fix(datasets): decouple datasets feature from std_rand

CHANGELOG.md

@@ -7,6 +7,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ## [Unreleased]
 
 - In the `...Regressor`s the features are always shuffled even when `mtry` equals the number of attributes. This changes the constructed trees. 
+- The `datasets` feature no longer enables `std_rand` (#416). The toy datasets now compile without `rand/std` and the OS RNG. The generators `make_blobs`, `make_circles` and `make_moons` now use the crate RNG. With `std_rand` the RNG takes its seed from OS entropy, as before. Without `std_rand` the RNG uses a fixed seed, thus the output is the same for each call. To keep the previous behaviour, enable `std_rand` together with `datasets`.
 
 ## [0.6.16]
 ### Fixed

Cargo.toml

@@ -47,8 +47,9 @@ serde = ["dep:serde", "dep:typetag"]
 ndarray-bindings = ["dep:ndarray"]
 
 # Sample datasets (iris, boston, digits, ...) and dataset generators.
-# Enables std_rand and serde because datasets ship serialized bundles.
-datasets = ["std_rand", "serde"]
+# Enables serde because datasets ship serialized bundles. Does not enable
+# std_rand: the generators use the crate RNG (SmallRng without std_rand).
+datasets = ["serde"]
 
 # Use the standard library RNG (StdRng / thread_rng) instead of SmallRng.
 # Required for non-deterministic seeding without an explicit seed.

src/dataset/generator.rs

@@ -1,9 +1,14 @@
 //! # Dataset Generators
 //!
+//! The generators get their RNG from `get_rng_impl(None)`. With the `std_rand`
+//! feature the RNG takes its seed from OS entropy. Without `std_rand` the RNG
+//! uses a fixed seed (or `getrandom` with the `js` feature), thus the
+//! `datasets` feature does not need `rand/std`.
 use rand::distr::Distribution;
 use rand::distr::Uniform;
 
 use crate::dataset::Dataset;
+use crate::rand_custom::get_rng_impl;
 
 /// Sample from N(mean, std) via Box-Muller transform using only rand 0.10
 #[inline]
@@ -24,7 +29,7 @@ pub fn make_blobs(
 ) -> Dataset<f32, f32> {
     let center_box = Uniform::new(-10.0f32, 10.0f32).expect("Invalid uniform range");
     let cluster_std = 1.0f32;
-    let mut rng = rand::rng();
+    let mut rng = get_rng_impl(None);
 
     // Pre-compute cluster centers (one mean per feature per cluster)
     let centers: Vec<Vec<f32>> = (0..num_centers)
@@ -70,7 +75,7 @@ pub fn make_circles(num_samples: usize, factor: f32, noise: f32) -> Dataset<f32,
     let linspace_out = linspace(0.0, 2.0 * std::f32::consts::PI, num_samples_out);
     let linspace_in = linspace(0.0, 2.0 * std::f32::consts::PI, num_samples_in);
 
-    let mut rng = rand::rng();
+    let mut rng = get_rng_impl(None);
 
     let mut x: Vec<f32> = Vec::with_capacity(num_samples * 2);
     let mut y: Vec<f32> = Vec::with_capacity(num_samples);
@@ -107,7 +112,7 @@ pub fn make_moons(num_samples: usize, noise: f32) -> Dataset<f32, u32> {
     let linspace_out = linspace(0.0, std::f32::consts::PI, num_samples_out);
     let linspace_in = linspace(0.0, std::f32::consts::PI, num_samples_in);
 
-    let mut rng = rand::rng();
+    let mut rng = get_rng_impl(None);
 
     let mut x: Vec<f32> = Vec::with_capacity(num_samples * 2);
     let mut y: Vec<f32> = Vec::with_capacity(num_samples);
@@ -194,4 +199,20 @@ mod tests {
         assert_eq!(dataset.num_features, 2);
         assert_eq!(dataset.num_samples, 10);
     }
+
+    #[cfg(not(any(feature = "std_rand", feature = "js")))]
+    #[cfg_attr(
+        all(target_arch = "wasm32", not(target_os = "wasi")),
+        wasm_bindgen_test::wasm_bindgen_test
+    )]
+    #[test]
+    fn test_generators_without_std_rand_are_reproducible() {
+        // without std_rand the generators use a fixed-seed SmallRng
+        assert_eq!(make_blobs(10, 2, 3).data, make_blobs(10, 2, 3).data);
+        assert_eq!(
+            make_circles(10, 0.5, 0.05).data,
+            make_circles(10, 0.5, 0.05).data
+        );
+        assert_eq!(make_moons(10, 0.05).data, make_moons(10, 0.05).data);
+    }
 }

src/readers/io_testing.rs

@@ -1,13 +1,16 @@
 //! This module contains functionality to test IO. It has both functions that write
 //! to the file-system for end-to-end tests, but also abstractions to avoid this by
 //! reading from strings instead.
-use rand::distr::{Alphanumeric, SampleString};
 use std::fs;
 use std::io::Bytes;
 use std::io::Read;
 use std::io::{Chain, IoSliceMut, Take, Write};
+use std::sync::atomic::{AtomicUsize, Ordering};
 
-/// Writing out a temporary csv file at a random location and cleaning
+/// Counter that makes each temporary file name unique in the process.
+static TEMPORARY_FILE_COUNTER: AtomicUsize = AtomicUsize::new(0);
+
+/// Writing out a temporary csv file at a unique location and cleaning
 /// it up on `Drop`.
 #[derive(Clone, Debug, Default, Eq, PartialEq)]
 pub struct TemporaryTextFile {
@@ -16,7 +19,13 @@ pub struct TemporaryTextFile {
 impl TemporaryTextFile {
     pub fn new(contents: &str) -> std::io::Result<Self> {
         let test_text_file = TemporaryTextFile {
-            random_path: Alphanumeric.sample_string(&mut rand::rng(), 16),
+            // Process id and counter give a unique name without an OS RNG,
+            // thus the tests do not need the `std_rand` feature.
+            random_path: format!(
+                "smartcore_tmp_{}_{}",
+                std::process::id(),
+                TEMPORARY_FILE_COUNTER.fetch_add(1, Ordering::Relaxed)
+            ),
         };
         string_to_file(contents, &test_text_file.random_path)?;
         Ok(test_text_file)