Files
trueskill-tt/tests/api_shape.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

297 lines
7.8 KiB
Rust

//! Tests for the new T2 public API surface: typed add_events(iter) and the
//! fluent event builder (added in Task 16).
use smallvec::smallvec;
use trueskill_tt::{ConstantDrift, ConvergenceOptions, Event, History, Member, Outcome, Team};
#[test]
fn add_events_bulk_via_iter() {
let mut h = History::builder()
.mu(0.0)
.sigma(2.0)
.beta(1.0)
.p_draw(0.0)
.drift(ConstantDrift::new(0.0))
.convergence(ConvergenceOptions {
max_iter: 30,
epsilon: 1e-6,
alpha: 1.0,
})
.build();
let events: Vec<Event<i64, &'static str>> = vec![
Event {
time: 1,
teams: smallvec![
Team::with_members([Member::new("a")]),
Team::with_members([Member::new("b")]),
],
outcome: Outcome::winner(0, 2),
},
Event {
time: 2,
teams: smallvec![
Team::with_members([Member::new("b")]),
Team::with_members([Member::new("c")]),
],
outcome: Outcome::winner(0, 2),
},
];
h.add_events(events).unwrap();
let report = h.converge().unwrap();
assert!(report.converged);
assert!(h.lookup(&"a").is_some());
assert!(h.lookup(&"b").is_some());
assert!(h.lookup(&"c").is_some());
}
#[test]
fn add_events_draw() {
let mut h = History::builder()
.mu(25.0)
.sigma(25.0 / 3.0)
.beta(25.0 / 6.0)
.p_draw(0.25)
.drift(ConstantDrift::new(25.0 / 300.0))
.build();
let events: Vec<Event<i64, &'static str>> = vec![Event {
time: 1,
teams: smallvec![
Team::with_members([Member::new("alice")]),
Team::with_members([Member::new("bob")]),
],
outcome: Outcome::draw(2),
}];
h.add_events(events).unwrap();
let _ = h.converge().unwrap();
}
#[test]
fn add_events_rejects_mismatched_outcome_ranks() {
use trueskill_tt::InferenceError;
let mut h: History = History::builder().build();
let events: Vec<Event<i64, &'static str>> = vec![Event {
time: 1,
teams: smallvec![
Team::with_members([Member::new("a")]),
Team::with_members([Member::new("b")]),
],
outcome: Outcome::ranking([0, 1, 2]), // 3 ranks but 2 teams
}];
let err = h.add_events(events).unwrap_err();
assert!(matches!(err, InferenceError::MismatchedShape { .. }));
}
#[test]
fn fluent_event_builder_basic() {
let mut h = History::builder()
.mu(25.0)
.sigma(25.0 / 3.0)
.beta(25.0 / 6.0)
.p_draw(0.0)
.build();
h.event(1)
.team(["alice", "bob"])
.weights([1.0, 0.7])
.team(["carol"])
.ranking([1, 0])
.commit()
.unwrap();
let report = h.converge().unwrap();
assert!(report.converged);
assert!(h.lookup(&"alice").is_some());
assert!(h.lookup(&"bob").is_some());
assert!(h.lookup(&"carol").is_some());
}
#[test]
fn fluent_event_builder_winner_convenience() {
let mut h = History::builder()
.mu(25.0)
.sigma(25.0 / 3.0)
.beta(25.0 / 6.0)
.p_draw(0.0)
.build();
h.event(1)
.team(["alice"])
.team(["bob"])
.winner(0)
.commit()
.unwrap();
let _ = h.converge().unwrap();
}
#[test]
fn fluent_event_builder_draw() {
let mut h = History::builder()
.mu(25.0)
.sigma(25.0 / 3.0)
.beta(25.0 / 6.0)
.p_draw(0.25)
.build();
h.event(1)
.team(["alice"])
.team(["bob"])
.draw()
.commit()
.unwrap();
let _ = h.converge().unwrap();
}
#[test]
fn current_skill_and_learning_curve() {
use trueskill_tt::History;
let mut h = History::builder()
.mu(25.0)
.sigma(25.0 / 3.0)
.beta(25.0 / 6.0)
.p_draw(0.0)
.build();
h.record_winner(&"a", &"b", 1).unwrap();
h.record_winner(&"a", &"b", 2).unwrap();
let _ = h.converge().unwrap();
