Clusters phase A: community detection core (Louvain, seeded, structural)

detectCommunities(nodes, edges) in src/core/clusters.ts (new dep
graphology-communities-louvain): Louvain modularity over the undirected,
unweighted follows+supports structure (user-decided 2026-09-13). The
random-walk traversal runs on an inlined seeded mulberry32 so the same
graph always yields the same partition; community indices are still
unstable across edits, which is exactly why labelings (phase B) key to
sorted MEMBER SETS. follows+supports between the same pair collapse to
one edge; self-loops and dangling edges are skipped defensively; no
min-size filter here (the >=3 render threshold is a presentation rule).

Tests: two-cliques-plus-bridge split, determinism, singleton/empty
graphs, pair collapse, defensive skips, member sorting. 363/363.

Real-data smoke over the current notes graph: 338 nodes / 211 edges ->
138 communities, modularity 0.95, and the big ones are exactly the
learn-session topics (databases, differential forms, sales, servers,
vim, copulas...). 32 communities clear the >=3 render threshold.
This commit is contained in:
amosblomqvist
2026-09-13 03:46:24 +03:00
parent b4245a209d
commit 95a4477283
5 changed files with 276 additions and 0 deletions
+103
View File
@@ -0,0 +1,103 @@
/**
* Community detection tests (vision §1, DECIDED 2026-09-13) — pure
* structural Louvain over follows+supports, deterministic via seed.
* Assertions are on SHAPE and MEMBER SETS, never community indices
* (indices reshuffle; member sets are what labelings key to).
*/
import { strict as assert } from "node:assert";
import { describe, test } from "node:test";
import { detectCommunities } from "../src/core/clusters.ts";
import type { Community } from "../src/core/clusters.ts";
const ids = (n: number, prefix = "n") => [...Array(n).keys()].map((i) => `${prefix}${i}`);
/** A clique on the given ids. */
const clique = (nodeIds: string[]) =>
nodeIds.flatMap((a, i) => nodeIds.slice(i + 1).map((b) => ({ from: a, to: b })));
describe("detectCommunities", () => {
test("two dense cliques joined by a single bridge split into two communities", () => {
const left = ids(4, "L");
const right = ids(4, "R");
const bridge = { from: "L0", to: "R0" };
const result = detectCommunities([...left, ...right].map((id) => ({ id })), [...clique(left), ...clique(right), bridge]);
assert.equal(result.communities.length, 2);
assert.equal(result.modularity > 0.3, true);
// Member sets, not order: the two big communities are exactly the cliques.
const big = result.communities.filter((c) => c.members.length === 4);
assert.deepEqual(big.map((c) => c.members.sort()).sort(), [left.slice().sort(), right.slice().sort()]);
});
test("deterministic: same graph, same seed → identical partition", () => {
const nodes = ids(10).map((id) => ({ id }));
const edges = [...clique(ids(5)), ...clique(ids(5, "n").slice().reverse().slice(0, 5)), { from: "n0", to: "n9" }];
const a = detectCommunities(nodes, edges);
const b = detectCommunities(nodes, edges);
assert.deepEqual(a.communities, b.communities);
assert.equal(a.modularity, b.modularity);
});
test("no edges: every node is its own singleton community", () => {
const result = detectCommunities(ids(3).map((id) => ({ id })), []);
assert.equal(result.communities.length, 3);
for (const c of result.communities) assert.equal(c.members.length, 1);
assert.equal(result.modularity, 0);
});
test("empty graph: zero communities", () => {
assert.deepEqual(detectCommunities([], []), { communities: [], modularity: 0 });
});
test("duplicate and reversed pairs collapse to one edge (undirected, unweighted)", () => {
const nodes = ["a", "b", "c"].map((id) => ({ id }));
// follows a→b AND supports b→a — same pair twice, both directions.
const result = detectCommunities(nodes, [
{ from: "a", to: "b" },
{ from: "b", to: "a" },
{ from: "b", to: "c" },
]);
assert.equal(result.communities.length, 1);
assert.deepEqual(result.communities[0].members.sort(), ["a", "b", "c"]);
});
test("self-loops and unknown-endpoint edges are skipped defensively", () => {
const nodes = ["a", "b"].map((id) => ({ id }));
const result = detectCommunities(nodes, [
{ from: "a", to: "a" }, // self-loop
{ from: "a", to: "ghost" }, // dangling
{ from: "ghost1", to: "ghost2" },
{ from: "a", to: "b" }, // the one real edge
]);
assert.equal(result.communities.length, 1);
assert.deepEqual(result.communities[0].members.sort(), ["a", "b"]);
});
test("members are sorted; communities ordered by size then id", () => {
const left = ids(4, "L");
const right = ids(4, "R");
const result = detectCommunities(
[...left, ...right, "iso"].map((id) => ({ id })),
[...clique(left), ...clique(right), { from: "L0", to: "R0" }],
);
for (const c of result.communities as Community[]) {
const sorted = c.members.slice().sort();
assert.deepEqual(c.members, sorted);
}
// iso (isolated) is last: size 1 < 4.
const last = result.communities[result.communities.length - 1];
assert.deepEqual(last.members, ["iso"]);
});
test("seed override changes nothing structurally but stays deterministic", () => {
const nodes = ids(8).map((id) => ({ id }));
const edges = [...clique(["n0", "n1", "n2", "n3"]), ...clique(["n4", "n5", "n6", "n7"]), { from: "n0", to: "n4" }];
const a = detectCommunities(nodes, edges, { seed: "one" });
const b = detectCommunities(nodes, edges, { seed: "one" });
const c = detectCommunities(nodes, edges, { seed: "two" });
assert.deepEqual(a.communities, b.communities);
// A different seed partitions the same graph into member sets that
// may or may not coincide — but both runs are 2 communities here,
// because the structure dominates.
assert.equal(c.communities.length, 2);
});
});