vyndr/scripts/ingest-game-sequences.js

#!/usr/bin/env node
'use strict';

/**
 * ingest-game-sequences — the raw material for the reliever chain.
 *
 * Every link in this chain needs something the ledger does not carry: when the
 * starter actually left, and which arm actually faced each plate appearance.
 * Both are free from statsapi (playByPlay + boxscore), on the same host we
 * already use for game logs and schedules.
 *
 * Caches to disk so Link 1, 2 and 3 all read one fetch rather than three.
 *
 *   node scripts/ingest-game-sequences.js            # default window
 *   SEQ_FROM=2026-06-01 SEQ_TO=2026-08-04 node scripts/ingest-game-sequences.js
 */

const fs = require('fs');
const path = require('path');
const axios = require('axios');

const FROM = process.env.SEQ_FROM || '2026-06-15';
const TO = process.env.SEQ_TO || '2026-08-04';
const OUT = process.env.SEQ_OUT || path.join(process.cwd(), '.seq-cache', 'sequences.json');
const CONCURRENCY = 6;

const get = async (url) => (await axios.get(url, { timeout: 45_000 })).data;

/** Innings pitched come as '5.2' meaning five and TWO THIRDS — parseFloat is wrong. */
function ipToOuts(ip) {
  if (ip == null) return null;
  const [whole, frac] = String(ip).split('.');
  const w = Number(whole); const f = Number(frac || 0);
  if (!Number.isFinite(w)) return null;
  return w * 3 + (Number.isFinite(f) ? f : 0);
}

function datesBetween(from, to) {
  const out = [];
  const d = new Date(`${from}T12:00:00Z`);
  const end = new Date(`${to}T12:00:00Z`);
  while (d <= end) { out.push(d.toISOString().slice(0, 10)); d.setUTCDate(d.getUTCDate() + 1); }
  return out;
}

async function pool(items, fn, n = CONCURRENCY) {
  const out = []; let i = 0;
  await Promise.all(Array.from({ length: n }, async () => {
    while (i < items.length) {
      const idx = i; i += 1;
      try { out[idx] = await fn(items[idx]); } catch { out[idx] = null; }
    }
  }));
  return out.filter(Boolean);
}

async function loadGame(g) {
  const pk = g.gamePk;
  const [box, pbp] = await Promise.all([
    get(`https://statsapi.mlb.com/api/v1/game/${pk}/boxscore`),
    get(`https://statsapi.mlb.com/api/v1/game/${pk}/playByPlay`),
  ]);

  const sides = {};
  for (const side of ['home', 'away']) {
    const t = box.teams[side];
    if (!t) return null;
    const arms = (t.pitchers || []).map((id) => {
      const pl = t.players[`ID${id}`];
      const s = pl && pl.stats && pl.stats.pitching;
      if (!s) return null;
      return {
        id: Number(id),
        name: pl.person && pl.person.fullName,
        started: Number(s.gamesStarted || 0) === 1,
        bf: s.battersFaced == null ? null : Number(s.battersFaced),
        outs: ipToOuts(s.inningsPitched),
        pitches: s.pitchesThrown == null ? null : Number(s.pitchesThrown),
      };
    }).filter(Boolean);
    sides[side] = { team: t.team && t.team.name, abbr: t.team && t.team.abbreviation, arms };
  }

  // Every plate appearance in order, with who threw it.
  const pas = [];
  for (const p of pbp.allPlays || []) {
    const m = p.matchup || {}; const a = p.about || {};
    if (!m.batter || !m.pitcher) continue;
    pas.push({
      batter: Number(m.batter.id),
      batter_name: m.batter.fullName,
      pitcher: Number(m.pitcher.id),
      bats: m.batSide && m.batSide.code,
      throws: m.pitchHand && m.pitchHand.code,
      inning: a.inning,
      half: a.halfInning,
      idx: a.atBatIndex,
      event: p.result && p.result.eventType,
    });
  }
  if (!pas.length) return null;

  return {
    gamePk: pk,
    date: g.officialDate || (g.gameDate || '').slice(0, 10),
    venue_id: g.venue && g.venue.id,
    home: sides.home, away: sides.away,
    pas,
  };
}

async function main() {
  const dates = datesBetween(FROM, TO);
  console.error(`[seq] ${dates.length} dates ${FROM} -> ${TO}`);

  const allGames = [];
  for (const d of dates) {
    try {
      const s = await get(`https://statsapi.mlb.com/api/v1/schedule?sportId=1&date=${d}&hydrate=venue`);
      for (const day of s.dates || []) {
        for (const g of day.games || []) {
          if (String(g.status && g.status.detailedState) === 'Final') allGames.push(g);
        }
      }
    } catch { /* absent day */ }
  }
  console.error(`[seq] ${allGames.length} final games; fetching sequences`);

  const games = await pool(allGames, loadGame);
  fs.mkdirSync(path.dirname(OUT), { recursive: true });
  fs.writeFileSync(OUT, JSON.stringify({ from: FROM, to: TO, games }));

  const starters = games.reduce((s, g) =>
    s + ['home', 'away'].filter((k) => g[k].arms.some((a) => a.started)).length, 0);
  console.log(JSON.stringify({
    dates: dates.length,
    final_games: allGames.length,
    games_loaded: games.length,
    starter_games: starters,
    plate_appearances: games.reduce((s, g) => s + g.pas.length, 0),
    cache: OUT,
  }, null, 2));
  process.exit(0);
}

main().catch((e) => { console.error(e); process.exit(1); });