Files
trueskill-tt/tests/event_builder_members.rs
T
logaritmiskandClaude Opus 5 e4a68ba1a7 fix!: per-key queries report unknown keys instead of a plausible constant
Two accessors answered a question about a key the history had never seen
with a well-formed value indistinguishable from a real answer.

`log_evidence_for` filter_map'd unknown keys away. An empty target list
means "no restriction" downstream, so a list of *entirely* unknown keys
returned the whole-history evidence: measured on a two-cohort fixture,
`log_evidence_for(["typo"])` returned exactly `log_evidence()`. On the
one workload it is documented for — leave-one-out cross-validation —
that is the un-held-out score, a plausible number that silently
invalidates the comparison it was computed for. It now returns
`Err(UnknownKey)` naming the offending position.

`learning_curve` and `filtered_learning_curve` returned an empty `Vec`
both for a typo'd key and for a competitor who is registered but has not
played yet. They now return `Option`, so `None` is "never heard of it"
and `Some(vec![])` is "known, no appearances".

Tests carry a control case in each direction, so they cannot pass by
everything returning the same thing.

Closes #66, closes #70.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011hcFjNDmHXZF8URGLku5zZ
2026-09-09 21:13:35 +02:00

195 lines
5.9 KiB
Rust

//! `EventBuilder::members` must reach exactly what the typed path reaches.
//!
//! Before this existed, `EventBuilder` could set weights and nothing else, so
//! `prior` and `drift_scale` were expressible only through `Event`/`Team`/
//! `Member` + `add_events`. Which ingestion route a competitor arrived through
//! decided whether it could be configured at all.
use smallvec::smallvec;
use trueskill_tt::{
ConstantDrift, ConvergenceOptions, Event, Gaussian, History, InferenceError, Member, Outcome,
Team,
};
type H = History<i64, ConstantDrift, trueskill_tt::NullObserver, &'static str>;
fn history() -> H {
History::builder()
.mu(0.0)
.sigma(6.0)
.beta(1.0)
.score_sigma(2.0)
.drift(ConstantDrift::new(0.5))
.convergence(ConvergenceOptions {
max_iter: 20_000,
epsilon: 1e-13,
alpha: 1.0,
})
.build()
}
const PRIOR: Gaussian = Gaussian::from_ms(3.0, 1.5);
/// The contract that makes the escape hatch worth having: same configuration,
/// same fit, bit for bit.
#[test]
fn members_matches_the_typed_path_exactly() {
let mut typed = history();
typed
.add_events(vec![Event {
time: 1,
teams: smallvec![
Team::with_members([Member::new("player")]),
Team::with_members([Member::new("layout_7")
.with_drift_scale(0.0)
.with_prior(PRIOR)]),
],
outcome: Outcome::scores([5.0, 2.0]),
}])
.unwrap();
assert!(typed.converge().unwrap().converged);
let mut fluent = history();
fluent
.event(1)
.team(["player"])
.members([Member::new("layout_7")
.with_drift_scale(0.0)
.with_prior(PRIOR)])
.scores([5.0, 2.0])
.commit()
.unwrap();
assert!(fluent.converge().unwrap().converged);
for key in ["player", "layout_7"] {
let a = typed.current_skill(&key).unwrap();
let b = fluent.current_skill(&key).unwrap();
assert_eq!(a.pi(), b.pi(), "{key} pi");
assert_eq!(a.tau(), b.tau(), "{key} tau");
}
}
/// The configuration has to actually take effect, not merely round-trip: a
/// competitor pinned with `drift_scale = 0.0` must not move across slices,
/// where an unpinned one does.
///
/// The comparison is against a control rather than against a fixed epsilon.
/// Pinned marginals are not bit-identical across slices — each slice combines
/// its own forward and backward messages, so the arithmetic order differs and
/// the last bit moves. What "pinned" promises is that no drift variance
/// accumulates, and the control is what makes that measurable.
#[test]
fn a_drift_scale_set_through_members_is_applied() {
fn spread(h: &H, key: &'static str) -> f64 {
let curve = h.learning_curve(&key).unwrap();
assert!(curve.len() >= 2, "{key}: expected several appearances");
let (lo, hi) = curve.iter().fold((f64::MAX, f64::MIN), |(lo, hi), (_, g)| {
(lo.min(g.sigma()), hi.max(g.sigma()))
});
(hi - lo) / hi
}
let mut h = history();
for t in 1..=4 {
h.event(t)
.team(["player"])
.members([Member::new("pinned").with_drift_scale(0.0)])
.scores([5.0, 2.0])
.commit()
.unwrap();
// Same shape, no pinning: the control.
h.event(t)
.team(["rival"])
.team(["drifting"])
.scores([5.0, 2.0])
.commit()
.unwrap();
}
assert!(h.converge().unwrap().converged);
let pinned = spread(&h, "pinned");
let drifting = spread(&h, "drifting");
assert!(pinned < 1e-9, "pinned competitor moved: {pinned:e}");
assert!(
drifting > 1e-3,
"control did not move, so the test proves nothing: {drifting:e}"
);
}
/// `weights` still applies to a team added through `members`, and still
/// records a mismatch rather than partially applying it.
#[test]
fn weights_still_guards_a_members_team() {
let mut h = history();
let err = h
.event(1)
.team(["a"])
.members([Member::new("b"), Member::new("c")])
.weights([1.0])
.winner(0)
.commit()
.unwrap_err();
assert!(
matches!(
err,
InferenceError::MismatchedShape {
kind: "weights",
expected: 2,
got: 1,
..
}
),
"{err:?}"
);
assert!(h.current_skill(&"b").is_none(), "nothing may reach history");
}
/// An invalid `drift_scale` surfaces from `commit`, not from a panic and not
/// silently.
#[test]
fn an_invalid_drift_scale_surfaces_from_commit() {
for bad in [-1.0, f64::NAN, f64::INFINITY] {
let mut h = history();
let err = h
.event(1)
.team(["a"])
.members([Member::new("b").with_drift_scale(bad)])
.winner(0)
.commit()
.unwrap_err();
assert!(
matches!(
err,
InferenceError::InvalidParameter {
name: "drift_scale",
..
}
),
"{bad}: {err:?}"
);
assert!(h.current_skill(&"b").is_none(), "{bad} reached the history");
}
}
/// `members` and `team` compose in either order.
#[test]
fn members_and_team_interleave() {
let mut h = history();
h.event(1)
.members([Member::new("a").with_prior(PRIOR)])
.team(["b"])
.scores([3.0, 1.0])
.commit()
.unwrap();
h.event(2)
.team(["b"])
.members([Member::new("c").with_prior(PRIOR)])
.scores([2.0, 4.0])
.commit()
.unwrap();
assert!(h.converge().unwrap().converged);
for key in ["a", "b", "c"] {
assert!(h.current_skill(&key).is_some(), "{key} missing");
}
}