let a = h.current_skill(&"a").unwrap();
assert!(a.mu() > 25.0);
let b = h.current_skill(&"b").unwrap();
assert!(b.mu() < 25.0);
let a_curve = h.learning_curve(&"a").unwrap();
assert_eq!(a_curve.len(), 2);
assert_eq!(a_curve[0].0, 1);
assert_eq!(a_curve[1].0, 2);
let all = h.learning_curves();
assert_eq!(all.len(), 2);
assert!(all.contains_key("a"));
assert!(all.contains_key("b"));
}
#[test]
fn log_evidence_total_vs_subset() {
use trueskill_tt::{ConstantDrift, History};
let mut h = History::builder()
.mu(0.0)
.sigma(6.0)
.beta(1.0)
.p_draw(0.0)
.drift(ConstantDrift::new(0.0))
.build();
h.record_winner(&"a", &"b", 1).unwrap();
h.record_winner(&"b", &"a", 2).unwrap();
let total = h.log_evidence();
let a_only = h.log_evidence_for(&[&"a"]).unwrap();
assert!(total.is_finite());
assert!(a_only.is_finite());
}
#[test]
fn predict_quality_two_teams() {
use trueskill_tt::History;
let mut h = History::builder()
.mu(25.0)
.sigma(25.0 / 3.0)
.beta(25.0 / 6.0)
.p_draw(0.0)
.build();
h.record_winner(&"a", &"b", 1).unwrap();
let _ = h.converge().unwrap();
let q = h.predict_quality(&[&[&"a"], &[&"b"]]).unwrap();
assert!(q > 0.0 && q <= 1.0);
}
#[test]
fn predict_outcome_two_teams_sums_to_one() {
use trueskill_tt::History;
let mut h = History::builder()
.mu(25.0)
.sigma(25.0 / 3.0)
.beta(25.0 / 6.0)
.p_draw(0.0)
.build();
h.record_winner(&"a", &"b", 1).unwrap();
let _ = h.converge().unwrap();
let p = h.predict_outcome(&[&[&"a"], &[&"b"]]).unwrap();
let wins = p.win_probabilities();
assert_eq!(wins.len(), 2);
// With p_draw == 0 there is no draw outcome, so the two win
// probabilities are the whole space.
assert!((p.total() - 1.0).abs() < 1e-9, "total = {}", p.total());
assert!((wins[0] + wins[1] - 1.0).abs() < 1e-9);
assert!(wins[0] > wins[1]);
}
#[test]
fn fluent_event_builder_scores() {
use trueskill_tt::ConstantDrift;
let mut h = History::builder()
.mu(25.0)
.sigma(25.0 / 3.0)
.beta(25.0 / 6.0)
.drift(ConstantDrift::new(0.0))
.build();
h.event(1)
.team(["alice"])
.team(["bob"])
.scores([12.0, 4.0])
.commit()
.unwrap();
let _ = h.converge().unwrap();
let a = h.current_skill(&"alice").unwrap();
let b = h.current_skill(&"bob").unwrap();
assert!(a.mu() > b.mu());
}
/// Every field of `ConvergenceReport` must carry real information.
///
/// `slices_skipped` was public, hardcoded to `0`, and reported a plausible
/// value for a feature that never existed — the same shape as the inert
/// `online` flag in #19. It was removed in #33. This pins the remaining fields
/// so the next always-constant member has to survive an assertion rather than
/// just a reviewer's attention.
#[test]
fn every_convergence_report_field_is_populated() {
let mut h = History::builder().build();
for time in 1..=6i64 {
h.record_winner(&"a", &"b", time).unwrap();
}
let report = h.converge().unwrap();
assert!(
report.iterations > 0,
"iterations is zero on a real converge"
);
assert!(report.converged, "fixture must converge");
assert!(
report.final_step.0.is_finite() && report.final_step.1.is_finite(),
"final_step is not finite: {:?}",
report.final_step
);
assert!(
report.log_evidence.is_finite() && report.log_evidence < 0.0,
"log_evidence is not a finite negative log probability: {}",
report.log_evidence
);
assert_eq!(
report.per_iteration_time.len(),
report.iterations,
"per_iteration_time must carry one duration per iteration"
);
}