From 1fb03c3807b2aba92dba06dd2e792afab5f71a5d Mon Sep 17 00:00:00 2001 From: David Peter Date: Mon, 5 Oct 2026 09:47:33 +0200 Subject: [PATCH] Replace statistical with local floating-point helpers --- Cargo.lock | 250 +------------------------------------- Cargo.toml | 1 - src/benchmark/executor.rs | 2 +- src/benchmark/mod.rs | 4 +- src/outlier_detection.rs | 2 +- src/util/mod.rs | 1 + src/util/statistics.rs | 127 +++++++++++++++++++ 7 files changed, 135 insertions(+), 252 deletions(-) create mode 100644 src/util/statistics.rs diff --git a/Cargo.lock b/Cargo.lock index b5cca2e..1c41fac 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -97,27 +97,12 @@ dependencies = [ "wait-timeout", ] -[[package]] -name = "autocfg" -version = "0.1.8" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "0dde43e75fd43e8a1bf86103336bc699aa8d17ad1be60c76c0bdfd4828e19b78" -dependencies = [ - "autocfg 1.5.1", -] - [[package]] name = "autocfg" version = "1.5.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "f2032f911046de80f0a198e0901378627c33f59ea0ac00e363d481118bd70a53" -[[package]] -name = "bitflags" -version = "1.3.2" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a" - [[package]] name = "bitflags" version = "2.13.2" @@ -231,15 +216,6 @@ version = "1.1.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "1c133bc6a41be0d194c306b5506d15e6feeea7b1d6604bd3f8310dfb2ca96486" -[[package]] -name = "cloudabi" -version = "0.0.3" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "ddfc5b9aa5d4507acaf872de71051dfd0e309860e88966e1051e462a077aac4f" -dependencies = [ - "bitflags 1.3.2", -] - [[package]] name = "colorchoice" version = "1.0.5" @@ -352,12 +328,6 @@ dependencies = [ "num-traits", ] -[[package]] -name = "fuchsia-cprng" -version = "0.1.1" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "a06f77d526c1a601b7c4cdd98f54b5eaabffc14d5f2f0296febdc7f357c6d3ba" - [[package]] name = "getrandom" version = "0.2.17" @@ -421,7 +391,6 @@ dependencies = [ "serde", "serde_json", "shell-words", - "statistical", "tempfile", "thiserror", "windows-sys 0.61.2", @@ -508,7 +477,7 @@ version = "0.31.3" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "cf20d2fde8ff38632c426f1165ed7436270b44f199fc55284c38276f9db47c3d" dependencies = [ - "bitflags 2.13.2", + "bitflags", "cfg-if", "cfg_aliases", "libc", @@ -520,79 +489,13 @@ version = "0.3.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "61807f77802ff30975e01f4f071c8ba10c022052f98b3294119f3e615d13e5be" -[[package]] -name = "num" -version = "0.2.1" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "b8536030f9fea7127f841b45bb6243b27255787fb4eb83958aa1ef9d2fdc0c36" -dependencies = [ - "num-bigint", - "num-complex", - "num-integer", - "num-iter", - "num-rational", - "num-traits", -] - -[[package]] -name = "num-bigint" -version = "0.2.6" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "090c7f9998ee0ff65aa5b723e4009f7b217707f1fb5ea551329cc4d6231fb304" -dependencies = [ - "autocfg 1.5.1", - "num-integer", - "num-traits", -] - -[[package]] -name = "num-complex" -version = "0.2.4" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "b6b19411a9719e753aff12e5187b74d60d3dc449ec3f4dc21e3989c3f554bc95" -dependencies = [ - "autocfg 1.5.1", - "num-traits", -] - -[[package]] -name = "num-integer" -version = "0.1.47" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "7ce2d95d4b3734dc35aa2f45e1aa22cd416814592a4f9d9205e11affd5b8e10b" -dependencies = [ - "num-traits", -] - -[[package]] -name = "num-iter" -version = "0.1.46" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "c92800bd69a1eac91786bcfe9da64a897eb72911b8dc3095decbd07429e8048b" -dependencies = [ - "num-integer", - "num-traits", -] - -[[package]] -name = "num-rational" -version = "0.2.4" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "5c000134b5dbf44adc5cb772486d335293351644b801551abe8f75c84cfa4aef" -dependencies = [ - "autocfg 1.5.1", - "num-bigint", - "num-integer", - "num-traits", -] - [[package]] name = "num-traits" version = "0.2.19" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "071dfc062690e90b734c0b2273ce72ad0ffa95f0c74596bc250dcfd960262841" dependencies = [ - "autocfg 1.5.1", + "autocfg", ] [[package]] @@ -697,25 +600,6 @@ version = "6.0.