trueskill-tt/tests/evidence_matrix.rs

//! The evidence accessors span two independent axes — smoothed vs forward-only,
//! all-keys vs key-restricted — and all four corners must exist and differ.
//!
//! `filtered_log_evidence_for` was the missing corner: the one a per-competitor
//! prequential score needs.

use trueskill_tt::{Event, History, InferenceError, Member, Outcome, Team};

type H = History;

/// Two disjoint cohorts, so a key restriction is guaranteed to leave events out.
fn two_cohorts() -> H {
    let mut h = H::default();
    let mut events = Vec::new();
    for t in 1..=6 {
        for (x, y) in [("a", "b"), ("c", "d")] {
            events.push(Event {
                time: t,
                teams: [
                    Team::with_members([Member::new(x)]),
                    Team::with_members([Member::new(y)]),
                ]
                .into_iter()
                .collect(),
                outcome: Outcome::winner(0, 2),
            });
        }
    }
    h.add_events(events).expect("fixture ingests");
    h.converge().expect("fixture converges");
    h
}

#[test]
fn all_four_corners_are_distinct_quantities() {
    let h = two_cohorts();

    let smoothed_all = h.log_evidence();
    let smoothed_ab = h.log_evidence_for(&[&"a", &"b"]).unwrap();
    let filtered_all = h.filtered_log_evidence();
    let filtered_ab = h.filtered_log_evidence_for(&[&"a", &"b"]).unwrap();

    for (name, v) in [
        ("smoothed_all", smoothed_all),
        ("smoothed_ab", smoothed_ab),
        ("filtered_all", filtered_all),
        ("filtered_ab", filtered_ab),
    ] {
        assert!(
            v.is_finite() && v <= 0.0,
            "{name} = {v} is not a log probability"
        );
    }

    // Restricting to one cohort must drop the other cohort's events. Half the
    // events, and the two cohorts are symmetric, so it lands near half.
    assert!(
        smoothed_ab > smoothed_all,
        "restricting must drop evidence terms: {smoothed_ab} vs {smoothed_all}"
    );
    assert!(filtered_ab > filtered_all);

    // The forward-only corner is a genuinely different quantity from the
    // smoothed one, not an alias for it.
    assert!(
        (filtered_ab - smoothed_ab).abs() > 1e-9,
        "filtered and smoothed restricted evidence coincide ({filtered_ab} vs {smoothed_ab}); \
         one of them is not computing what it claims"
    );
}

#[test]
fn restricting_to_both_cohorts_recovers_the_unrestricted_value() {
    let h = two_cohorts();

    // Control on the filter itself: naming every competitor must restrict
    // nothing, so this catches a filter that drops events it should keep.
    let all_named = h
        .filtered_log_evidence_for(&[&"a", &"b", &"c", &"d"])
        .unwrap();
    assert!(
        (all_named - h.filtered_log_evidence()).abs() < 1e-12,
        "naming everyone changed the answer: {all_named} vs {}",
        h.filtered_log_evidence()
    );
}

/// The restriction selects *events*, not competitors: naming one member of a
/// pair that only ever plays each other selects the same events as naming both.
#[test]
fn naming_either_member_of_a_pair_selects_the_same_events() {
    let h = two_cohorts();

    let ab = h.filtered_log_evidence_for(&[&"a"]).unwrap();
    let ab_pair = h.filtered_log_evidence_for(&[&"a", &"b"]).unwrap();
    assert!(
        (ab - ab_pair).abs() < 1e-12,
        "a and b only ever play each other, so naming either or both selects \
         the same events: {ab} vs {ab_pair}"
    );
}

#[test]
fn an_unknown_key_is_an_error_here_too() {
    let h = two_cohorts();

    let err = h
        .filtered_log_evidence_for(&[&"typo"])
        .expect_err("unknown key");
    assert!(matches!(err, InferenceError::UnknownKey { .. }), "{err:?}");

    // Control: the same call on a known key succeeds.
    h.filtered_log_evidence_for(&[&"a"]).expect("a is known");
}

#[test]
fn current_skills_agrees_with_current_skill() {
    let h = two_cohorts();

    let all = h.current_skills();
    assert_eq!(all.len(), 4, "four competitors played");

    for key in ["a", "b", "c", "d"] {
        let one = h.current_skill(key).expect("played");
        let from_map = all[key];
        assert_eq!(
            (one.mu(), one.sigma()),
            (from_map.mu(), from_map.sigma()),
            "current_skills disagrees with current_skill for {key}"
        );
    }
}

#[test]
fn current_skills_omits_a_registered_but_unplayed_competitor() {
    let mut h = two_cohorts();
    h.register(Member::new("e")).expect("e is new");

    let all = h.current_skills();
    assert!(
        !all.contains_key("e"),
        "a competitor with no appearances has no posterior to report"
    );
    assert!(
        h.current_skill("e").is_none(),
        "control: the singular agrees"
    );
    assert_eq!(all.len(), 4);
}