty and single item sketches this method is equivalent to serialize()

Parameters

header_size_bytes space to reserve in front of the sketch

◆ begin() [1/2]

auto begin

virtual

Iterator over hash values in this sketch.

Returns: begin iterator

Implements theta_sketch_alloc< std::allocator< uint64_t > >.

◆ end() [1/2]

auto end

virtual

Iterator pointing past the valid range.

Not to be incremented or dereferenced.

Returns: end iterator

Implements theta_sketch_alloc< std::allocator< uint64_t > >.

◆ begin() [2/2]

auto begin

virtual

Const iterator over hash values in this sketch.

Returns: begin iterator

Implements theta_sketch_alloc< std::allocator< uint64_t > >.

◆ end() [2/2]

auto end

virtual

Const iterator pointing past the valid range.

Not to be incremented or dereferenced.

Returns: end iterator

Implements theta_sketch_alloc< std::allocator< uint64_t > >.

◆ deserialize() [1/2]

static compact_theta_sketch_alloc deserialize	(	std::istream &	is,
		uint64_t	seed = `DEFAULT_SEED`,
		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
allocator	instance of an Allocator

Returns: an instance of the sketch

◆ deserialize() [2/2]

static compact_theta_sketch_alloc deserialize	(	const void *	bytes,
		size_t	size,
		uint64_t	seed = `DEFAULT_SEED`,
		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
allocator	instance of an Allocator

Returns: an instance of the sketch

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

theta/include/theta_sketch.hpp
theta/include/theta_sketch_impl.hpp

Public Member Functions

Static Public Member Functions

Detailed Description

template<typename Allocator = std::allocator<uint64_t>> class datasketches::compact_theta_sketch_alloc< Allocator >

Constructor & Destructor Documentation

◆ compact_theta_sketch_alloc() [1/3]

◆ compact_theta_sketch_alloc() [2/3]

◆ compact_theta_sketch_alloc() [3/3]

Member Function Documentation

◆ operator=() [1/2]

◆ operator=() [2/2]

◆ get_allocator()

◆ is_empty()

◆ is_ordered()

◆ get_theta64()

◆ get_num_retained()

◆ get_seed_hash()

◆ get_max_serialized_size_bytes()

◆ get_serialized_size_bytes()

◆ serialize() [1/2]

◆ serialize() [2/2]

◆ serialize_compressed() [1/2]

◆ serialize_compressed() [2/2]

◆ begin() [1/2]

◆ end() [1/2]

◆ begin() [2/2]

◆ end() [2/2]

◆ deserialize() [1/2]

◆ deserialize() [2/2]

template<typename Allocator = std::allocator<uint64_t>>
class datasketches::compact_theta_sketch_alloc< Allocator >