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "f8dcc9c7d52a811697d2151c701e0d08956f92b0e24136cf4cf27b57a6a0d9bf" -[[package]] -name = "rand" -version = "0.6.5" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "6d71dacdc3c88c1fde3885a3be3fbab9f35724e6ce99467f7d9c5026132184ca" -dependencies = [ - "autocfg 0.1.8", - "libc", - "rand_chacha 0.1.1", - "rand_core 0.4.3", - "rand_hc", - "rand_isaac", - "rand_jitter", - "rand_os", - "rand_pcg", - "rand_xorshift", - "winapi", -] - [[package]] name = "rand" version = "0.8.8" @@ -748,16 +632,6 @@ dependencies = [ "rand_core 0.10.1", ] -[[package]] -name = "rand_chacha" -version = "0.1.1" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "556d3a1ca6600bfcbab7c7c91ccb085ac7fbbcd70e008a98742e7847f4f7bcef" -dependencies = [ - "autocfg 0.1.8", - "rand_core 0.3.2", -] - [[package]] name = "rand_chacha" version = "0.3.1" @@ -778,21 +652,6 @@ dependencies = [ "rand_core 0.9.5", ] -[[package]] -name = "rand_core" -version = "0.3.2" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "96f815e01bbd9678b50d927f79aa1cf3ffdfdb1b9787317c1284dadb894ad0e8" -dependencies = [ - "rand_core 0.4.3", -] - -[[package]] -name = "rand_core" -version = "0.4.3" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "0e5937858e6fd18cd595d558f90bb5de3b72ae23f9e3763af0e805949b04ef60" - [[package]] name = "rand_core" version = "0.6.4" @@ -817,77 +676,6 @@ version = "0.10.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "63b8176103e19a2643978565ca18b50549f6101881c443590420e4dc998a3c69" -[[package]] -name = "rand_hc" -version = "0.1.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "7b40677c7be09ae76218dc623efbf7b18e34bced3f38883af07bb75630a21bc4" -dependencies = [ - "rand_core 0.3.2", -] - -[[package]] -name = "rand_isaac" -version = "0.1.1" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "ded997c9d5f13925be2a6fd7e66bf1872597f759fd9dd93513dd7e92e5a5ee08" -dependencies = [ - "rand_core 0.3.2", -] - -[[package]] -name = "rand_jitter" -version = "0.1.4" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "1166d5c91dc97b88d1decc3285bb0a99ed84b05cfd0bc2341bdf2d43fc41e39b" -dependencies = [ - "libc", - "rand_core 0.4.3", - "winapi", -] - -[[package]] -name = "rand_os" -version = "0.1.3" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "7b75f676a1e053fc562eafbb47838d67c84801e38fc1ba459e8f180deabd5071" -dependencies = [ - "cloudabi", - "fuchsia-cprng", - "libc", - "rand_core 0.4.3", - "rdrand", - "winapi", -] - -[[package]] -name = "rand_pcg" -version = "0.1.2" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "abf9b09b01790cfe0364f52bf32995ea3c39f4d2dd011eac241d2914146d0b44" -dependencies = [ - "autocfg 0.1.8", - "rand_core 0.4.3", -] - -[[package]] -name = "rand_xorshift" -version = "0.1.1" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "cbf7e9e623549b0e21f6e97cf8ecf247c1a8fd2e8a992ae265314300b2455d5c" -dependencies = [ - "rand_core 0.3.2", -] - -[[package]] -name = "rdrand" -version = "0.4.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "678054eb77286b51581ba43620cc911abf02758c91f93f479767aed0f90458b2" -dependencies = [ - "rand_core 0.3.2", -] - [[package]] name = "regex" version = "1.13.1" @@ -940,7 +728,7 @@ version = "1.1.5" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "891efababe418670775f199f0d233d84843c227a0949a883ce15b37c78d6629d" dependencies = [ - "bitflags 2.13.2", + "bitflags", "errno", "libc", "linux-raw-sys", @@ -1014,16 +802,6 @@ version = "2.7.