refactor!: close the remaining API gaps from #21
Three unrelated small defects, all requiring signature changes: - `Game::one_v_one` hardcoded `GameOptions::default()`, so a 1v1 could never set `p_draw` or convergence options — and a drawn 1v1 was therefore unreachable through it, since the default `p_draw` is zero. It now takes `&GameOptions` like every other constructor. - `Observer::on_batch_processed` was declared on the trait and never called from anywhere: implementors wired up a callback that could not fire. It is now called after each slice sweep, and renamed `on_slice_processed` to match the vocabulary the codebase adopted in T2 — the unit of work is a `TimeSlice`, not a batch. A slice is swept once travelling backward and once forward, so a multi-slice history fires it twice per slice per iteration; the doc comment says so. - `pub mod factors` sat beside `pub(crate) mod factor`, two module paths differing by one character with only one of them importable. The public facade is now `graph`. Tests cover each as a behaviour rather than a compile check: a drawn 1v1 succeeds only when p_draw is supplied, and the observer tests fail if any callback stops firing. BREAKING CHANGE: `Game::one_v_one` takes a fourth `&GameOptions` argument; `Observer::on_batch_processed` is renamed `on_slice_processed`; the `factors` module is renamed `graph`. Closes #21 Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011hcFjNDmHXZF8URGLku5zZ
This commit is contained in:
@@ -19,7 +19,8 @@ fn ts_rating(mu: f64, sigma: f64, beta: f64, gamma: f64) -> R {
|
||||
fn game_1v1_golden_matches_historical() {
|
||||
let a = ts_rating(25.0, 25.0 / 3.0, 25.0 / 6.0, 25.0 / 300.0);
|
||||
let b = ts_rating(25.0, 25.0 / 3.0, 25.0 / 6.0, 25.0 / 300.0);
|
||||
let (a_post, b_post) = Game::<i64, _>::one_v_one(&a, &b, Outcome::winner(0, 2)).unwrap();
|
||||
let (a_post, b_post) =
|
||||
Game::<i64, _>::one_v_one(&a, &b, Outcome::winner(0, 2), &GameOptions::default()).unwrap();
|
||||
// Historical golden from pre-T2 test_1vs1 (team 0 wins):
|
||||
assert_ulps_eq!(
|
||||
a_post,
|
||||
|
||||
+44
-1
@@ -32,7 +32,8 @@ fn game_ranked_1v1_golden() {
|
||||
fn game_one_v_one_shortcut() {
|
||||
let a = default_rating();
|
||||
let b = default_rating();
|
||||
let (a_post, b_post) = Game::<i64, _>::one_v_one(&a, &b, Outcome::winner(0, 2)).unwrap();
|
||||
let (a_post, b_post) =
|
||||
Game::<i64, _>::one_v_one(&a, &b, Outcome::winner(0, 2), &GameOptions::default()).unwrap();
|
||||
assert!(a_post.mu() > 25.0);
|
||||
assert!(b_post.mu() < 25.0);
|
||||
}
|
||||
@@ -95,3 +96,45 @@ fn game_log_evidence_is_finite() {
|
||||
assert!(g.log_evidence().is_finite());
|
||||
assert!(g.log_evidence() < 0.0);
|
||||
}
|
||||
|
||||
/// `one_v_one` used to hardcode `GameOptions::default()`, so a 1v1 could
|
||||
/// never set `p_draw` and a drawn 1v1 was unreachable through it.
|
||||
#[test]
|
||||
fn one_v_one_honours_the_draw_probability_it_is_given() {
|
||||
let a = default_rating();
|
||||
let b = default_rating();
|
||||
|
||||
// Default options still reject a draw, because the default p_draw is zero.
|
||||
let err = Game::<i64, _>::one_v_one(&a, &b, Outcome::draw(2), &GameOptions::default())
|
||||
.expect_err("a draw needs a positive p_draw");
|
||||
assert!(matches!(
|
||||
err,
|
||||
InferenceError::TieWithoutDrawProbability { .. }
|
||||
));
|
||||
|
||||
// With a draw probability supplied it succeeds — which was impossible
|
||||
// before the signature took options.
|
||||
let options = GameOptions {
|
||||
p_draw: 0.25,
|
||||
..GameOptions::default()
|
||||
};
|
||||
let (a_post, b_post) = Game::<i64, _>::one_v_one(&a, &b, Outcome::draw(2), &options)
|
||||
.expect("a draw is representable once p_draw is positive");
|
||||
|
||||
// A symmetric draw leaves the means alone and sharpens both sides.
|
||||
assert!((a_post.mu() - b_post.mu()).abs() < 1e-9);
|
||||
assert!(a_post.sigma() < 25.0 / 3.0);
|
||||
}
|
||||
|
||||
/// Convergence options reach the 1v1 path too, not just `p_draw`.
