vyndr/scripts/measure-book-spread.js

'use strict';

/**
 * measure-book-spread — Book Comparison order, Phase 2 (GATES THE CROWN).
 *
 * Reads the snapshot-locked `bookprices:{sport}` store (Phase 1) — falling back
 * to the transient `odds:{sport}:{utcDate}` cache — and reports, PER SPORT, the
 * best-vs-worst PRICE spread among books posting the SAME line for the same
 * side:
 *   - median + distribution + tail, in American cents AND implied-prob points
 *   - how often the spread is exactly zero
 *   - book-count histogram per prop
 *   - pinnacle presence (captured, not built on — this order)
 *
 * PRE-REGISTERED CROWN THRESHOLD (do NOT lower it to make the crown appear):
 *   the crown ships for a sport ONLY if median same-line spread
 *   >= 8 American cents OR >= 2.0 implied-probability points.
 *
 * Never pools sports. Reports n + effective sample on every figure.
 *
 * Redis runs degraded locally (no live data) → this exits 0 cleanly rather than
 * hanging on a reconnect timer (the verify-grade-range.js precedent). Run it
 * post-deploy against prod Redis, after inducing a snapshot.
 *
 *   node scripts/measure-book-spread.js [sport ...]   (default: mlb wnba nba)
 */

const SPORTS = process.argv.slice(2).filter(Boolean);
const DEFAULT_SPORTS = ['mlb', 'wnba', 'nba', 'soccer'];
const CROWN_CENTS = 8;
const CROWN_PROB_PTS = 2.0;

/** American → implied probability (0..1). Includes the vig. */
function impliedProb(a) {
  if (a == null || !Number.isFinite(Number(a)) || Number(a) === 0) return null;
  const n = Number(a);
  return n > 0 ? 100 / (n + 100) : Math.abs(n) / (Math.abs(n) + 100);
}

function median(xs) {
  if (!xs.length) return null;
  const s = [...xs].sort((a, b) => a - b);
  const m = Math.floor(s.length / 2);
  return s.length % 2 ? s[m] : (s[m - 1] + s[m]) / 2;
}
function pct(xs, p) {
  if (!xs.length) return null;
  const s = [...xs].sort((a, b) => a - b);
  return s[Math.min(s.length - 1, Math.floor((p / 100) * s.length))];
}

function entriesFrom(store, oddsCache) {
  // Phase-1 store shape: { props: [{ player, stat_type, books:[{book,line,over_odds,under_odds}] }] }
  if (store && Array.isArray(store.props)) return store.props;
  // Fallback: group the flat odds cache the same way.
  const flat = oddsCache && Array.isArray(oddsCache.props) ? oddsCache.props : [];
  const by = new Map();
  for (const p of flat) {
    if (!p || !p.player || !p.stat_type || p.line == null || !p.book) continue;
    const k = `${p.player}|${p.stat_type}`;
    if (!by.has(k)) by.set(k, { player: p.player, stat_type: p.stat_type, books: [] });
    by.get(k).books.push({ book: p.book, line: p.line, over_odds: p.over_odds, under_odds: p.under_odds });
  }
  return [...by.values()];
}

function measureSport(entries) {
  const centsSpreads = [];
  const probSpreads = [];
  const bookCountHist = {};
  let sharedLineProps = 0;
  let zeroSpread = 0;
  let pinnacleRows = 0;
  let totalProps = 0;

  for (const e of entries) {
    totalProps += 1;
    const books = e.books || [];
    if (books.some((b) => b.book === 'pinnacle')) pinnacleRows += 1;
    const nBooks = new Set(books.map((b) => b.book)).size;
    bookCountHist[nBooks] = (bookCountHist[nBooks] || 0) + 1;