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "bbbb5d9659141646ae647b42fe094daf6c6192d1620870b449d9557f748b2daa" -[[package]] -name = "statistical" -version = "1.0.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "49d57902bb128e5e38b5218d3681215ae3e322d99f65d5420e9849730d2ea372" -dependencies = [ - "num", - "rand 0.6.5", -] - [[package]] name = "strsim" version = "0.11.1" @@ -1225,28 +1003,6 @@ dependencies = [ "unicode-ident", ] -[[package]] -name = "winapi" -version = "0.3.9" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "5c839a674fcd7a98952e593242ea400abe93992746761e38641405d28b00f419" -dependencies = [ - "winapi-i686-pc-windows-gnu", - "winapi-x86_64-pc-windows-gnu", -] - -[[package]] -name = "winapi-i686-pc-windows-gnu" -version = "0.4.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6" - -[[package]] -name = "winapi-x86_64-pc-windows-gnu" -version = "0.4.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f" - [[package]] name = "windows-link" version = "0.2.1" diff --git a/Cargo.toml b/Cargo.toml index dec668a..39d9afc 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -20,7 +20,6 @@ windows_process_extensions_main_thread_handle = [] colored = "3.1" # Newer versions regress ETA estimates: https://github.com/console-rs/indicatif/issues/580 indicatif = "=0.17.4" -statistical = "1.0" csv = "1.4" serde = { version = "1.0", features = ["derive"] } serde_json = "1.0" diff --git a/src/benchmark/executor.rs b/src/benchmark/executor.rs index b2d7974..59a622f 100644 --- a/src/benchmark/executor.rs +++ b/src/benchmark/executor.rs @@ -9,12 +9,12 @@ use crate::options::{ use crate::output::progress_bar::get_progress_bar; use crate::timer::execute_and_measure; use crate::util::randomized_environment_offset; +use crate::util::statistics::mean; use crate::util::units::Second; use super::measurement::Measurement; use anyhow::{bail, Context, Result}; -use statistical::mean; pub enum BenchmarkIteration { NonBenchmarkRun, diff --git a/src/benchmark/mod.rs b/src/benchmark/mod.rs index 0bf0673..0ba58a6 100644 --- a/src/benchmark/mod.rs +++ b/src/benchmark/mod.rs @@ -20,13 +20,13 @@ use crate::output::warnings::{OutlierWarningOptions, Warnings}; use crate::parameter::ParameterNameAndValue; use crate::util::exit_code::extract_exit_code; use crate::util::min_max::{max, min}; +use crate::util::statistics::{mean, median, standard_deviation}; use crate::util::units::Second; use benchmark_result::BenchmarkResult; use measurement::Measurement; use anyhow::{anyhow, Result}; use colored::*; -use statistical::{mean, median, standard_deviation}; use self::executor::Executor; @@ -339,7 +339,7 @@ impl<'a> Benchmark<'a> { let t_num = times_real.len(); let t_mean = mean(×_real); let t_stddev = if times_real.len() > 1 { - Some(standard_deviation(×_real, Some(t_mean))) + Some(standard_deviation(×_real, t_mean)) } else { None }; diff --git a/src/outlier_detection.rs b/src/outlier_detection.rs index 270e522..c4c3a24 100644 --- a/src/outlier_detection.rs +++ b/src/outlier_detection.rs @@ -5,7 +5,7 @@ //! The ASQC Basic References in Quality Control: Statistical Techniques, Edward F. Mykytka, //! Ph.D., Editor. -use statistical::median; +use crate::util::statistics::median; /// Minimum modified Z-score for a datapoint to be an outlier. Here, 1.4826 is a factor that /// converts the MAD to an estimator for the standard deviation. The second factor is the number diff --git a/src/util/mod.rs b/src/util/mod.rs index de9e168..8996214 100644 --- a/src/util/mod.rs +++ b/src/util/mod.rs @@ -2,4 +2,5 @@ pub mod exit_code; pub mod min_max; pub mod number; pub mod randomized_environment_offset; +pub mod statistics; pub mod units; diff --git a/src/util/statistics.rs b/src/util/statistics.rs new file mode 100644 index 0000000..676edbc --- /dev/null +++ b/src/util/statistics.rs @@ -0,0 +1,127 @@ +//! Statistics for non-empty samples of finite measurements. + +/// Arithmetic mean, summing measurements in their original order. +pub fn mean(values: &[f64]) -> f64 { + values.iter().fold(0.0, |sum, value| sum + value) / values.len() as f64 +} + +/// Median without modifying the input sample. +pub fn median(values: &[f64]) -> f64 { + assert!