Files
trueskill-tt/tests/game.rs
T
logaritmiskandClaude Opus 5 507894dae7 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
2026-09-07 14:57:39 +02:00

141 lines
4.0 KiB
Rust

use trueskill_tt::{
ConstantDrift, ConvergenceOptions, Game, GameOptions, Gaussian, InferenceError, Outcome, Rating,
};
type R = Rating<i64, ConstantDrift>;
fn default_rating() -> R {
R::new(
Gaussian::from_ms(25.0, 25.0 / 3.0),
25.0 / 6.0,
ConstantDrift(25.0 / 300.0),
)
}
#[test]
fn game_ranked_1v1_golden() {
let a = default_rating();
let b = default_rating();
let g = Game::<i64, _>::ranked(
&[&[a], &[b]],
Outcome::winner(0, 2),
&GameOptions::default(),
)
.unwrap();
let p = g.posteriors();
assert!(p[0][0].mu() > 25.0);
assert!(p[1][0].mu() < 25.0);
assert!((p[0][0].sigma() - p[1][0].sigma()).abs() < 1e-6);
}
#[test]
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), &GameOptions::default()).unwrap();
assert!(a_post.mu() > 25.0);
assert!(b_post.mu() < 25.0);
}
#[test]
fn game_ranked_rejects_bad_p_draw() {
let a = R::new(Gaussian::default(), 1.0, ConstantDrift(0.0));
let err = Game::<i64, _>::ranked(
&[&[a], &[a]],
Outcome::winner(0, 2),
&GameOptions {
p_draw: 1.5,
score_sigma: 1.0,
convergence: ConvergenceOptions::default(),
},
)
.unwrap_err();
assert!(matches!(err, InferenceError::InvalidProbability { .. }));
}
#[test]
fn game_ranked_rejects_mismatched_ranks() {
let a = R::new(Gaussian::default(), 1.0, ConstantDrift(0.0));
let err = Game::<i64, _>::ranked(
&[&[a], &[a]],
Outcome::ranking([0, 1, 2]),
&GameOptions::default(),
)
.unwrap_err();
assert!(matches!(err, InferenceError::MismatchedShape { .. }));
}
#[test]
fn game_free_for_all_three_players() {
let a = default_rating();
let b = default_rating();
let c = default_rating();
let g = Game::<i64, _>::free_for_all(
&[&a, &b, &c],
Outcome::ranking([0, 1, 2]),
&GameOptions::default(),
)
.unwrap();
let p = g.posteriors();
assert_eq!(p.len(), 3);
assert!(p[0][0].mu() > p[1][0].mu());
assert!(p[1][0].mu() > p[2][0].mu());
}
#[test]
fn game_log_evidence_is_finite() {
let a = default_rating();
let b = default_rating();
let g = Game::<i64, _>::ranked(
&[&[a], &[b]],
Outcome::winner(0, 2),
&GameOptions::default(),
)
.unwrap();
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);
}