vyndr/scripts/prove-hit-factors.js

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

/**
 * prove-hit-factors — does the hit grade read tonight's game, or say "he's due"?
 *
 * Each factor is conditioned against the player's OWN base rate and put through
 * the two-part gate: it must MOVE the prediction and the moved prediction must
 * be MORE ACCURATE out-of-sample. Movement alone is THEATER — a grade that
 * swings on park and platoon looks like it read the matchup, and a user cannot
 * tell the difference from outside.
 *
 * The baseline is deliberately the honest null this order describes: the
 * player's base rate, i.e. "he's due" with no reading of tonight at all. A
 * factor earns its place only by beating that.
 *
 *   SUPABASE_URL=... node scripts/prove-hit-factors.js
 */

require('dotenv').config();
const { createClient } = require('@supabase/supabase-js');
const fg = require('../src/services/model/factorGate');
const sk = require('../src/services/model/skillProjection');
const tl = require('../src/services/model/testLedger');
const mlb = require('../src/services/adapters/mlbStatsAdapter');
const { knownNumber, knownRate } = require('../src/utils/known');
const { nameKey } = require('../src/utils/playerName');
const sd = require('../src/services/model/sprayDefense');

const SB_URL = process.env.SUPABASE_URL;
const SB_KEY = process.env.SUPABASE_SERVICE_ROLE_KEY || process.env.SUPABASE_SERVICE_KEY;
const PAGE = 1000;
const ARCHS = (process.env.HF_ARCHETYPES || 'BOMBER,GHOST,ALL').split(',');

async function page(sb, table, select, apply) {
  const out = [];
  for (let from = 0; ; from += PAGE) {
    const { data, error } = await apply(sb.from(table).select(select)).range(from, from + PAGE - 1);
    if (error) throw error;
    if (!data || data.length === 0) break;
    out.push(...data);
    if (data.length < PAGE) break;
  }
  return out;
}

/**
 * THE FACTORS. Each returns a MULTIPLIER on the base rate, or null when the
 * input is absent — an absent factor must leave the baseline untouched rather
 * than nudge it toward some default.
 */
const FACTORS = [
  {
    key: 'defense_by_direction',
    needs: ['spray_multiplier'],
    mechanism: 'CAUSALLY-CORRECT DEFENCE. Where the hitter puts the ball (pull/straight/oppo x ground/air) crossed with the OAA of the fielders actually standing in those zones, joined by handedness. Team-average failed the gate because it averages in five fielders who will never touch his ball.',
    apply: (r) => r.spray_multiplier,
  },
  {
    key: 'defense',
    needs: ['team_defense'],
    mechanism: 'A ball in play becomes a hit or an out partly by who is standing behind the pitcher. Should matter most where contact stays in the park.',
    // More outs converted above average -> fewer hits.
    apply: (r) => 1 - Math.max(-0.12, Math.min(0.12, r.team_defense / 250)),
  },
  {
    key: 'pitcher_contact_profile',
    needs: ['pitcher_hard_hit_allowed'],
    mechanism: 'A contact-allowing arm concedes better contact than a bat-misser; hit probability should follow the quality of contact he permits.',
    apply: (r) => 1 + Math.max(-0.15, Math.min(0.15, (r.pitcher_hard_hit_allowed - 0.389) * 1.2)),
  },
  {
    key: 'park_hits',
    needs: ['park_factor'],
    mechanism: 'Some parks turn outs into hits without producing runs — big outfields, high walls, deep gaps.',
    apply: (r) => r.park_factor,
    caveat: 'STAT_BASE maps hits -> run_base, so this is a RUN factor standing in for a HITS factor. A park that converts outs to hits without scoring is invisible to it.',
  },
  {
    key: 'platoon',
    needs: ['platoon_edge'],
    mechanism: 'Handedness advantage — a hitter facing the opposite hand sees the ball better and hits it harder.',
    apply: (r) => (r.platoon_edge > 0 ? 1.06 : 0.96),
  },
];

async function main() {
  if (!SB_URL || !SB_KEY) throw new Error('SUPABASE_URL / service key required');
  const sb = createClient(SB_URL, SB_KEY, { auth: { persistSession: false } });

  const statcast = await page(sb, 'statcast_aggregates', '*', (q) => q.eq('sport', 'mlb'));
  const batters = new Map(); const pitchersById = new Map();
  for (const r of statcast) {
    const prof = sk.fromStatcastRow(r);
    if (r.role === 'pitcher' && r.source_id != null) pitchersById.set(Number(r.source_id), prof);
    if (r.role === 'batter' && r.player_key) batters.set(r.player_key, prof);
  }
  const sprayRows = await page(sb, 'batter_spray', '*', (q) => q.eq('sport', 'mlb'));
  const sprayByKey = new Map();
  for (const r of sprayRows) {
    if (!r.player_key) continue;
    const prev = sprayByKey.get(r.player_key);
    if (!prev || String(r.as_of_date) > String(prev.as_of_date)) sprayByKey.set(r.player_key, r);
  }

  const defRows = await page(sb, 'team_defense', '*', (q) => q.eq('sport', 'mlb'));
  const defByTeam = new Map();
  for (const d of defRows) defByTeam.set(d.team, d);

  const snaps = await page(sb, 'model_snapshots', 'player_key, game_date, archetype, stat',
    (q) => q.eq('sport', 'mlb').eq('stat', 'hits').not('archetype', 'is', null));
  const archOf = new Map();
  for (const s of snaps) archOf.set(`${s.player_key}|${s.game_date}`, s.archetype);

  const led = await page(sb, 'ledger_entries',
    'id, player_key, player_name, line, side, outcome, game_date, p_win, quarantine_reason, env_park_base',
    (q) => q.eq('sport', 'mlb').is('user_id', null).eq('stat', 'hits')
      .in('outcome', ['hit', 'miss']).not('p_win', 'is', null));
  const clean = led.filter((r) => !(r.quarantine_reason || '').startsWith('nontakeable_book'));

