v3: the lake processed + /data page + glossary terms

- scripts/processStatsbomb.ts: one pass over the 17GB StatsBomb lake (4,235
  matches) -> lakestats.json (12.82GB events / 14.9M events / 6,919 players),
  scorestate.json (goal-rate multipliers by game state — shipped as an insight,
  NOT wired into in-play: the raw effect is selection-biased toward stronger
  teams and would distort a calibrated model), fingerprints.json (40/48 nations'
  shots/xG/set-piece share from real event data). Artifacts committed; raw lake
  stays local (gitignored).
- /data page + /api/data/stats: the gigabytes made visible — lake counters,
  historical archive, live-collection counts (odds lines, frozen forecasts,
  enrichment), per-source health with freshness. Footer links.
- Term component: plain-language glossary tooltips (RPS, Brier, ECE, Elo, xG,
  de-vig, ensemble) attached where metrics appear.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

server/src/db/db.ts

@@ -177,6 +177,20 @@ export function healthRecord(source: string, ok: boolean, note?: string, openMs?
     });
 }
 
+/** Row counts for the /data page — everything the live layer has collected. */
+export function dbCounts(): Record<string, number> {
+  const c = (sql: string) => (db().prepare(sql).get() as { n: number }).n;
+  return {
+    oddsLines: c('SELECT COUNT(*) n FROM odds_history'),
+    oddsFixtures: c('SELECT COUNT(DISTINCT fixture_num) n FROM odds_history'),
+    frozenForecasts: c('SELECT COUNT(*) n FROM prediction_snapshots'),
+    enrichedMatches: c('SELECT COUNT(*) n FROM match_ext'),
+    mappedFixtures: c('SELECT COUNT(*) n FROM source_map'),
+    cachedResponses: c('SELECT COUNT(*) n FROM kv_cache'),
+    ingestEvents: c('SELECT COUNT(*) n FROM ingest_log'),
+  };
+}
+
 export function logIngest(source: string, job: string, ok: boolean, ms: number, note?: string): void {
   db().prepare('INSERT INTO ingest_log (source, job, ok, ms, note, at) VALUES (?, ?, ?, ?, ?, ?)')
     .run(source, job, ok ? 1 : 0, Math.round(ms), note ?? null, Date.now());

server/src/index.ts

@@ -10,7 +10,8 @@ import { startScheduler } from './ingest/scheduler';
 import { ModelEngine } from './model';
 import { buildPreview, buildTeamProfile } from './preview';
 import { buildScoreboard, snapshotCheck } from './scoreboard';
-import { db, healthAll, oddsFor, latestOddsAll } from './db/db';
+import { db, healthAll, oddsFor, latestOddsAll, dbCounts } from './db/db';
+import { loadStatic } from './preview';
 import { canonicalTeam } from '../../src/lib/teams';
 import type { MatchStatus, ServerMessage } from '../../src/lib/types';
 
@@ -61,6 +62,22 @@ export function buildServer() {
   // Bookmaker odds (benchmark for the Model-vs-Market scoreboard; not a model input)
   app.get('/api/odds', async () => ({ odds: latestOddsAll() }));
   app.get('/api/scoreboard', async () => buildScoreboard(state));
+  // The data lake, quantified — counters for the /data page.
+  app.get('/api/data/stats', async () => {
+    const safe = <T,>(fn: () => T): T | null => { try { return fn(); } catch { return null; } };
+    return {
+      lake: safe(() => loadStatic('lakestats.json')),
+      archive: safe(() => {
+        const r = loadStatic<{ matchesProcessed: number; asOf: string }>('ratings.json');
+        const h = loadStatic<Record<string, unknown>>('h2h.json');
+        return { results: r.matchesProcessed, asOf: r.asOf, h2hPairings: Object.keys(h).length };
+      }),
+      fingerprints: safe(() => Object.keys(loadStatic<{ teams: Record<string, unknown> }>('fingerprints.json').teams).length),
+      squadValues: safe(() => Object.keys(loadStatic<{ teams: Record<string, unknown> }>('squadvalues.json').teams).length),
+      db: dbCounts(),
+      sources: healthAll(),
+    };
+  });
   app.get('/api/odds/:num', async (req, reply) => {
     const num = Number((req.params as { num: string }).num);
     if (!Number.isFinite(num)) return reply.code(400).send({ error: 'bad num' });

server/src/preview.ts

@@ -17,7 +17,7 @@ interface H2HRecord {
   last: { date: string; home: string; away: string; hs: number; as: number }[];
 }
 
-function loadStatic<T>(name: string): T {
+export function loadStatic<T>(name: string): T {
   const candidates = [
     `${process.env.STATIC_DIR ?? ''}/data/${name}`,
     `${process.cwd()}/public/data/${name}`,