|
||||
#[test]
|
||||
fn one_v_one_honours_convergence_options() {
|
||||
let a = default_rating();
|
||||
let b = default_rating();
|
||||
let options = GameOptions {
|
||||
convergence: ConvergenceOptions::default(),
|
||||
..GameOptions::default()
|
||||
};
|
||||
let (a_post, _) = Game::<i64, _>::one_v_one(&a, &b, Outcome::winner(0, 2), &options).unwrap();
|
||||
assert!(a_post.mu() > 25.0);
|
||||
}
|
||||
|
||||
@@ -0,0 +1,105 @@
|
||||
//! `Observer` callbacks must actually fire.
|
||||
//!
|
||||
//! `on_slice_processed` (formerly `on_batch_processed`) was declared on the
|
||||
//! trait and never called from anywhere, so implementors wired up a callback
|
||||
//! that could not run. These tests exist so that cannot silently recur.
|
||||
|
||||
use std::sync::{Arc, Mutex};
|
||||
|
||||
use trueskill_tt::{History, Observer};
|
||||
|
||||
/// `History` takes its observer by value and never hands it back, so a test
|
||||
/// that wants to read what was recorded shares the storage rather than the
|
||||
/// observer: the handles are cloned, the buffers are not.
|
||||
#[derive(Clone, Default)]
|
||||
struct Recorder {
|
||||
iterations: Arc<Mutex<Vec<usize>>>,
|
||||
slices: Arc<Mutex<Vec<(i64, usize, usize)>>>,
|
||||
converged: Arc<Mutex<Vec<(usize, bool)>>>,
|
||||
}
|
||||
|
||||
impl Observer<i64> for Recorder {
|
||||
fn on_iteration_end(&self, iter: usize, _max_step: (f64, f64)) {
|
||||
self.iterations.lock().unwrap().push(iter);
|
||||
}
|
||||
|
||||
fn on_slice_processed(&self, time: &i64, slice_idx: usize, n_events: usize) {
|
||||
self.slices
|
||||
.lock()
|
||||
.unwrap()
|
||||
.push((*time, slice_idx, n_events));
|
||||
}
|
||||
|
||||
fn on_converged(&self, iters: usize, _final_step: (f64, f64), converged: bool) {
|
||||
self.converged.lock().unwrap().push((iters, converged));
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn every_observer_callback_fires() {
|
||||
let recorder = Recorder::default();
|
||||
let mut h = History::builder().observer(recorder.clone()).build();
|
||||
|
||||
h.record_winner(&"a", &"b", 1).unwrap();
|
||||
h.record_winner(&"b", &"c", 2).unwrap();
|
||||
h.record_winner(&"c", &"a", 3).unwrap();
|
||||
h.converge().unwrap();
|
||||
|
||||
assert!(
|
||||
!recorder.iterations.lock().unwrap().is_empty(),
|
||||
"on_iteration_end never fired"
|
||||
);
|
||||
assert!(
|
||||
!recorder.converged.lock().unwrap().is_empty(),
|
||||
"on_converged never fired"
|
||||
);
|
||||
assert!(
|
||||
!recorder.slices.lock().unwrap().is_empty(),
|
||||
"on_slice_processed never fired — the defect this test exists for"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn slice_callbacks_report_the_slice_they_swept() {
|
||||
let recorder = Recorder::default();
|
||||
let mut h = History::builder().observer(recorder.clone()).build();
|
||||
|
||||
h.record_winner(&"a", &"b", 10).unwrap();
|
||||
h.record_winner(&"a", &"b", 20).unwrap();
|
||||
h.converge().unwrap();
|
||||
|
||||
let slices = recorder.slices.lock().unwrap();
|
||||
|
||||
// Only the times actually in the history, and each with its own events.
|
||||
for &(time, idx, events) in slices.iter() {
|
||||
assert!(time == 10 || time == 20, "unexpected slice time {time}");
|
||||
assert!(idx < 2, "slice index {idx} out of range");
|
||||
assert_eq!(events, 1, "each slice holds exactly one event");
|
||||
}
|
||||
|
||||
// Both slices must be reported, not just one end of the sweep.
|
||||
assert!(
|
||||
slices.iter().any(|&(t, ..)| t == 10),
|
||||
"slice 10 never reported"
|
||||
);
|
||||
assert!(
|
||||
slices.iter().any(|&(t, ..)| t == 20),
|
||||
"slice 20 never reported"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_single_slice_history_still_reports_its_sweep() {
|
||||
let recorder = Recorder::default();
|
||||
let mut h = History::builder().observer(recorder.clone()).build();
|
||||
|
||||
h.record_winner(&"a", &"b", 1).unwrap();
|
||||
h.converge().unwrap();
|
||||
|
||||
let slices = recorder.slices.lock().unwrap();
|
||||
assert!(
|
||||
!slices.is_empty(),
|
||||
"the single-slice path must report its sweep too"
|
||||
);
|
||||
assert!(slices.iter().all(|&(t, idx, _)| t == 1 && idx == 0));
|
||||
}
|
||||
Reference in New Issue
Block a user