  // Opponent faced, from each hitter's own game log.
  const names = new Map();
  for (const r of clean) if (!names.has(r.player_key)) names.set(r.player_key, r.player_name);
  const oppBy = new Map(); const startersBy = new Map();
  const dates = [...new Set(clean.map((r) => r.game_date))].sort();
  for (const d of dates) {
    try {
      const games = await mlb.getScheduleWithPitchers(d);
      for (const g of games) {
        if (!g.home || !g.away) continue;
        if (g.home.probablePitcher) startersBy.set(`${d}|OPP:${g.home.team}`, g.home.probablePitcher.id);
        if (g.away.probablePitcher) startersBy.set(`${d}|OPP:${g.away.team}`, g.away.probablePitcher.id);
      }
    } catch { /* absent slate */ }
  }
  for (const [key, name] of names) {
    try {
      const found = await mlb.searchPlayer(name);
      if (!found || !found.id) continue;
      const log = await mlb.getPlayerGameLog(found.id);
      for (const g of log || []) if (g && g.date && g.opponent) oppBy.set(`${key}|${String(g.date).slice(0, 10)}`, g.opponent);
    } catch { /* no log */ }
  }

  // Per-player base rate — the honest null: "he's due", no reading of tonight.
  const byPlayer = new Map();
  for (const r of clean) {
    const cur = byPlayer.get(r.player_key) || { n: 0, w: 0 };
    cur.n += 1; cur.w += r.outcome === 'hit' ? 1 : 0;
    byPlayer.set(r.player_key, cur);
  }

  const rows = [];
  for (const r of clean) {
    const bat = batters.get(r.player_key);
    const bp = byPlayer.get(r.player_key);
    if (!bp || bp.n < 3) continue;
    // Leave-one-out so a row never contributes to its own baseline.
    const baseline = (bp.w - (r.outcome === 'hit' ? 1 : 0)) / (bp.n - 1);
    const faced = oppBy.get(`${r.player_key}|${r.game_date}`) || null;
    const nick = faced ? String(faced).split(' ').pop() : null;
    const def = faced ? (defByTeam.get(faced) || defByTeam.get(nick)) : null;
    const starterId = faced ? startersBy.get(`${r.game_date}|OPP:${faced}`) : null;
    const pit = starterId != null ? pitchersById.get(Number(starterId)) : null;
    rows.push({
      id: r.id,
      archetype: archOf.get(`${r.player_key}|${r.game_date}`) || null,
      won: r.outcome === 'hit' ? 1 : 0,
      baseline,
      team_defense: def ? knownNumber(def.oaa_sum) : null,
      pitcher_hard_hit_allowed: pit ? knownRate(pit.hard_hit_pct) : null,
      park_factor: knownNumber(r.env_park_base),
      spray_multiplier: (() => {
        const sp = sprayByKey.get(r.player_key);
        const posOaa = def && def.position_oaa ? def.position_oaa : null;
        if (!sp || !posOaa || !bat || !bat.bats) return null;
        const out = sd.sprayDefenseMultiplier({ spray: sp, bats: bat.bats, positionOaa: posOaa });
        return out ? out.multiplier : null;
      })(),
      platoon_edge: (bat && pit && bat.bats && pit.throws)
        ? (String(bat.bats)[0] !== String(pit.throws)[0] ? 1 : -1) : null,
    });
  }

  // Cumulative Bonferroni across the programme lifetime.
  const store = tl.supabaseStore(sb);
  const mc = await tl.recordAndCount(store, FACTORS.flatMap((f) =>
    ARCHS.map((a) => ({ sport: 'mlb', stat: 'hits', archetype: a === 'ALL' ? null : a, interaction: `factor:${f.key}`, target: 'outcome' }))));

  const results = [];
  for (const arch of ARCHS) {
    const slot = arch === 'ALL' ? rows : rows.filter((r) => String(r.archetype || '').toUpperCase() === arch);
    for (const f of FACTORS) {
      const usable = slot.filter((r) => f.needs.every((k) => knownNumber(r[k]) !== null));
      const paired = usable.map((r) => {
        const mult = f.apply(r);
        const cond = mult === null ? null : Math.min(0.99, Math.max(0.01, r.baseline * mult));
        return { baseline: r.baseline, conditioned: cond, won: r.won };
      });
      const v = fg.adjudicate(paired, {
        factor: f.key, archetype: arch, stat: 'hits',
        cumulativeTests: mc.cumulative_tests,      // native cumulative correction
      });
      results.push({
        archetype: arch, factor: f.key, n: v.movement.n,
        mean_abs_shift: v.movement.mean_abs_shift,
        brier_delta: v.improvement ? v.improvement.brier_delta : null,
        ci: v.improvement ? v.improvement.ci : null,
        ci_level: v.improvement ? v.improvement.ci_level : null,
        verdict: v.verdict,
        reason: v.reason,
        ...(f.caveat ? { input_caveat: f.caveat } : {}),
      });
    }
  }

  console.log(JSON.stringify({
    baseline: "each row scored against the player's OWN leave-one-out base rate — the honest 'he's due' null",
    total_rows: rows.length,
    cumulative_bonferroni: mc,
    gate: 'a factor must MOVE the prediction AND improve out-of-sample Brier; movement alone is THEATER',
    results,
    proven: results.filter((r) => r.verdict === 'PROVES'),
    theater: results.filter((r) => r.verdict === 'THEATER'),
  }, null, 2));
  process.exit(0);
}

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