    // Group this prop's book rows by line; a shared line = ≥2 books at one line.
    const byLine = {};
    for (const b of books) {
      const L = String(b.line);
      (byLine[L] = byLine[L] || []).push(b);
    }
    let contributed = false;
    for (const rows of Object.values(byLine)) {
      const distinctBooks = new Set(rows.map((r) => r.book));
      if (distinctBooks.size < 2) continue;
      for (const side of ['over_odds', 'under_odds']) {
        const prices = rows.map((r) => r[side]).filter((v) => v != null && Number.isFinite(Number(v))).map(Number);
        if (prices.length < 2) continue;
        // Best price for a bettor = highest implied payout = LOWEST implied prob.
        const probs = prices.map(impliedProb).filter((v) => v != null);
        if (probs.length < 2) continue;
        const probSpread = (Math.max(...probs) - Math.min(...probs)) * 100; // points
        probSpreads.push(+probSpread.toFixed(3));
        // American cents: meaningful when same-sign; use nominal max-min.
        const centSpread = Math.max(...prices) - Math.min(...prices);
        centsSpreads.push(Math.abs(centSpread));
        if (probSpread < 1e-9) zeroSpread += 1;
        contributed = true;
      }
    }
    if (contributed) sharedLineProps += 1;
  }

  const nEff = probSpreads.length; // side-level shared-line comparisons
  const verdictCents = median(centsSpreads);
  const verdictProb = median(probSpreads);
  const crownShips = nEff > 0 && ((verdictCents != null && verdictCents >= CROWN_CENTS) || (verdictProb != null && verdictProb >= CROWN_PROB_PTS));

  return {
    totalProps,
    sharedLineProps,
    nEff,
    zeroSpread,
    pctZero: nEff ? +(100 * zeroSpread / nEff).toFixed(1) : null,
    bookCountHist,
    pinnacleRows,
    cents: { median: verdictCents, p75: pct(centsSpreads, 75), p90: pct(centsSpreads, 90), max: centsSpreads.length ? Math.max(...centsSpreads) : null },
    prob: { median: verdictProb, p75: pct(probSpreads, 75), p90: pct(probSpreads, 90), max: probSpreads.length ? Math.max(...probSpreads) : null },
    crownShips,
  };
}

async function main() {
  let cacheGet;
  try {
    ({ cacheGet } = require('../src/utils/redis'));
  } catch (e) {
    console.log('[measure] redis util unavailable — nothing to measure.');
    process.exit(0);
  }
  const sports = SPORTS.length ? SPORTS : DEFAULT_SPORTS;
  const utcDate = new Date().toISOString().split('T')[0];
  const report = {};
  for (const sp of sports) {
    let store = null; let oddsCache = null;
    try { store = await cacheGet(`bookprices:${sp}`); } catch { /* degraded */ }
    if (!store) { try { oddsCache = (await cacheGet(`odds:${sp}:${utcDate}`)) || (await cacheGet(`odds:${sp}`)); } catch { /* degraded */ } }
    const entries = entriesFrom(store, oddsCache);
    report[sp] = { source: store ? 'bookprices' : (oddsCache ? 'odds-cache' : 'none'), ...measureSport(entries) };
  }

  console.log('\n=== BOOK-PRICE SPREAD (Phase 2) — never pooled ===');
  for (const sp of sports) {
    const r = report[sp];
    console.log(`\n--- ${sp.toUpperCase()} (source: ${r.source}) ---`);
    if (r.source === 'none' || r.totalProps === 0) { console.log('  no captured data (run post-deploy after a snapshot)'); continue; }
    console.log(`  props: ${r.totalProps} | with ≥2 books at a shared line: ${r.sharedLineProps} | side-level comparisons n=${r.nEff}`);
    console.log(`  book-count histogram: ${JSON.stringify(r.bookCountHist)}`);
    console.log(`  pinnacle present on: ${r.pinnacleRows} props`);
    console.log(`  spread exactly zero: ${r.zeroSpread}/${r.nEff} (${r.pctZero}%)`);
    console.log(`  American cents  — median ${r.cents.median} | p75 ${r.cents.p75} | p90 ${r.cents.p90} | max ${r.cents.max}`);
    console.log(`  implied-prob pt — median ${r.prob.median} | p75 ${r.prob.p75} | p90 ${r.prob.p90} | max ${r.prob.max}`);
    console.log(`  CROWN THRESHOLD (median ≥${CROWN_CENTS}c OR ≥${CROWN_PROB_PTS}pp): ${r.crownShips ? 'MET → crown MAY ship' : 'NOT met → crown does NOT ship'}`);
  }
  console.log('\n(JSON) ' + JSON.stringify(report));
  process.exit(0);
}

main().catch((e) => { console.error('[measure] failed:', e.message); process.exit(0); });