( + !values.is_empty(), + "median requires at least one measurement" + ); + let mut sorted = values.to_vec(); + sorted.sort_unstable_by(|a, b| a.partial_cmp(b).expect("No NaN measurements")); + + let mid = sorted.len() / 2; + if sorted.len() % 2 == 1 { + sorted[mid] + } else { + (sorted[mid] + sorted[mid - 1]) / 2.0 + } +} + +/// Sample standard deviation, using an already computed mean. +pub fn standard_deviation(values: &[f64], mean: f64) -> f64 { + assert!( + values.len() > 1, + "standard deviation requires at least two measurements" + ); + let sum = values + .iter() + .map(|value| (value - mean) * (value - mean)) + .fold(0.0, |sum, deviation| sum + deviation); + assert!(sum >= 0.0, "invalid sum of squared deviations"); + + // Preserve the operation order of statistical 1.0: dividing by n - 1 + // before taking the square root also preserves exported floating-point values. + (sum / (values.len() as f64 - 1.0)).sqrt() +} + +#[cfg(test)] +mod tests { + use super::*; + + #[test] + fn mean_preserves_summation_order() { + assert_eq!(mean(&[1.0]), 1.0); + assert_eq!(mean(&[1.0, 2.0, 6.0]), 3.0); + assert_eq!(mean(&[1e16, 1.0, -1e16]), 0.0); + } + + #[test] + fn median_handles_odd_even_and_repeated_values() { + assert_eq!(median(&[7.0]), 7.0); + assert_eq!(median(&[6.0, 1.0, 2.0]), 2.0); + assert_eq!(median(&[6.0, 1.0, 3.0, 2.0]), 2.5); + assert_eq!(median(&[0.0, 0.0, 0.0, 1.0]), 0.0); + assert_eq!(median(&[-3.0, -1.0, -2.0]), -2.0); + } + + #[test] + fn median_preserves_input_order() { + let values = [3.0, 1.0, 2.0]; + assert_eq!(median(&values), 2.0); + assert_eq!(values, [3.0, 1.0, 2.0]); + } + + #[test] + #[should_panic(expected = "median requires at least one measurement")] + fn median_rejects_empty_samples() { + median(&[]); + } + + #[test] + fn standard_deviation_uses_sample_variance() { + assert_eq!(standard_deviation(&[1.0, 2.0, 3.0], 2.0), 1.0); + assert_eq!(standard_deviation(&[0.0, 0.0], 0.0), 0.0); + assert_eq!(standard_deviation(&[7.0, 7.0, 7.0], 7.0), 0.0); + } + + #[test] + fn matches_statistical_1_0_floating_point_results() { + // Recorded from statistical 1.0.0, including small durations and + // small differences between large values. Compare bits to catch + // changes that would affect the full precision JSON/CSV exports. + let cases: &[(&[f64], u64, u64, u64)] = &[ + ( + &[0.09, 0.10, 0.14], + 0x3fbc28f5c28f5c29, + 0x3fb999999999999a, + 0x3f9b17ada62cc3bd, + ), + ( + &[0.1, 0.2, 0.3, 0.4], + 0x3fd0000000000000, + 0x3fd0000000000000, + 0x3fc08654a2d4f6da, + ), + ( + &[1e-9, 2e-9, 3e-9, 9e-9], + 0x3e301b2b29a4692c, + 0x3e25798ee2308c3a, + 0x3e2edf3cdee63e61, + ), + ( + &[1e12 + 0.001, 1e12 + 0.002, 1e12 + 0.003], + 0x426d1a94a2000010, + 0x426d1a94a2000010, + 0x3f510785dd689a29, + ), + ]; + + for &(values, mean_bits, median_bits, stddev_bits) in cases { + let mean = mean(values); + assert_eq!(mean.to_bits(), mean_bits); + assert_eq!(median(values).to_bits(), median_bits); + assert_eq!(standard_deviation(values, mean).to_bits(), stddev_bits); + } + } + + #[test] + #[should_panic(expected = "standard deviation requires at least two measurements")] + fn standard_deviation_rejects_single_measurements() { + standard_deviation(&[1.0], 1.0); + } +}