std::ranges::sample
From cppreference.com
C++
Feature test macros (C++20)
Concepts library (C++20)
Metaprogramming library (C++11)
Ranges library (C++20)
Filesystem library (C++17)
Concurrency support library (C++11)
Execution control library (C++26)
Algorithm library
Constrained algorithms, e.g. ranges::copy, ranges::sort, ...
(C++17)
(C++17) (C++17)(C++17)(C++20)
(C++17)
(C++11)
(until C++17)(C++11)
(C++20)(C++20)
(C++17)
(C++17)
(C++17)
(C++17)
Constrained algorithms
All names in this menu belong to namespace
std::ranges
(C++23)
(C++23)
(C++23)
(C++23)
(C++23)
(C++23)
(C++23)
Defined in header
<algorithm>
Call signature
template< std::input_iterator I, std::sentinel_for <I> S,
(1)
(since C++20)
std::weakly_incrementable O, class Gen >
requires (std::forward_iterator <I> || std::random_access_iterator <O>) &&
std::indirectly_copyable <I, O> &&
std::uniform_random_bit_generator <std::remove_reference_t <Gen>>
template< ranges::input_range R, std::weakly_incrementable O, class Gen >
(2)
(since C++20)
requires (ranges::forward_range <R> || std::random_access_iterator <O>) &&
std::indirectly_copyable <ranges::iterator_t <R>, O> &&
std::uniform_random_bit_generator <std::remove_reference_t <Gen>>
1) Selects M = min(n, last - first) elements from the sequence
[first, last) (without replacement) such that each possible sample has equal probability of appearance, and writes those selected elements into the range beginning at out. The algorithm is stable (preserves the relative order of the selected elements) only if
I models std::forward_iterator . The behavior is undefined if out is in
[first, last).2) Same as (1), but uses r as the source range, as if using ranges::begin (r) as first, and ranges::end (r) as last.
The function-like entities described on this page are algorithm function objects (informally known as niebloids), that is:
- Explicit template argument lists cannot be specified when calling any of them.
- None of them are visible to argument-dependent lookup.
- When any of them are found by normal unqualified lookup as the name to the left of the function-call operator, argument-dependent lookup is inhibited.
Contents
[edit] Parameters
first, last
-
the iterator-sentinel pair defining the range of elements from which to make the sampling (the population)
r
-
the range from which to make the sampling (the population)
out
-
the output iterator where the samples are written
n
-
number of samples to take
gen
-
the random number generator used as the source of randomness
[edit] Return value
An iterator equal to out + M, that is the end of the resulting sample range.
[edit] Complexity
Linear: O(last - first).
[edit] Notes
This function may implement selection sampling or reservoir sampling.
[edit] Possible implementation
struct sample_fn { template<std::input_iterator I, std::sentinel_for <I> S, std::weakly_incrementable O, class Gen> requires (std::forward_iterator <I> or std::random_access_iterator <O>) && std::indirectly_copyable <I, O> && std::uniform_random_bit_generator <std::remove_reference_t <Gen>> O operator()(I first, S last, O out, std::iter_difference_t <I> n, Gen&& gen) const { using diff_t = std::iter_difference_t <I>; using distrib_t = std::uniform_int_distribution <diff_t>; using param_t = typename distrib_t::param_type; distrib_t D{}; if constexpr (std::forward_iterator <I>) { // this branch preserves "stability" of the sample elements auto rest{ranges::distance (first, last)}; for (n = ranges::min (n, rest); n != 0; ++first) if (D(gen, param_t(0, --rest)) < n) { *out++ = *first; --n; } return out; } else { // O is a random_access_iterator diff_t sample_size{}; // copy [first, first + M) elements to "random access" output for (; first != last && sample_size != n; ++first) out[sample_size++] = *first; // overwrite some of the copied elements with randomly selected ones for (auto pop_size{sample_size}; first != last; ++first, ++pop_size) { const auto i{D(gen, param_t{0, pop_size})}; if (i < n) out[i] = *first; } return out + sample_size; } } template<ranges::input_range R, std::weakly_incrementable O, class Gen> requires (ranges::forward_range <R> or std::random_access_iterator <O>) && std::indirectly_copyable <ranges::iterator_t <R>, O> && std::uniform_random_bit_generator <std::remove_reference_t <Gen>> O operator()(R&& r, O out, ranges::range_difference_t <R> n, Gen&& gen) const { return (*this)(ranges::begin (r), ranges::end (r), std::move(out), n, std::forward <Gen>(gen)); } }; inline constexpr sample_fn sample {};
[edit] Example
Run this code
#include <algorithm> #include <iomanip> #include <iostream> #include <iterator> #include <random> #include <vector> void print(auto const& rem, auto const& v) { std::cout << rem << " = [" << std::size (v) << "] { "; for (auto const& e : v) std::cout << e << ' '; std::cout << "}\n"; } int main() { const auto in = {1, 2, 3, 4, 5, 6}; print("in", in); std::vector <int> out; const int max = in.size() + 2; auto gen = std::mt19937 {std::random_device {}()}; for (int n{}; n != max; ++n) { out.clear(); std::ranges::sample(in, std::back_inserter (out), n, gen); std::cout << "n = " << n; print(", out", out); } }
Possible output:
in = [6] { 1 2 3 4 5 6 }
n = 0, out = [0] { }
n = 1, out = [1] { 5 }
n = 2, out = [2] { 4 5 }
n = 3, out = [3] { 2 3 5 }
n = 4, out = [4] { 2 4 5 6 }
n = 5, out = [5] { 1 2 3 5 6 }
n = 6, out = [6] { 1 2 3 4 5 6 }
n = 7, out = [6] { 1 2 3 4 5 6 }