trueskill-tt/tests/sparsity_measurement.rs

//! What a sparse factorisation of the joint would actually buy (#52).
//!
//! Run explicitly:
//!
//! ```text
//! cargo test --release --features approx,measure-sparsity \
//!     --test sparsity_measurement -- --ignored --nocapture
//! ```
//!
//! The whole file is gated: it reaches for the joint's sparsity pattern, which
//! is exposed only under `measure-sparsity`.
#![cfg(feature = "measure-sparsity")]

use std::collections::HashSet;

use trueskill_tt::{ConvergenceOptions, History};

/// A history shaped like the issue's fixture: many slices, scored duels,
/// competitors reappearing across slices so the drift links are long.
fn fitted(slices: i64, duels: usize, competitors: usize) -> History<String> {
    let mut h: History<String> = History::builder()
        .key_type::<String>()
        .mu(0.0)
        .sigma(6.0)
        .beta(1.0)
        .score_sigma(2.0)
        .gamma(0.05)
        .convergence(ConvergenceOptions {
            max_iter: trueskill_tt::ITERATIONS,
            epsilon: 1e-8,
            alpha: 1.0,
        })
        .build();

    let mut k = 0usize;
    for t in 0..slices {
        for _ in 0..duels {
            k += 1;
            h.event(t)
                .team([format!("p{}", k % competitors)])
                .team([format!("p{}", (k + 37) % competitors)])
                .scores([
                    (k as f64 * 0.3).sin().abs() * 20.0,
                    (k as f64 * 0.3).cos().abs() * 20.0,
                ])
                .commit()
                .expect("ingests");
        }
    }
    h.converge().expect("converges");
    h
}

/// Symbolic Cholesky by row-merge: returns (nnz(L), flops).
///
/// Fill-in is simulated directly — for each column, the set of rows below the
/// diagonal that are nonzero — which is exact and easily checked, at the cost
/// of being O(n * nnz(L)) rather than the linear elimination-tree method.
fn symbolic(n: usize, adj: &[HashSet<usize>], perm_of: &[usize]) -> (usize, f64) {
    // `perm_of[old] = new`. Build the permuted lower-triangle pattern.
    let mut cols: Vec<HashSet<usize>> = vec![HashSet::new(); n];
    for (old, nbrs) in adj.iter().enumerate() {
        let i = perm_of[old];
        for &old_j in nbrs {
            let j = perm_of[old_j];
            if j < i {
                cols[j].insert(i);
            }
        }
    }

    let mut nnz = 0usize;
    let mut flops = 0.0f64;
    for j in 0..n {
        // Column j's pattern is final once every earlier column has merged in.
        let rows: Vec<usize> = cols[j].iter().copied().collect();
        let c = rows.len();
        nnz += c + 1; // below-diagonal entries plus the diagonal
        // Cholesky work for this column: one outer product over its pattern.
        flops += (c as f64 + 1.0) * (c as f64 + 1.0);
        // Fill-in: every pair in column j becomes an edge in the remaining graph.
        for (a_idx, &a) in rows.iter().enumerate() {
            for &b in &rows[a_idx + 1..] {
                let (lo, hi) = if a < b { (a, b) } else { (b, a) };
                cols[lo].insert(hi);
            }
        }
    }
    (nnz, flops)
}

#[test]
#[ignore = "measurement, run explicitly"]
fn what_sparsity_would_buy() {
    for (slices, duels, competitors) in [(30, 8, 100), (76, 13, 200)] {
        let h = fitted(slices, duels, competitors);
        let (n, pattern) = h.joint_pattern_for_measurement();

        let nnz_a: usize = pattern.iter().map(HashSet::len).sum::<usize>() + n;
        let dense_flops = (n as f64).powi(3) / 3.0;

        let natural: Vec<usize> = (0..n).collect();
        let (nnz_nat, flops_nat) = symbolic(n, &pattern, &natural);

        // AMD returns `perm[new] = old`; invert it.
        let (col_ptr, row_idx) = csc(n, &pattern);
        let p = feral_amd::amd_order(
            &feral_amd::CscPattern::new(n, &col_ptr, &row_idx).expect("valid pattern"),
        )
        .expect("amd");
        let mut perm_of = vec![0usize; n];
        for (new, &old) in p.iter().enumerate() {
            perm_of[old as usize] = new;
        }
        let (nnz_amd, flops_amd) = symbolic(n, &pattern, &perm_of);

        println!(
            "\n=== {slices} slices x {duels} duels, {competitors} competitors ===\n\
             n              = {n}\n\
             nnz(A)         = {nnz_a}  ({:.4}% dense)\n\
             dense flops    = {:.3e}\n\
             nnz(L) natural = {nnz_nat}   flops = {:.3e}  ({:.1}x vs dense)\n\
             nnz(L) AMD     = {nnz_amd}   flops = {:.3e}  ({:.1}x vs dense)",
            100.0 * nnz_a as f64 / (n * n) as f64,
            dense_flops,
            flops_nat,
            dense_flops / flops_nat,
            flops_amd,
            dense_flops / flops_amd,
        );
    }
}

/// Full symmetric pattern to CSC, as `feral-amd` wants it.
fn csc(n: usize, adj: &[HashSet<usize>]) -> (Vec<i32>, Vec<i32>) {
    let mut col_ptr = Vec::with_capacity(n + 1);
    let mut row_idx = Vec::new();
    col_ptr.push(0i32);
    for (j, nbrs) in adj.iter().enumerate() {
        let mut rows: Vec<i32> = nbrs.iter().map(|&i| i as i32).collect();
        rows.push(j as i32);
        rows.sort_unstable();
        rows.dedup();
        row_idx.extend_from_slice(&rows);
        col_ptr.push(row_idx.len() as i32);
    }
    (col_ptr, row_idx)
}

/// End-to-end factorisation time at the scale #52 was opened about.
#[test]
#[ignore = "measurement, run explicitly"]
fn factorisation_time_at_scale() {
    use std::time::Instant;

    for (slices, duels, competitors) in [(30, 8, 100), (76, 13, 200), (150, 26, 400)] {
        let h = fitted(slices, duels, competitors);
        let (n, _) = h.joint_pattern_for_measurement();

        // Warm, then time.
        let _ = h.joint().expect("scored history");
        let t = Instant::now();
        let joint = h.joint().expect("scored history");
        let factor = t.elapsed();

        let a = "p0".to_string();
        let b = "p1".to_string();
        let t = Instant::now();
        let _ = joint.posterior_of(&[(&a, 1.0), (&b, -1.0)]).expect("known");
        let query = t.elapsed();

        println!(
            "n = {n:5}  factorise = {factor:>12?}   query = {query:>10?}   \
             (dense was O(n^3): {:.3e} flops)",
            (n as f64).powi(3) / 3.0
        );
    }
}