/**
 * Consistency score — how predictable is this player for this stat?
 *
 * TWO scale-appropriate statistics, split at the mean where each is valid:
 *
 *   HIGH-MEAN (mean ≥ 4, e.g. NBA points, pitcher Ks):
 *       cv = stddev / mean   (coefficient of variation)
 *   LOW-MEAN  (mean < 4, e.g. MLB hits / TB / HR / RBI):
 *       iod = variance / mean   (index of dispersion; Poisson baseline = 1)
 *
 * WHY THE SPLIT (Session — consistency classifier fix): CV is scale-DEPENDENT
 * on count data — for a Poisson-ish stat cv ≈ 1/sqrt(mean), so EVERY stat with
 * mean < 4 blows past the CV boom_bust cutoff no matter how the player actually
 * behaves. The A/D investigation found this was eating a real +1.0 signal:
 * steady low-mean hitters (Kwan, Alonso hits) were blanket-classified and
 * their earned consistency factor never fired. The index of dispersion is the
 * correct statistic for counts — UNBIASED, centered at 1.0 for a random
 * (Poisson) process regardless of the mean — so it recovers that signal
 * without systematically down- or up-grading anyone. This is a bug CORRECTION,
 * not a threshold loosening: the CV thresholds and the engine1 ±1.0 delta are
 * unchanged; only the low-mean branch that used to return 'unknown' now
 * classifies on merit.
 *
 * The consistency score modifies the grade: an "elite"/"reliable" player adds
 * +1.0 (engine1), a "boom_bust" player subtracts −1.0; "volatile"/"unknown"
 * add nothing.
 */

const gameLogService = require('./gameLogService');

function statFromGameLog(row, statType) {
  if (!row) return null;
  switch (statType) {
    case 'pts_reb_ast':
      return (Number(row.points) || 0) + (Number(row.rebounds) || 0) + (Number(row.assists) || 0);
    case 'pts_reb':
      return (Number(row.points) || 0) + (Number(row.rebounds) || 0);
    case 'pts_ast':
      return (Number(row.points) || 0) + (Number(row.assists) || 0);
    case 'reb_ast':
      return (Number(row.rebounds) || 0) + (Number(row.assists) || 0);
    case 'stl_blk':
      return (Number(row.steals) || 0) + (Number(row.blocks) || 0);
    default: {
      const v = Number(row[statType]);
      return Number.isFinite(v) ? v : null;
    }
  }
}

function classify(cv) {
  if (cv < 0.15) return { consistency: 'elite', score: 1.0 };
  if (cv < 0.30) return { consistency: 'reliable', score: 0.7 };
  if (cv < 0.50) return { consistency: 'volatile', score: 0.4 };
  return { consistency: 'boom_bust', score: 0.1 };
}

/**
 * INDEX-OF-DISPERSION classifier for LOW-MEAN COUNT stats. iod = variance/mean;
 * a random (Poisson) process sits at 1.0 REGARDLESS of the mean, so the bands
 * are anchored on 1.0, not on an NBA-calibrated absolute like CV's.
 *
 * The bands are deliberately ASYMMETRIC around 1.0: real count stats are
 * naturally mildly over-dispersed (the per-game rate itself varies with
 * matchup / park), so "meaningfully steadier than random" (iod < 0.85) is the
 * signal that earns +1.0, and only a clear spike (iod > 1.30) earns −1.0. The
 * wide neutral band 0.85–1.30 abstains — most hitters are Poisson-ish and get
 * NO factor, which is the honest answer, not a limitation.
 *
 *   Validated on real 10-game logs: Kwan hits 0.67 → reliable, Alonso hits
 *   0.78 → reliable (the recovery), Alonso TB 2.57 / Henderson hits 1.33 →
 *   boom_bust (spikes), HR at mean 0.1 → 1.0 → volatile (rare-event Poisson).
 */
const IOD_ELITE_MAX = Number(process.env.CONSISTENCY_IOD_ELITE || 0.60);
const IOD_RELIABLE_MAX = Number(process.env.CONSISTENCY_IOD_RELIABLE || 0.85);
const IOD_BOOMBUST_MIN = Number(process.env.CONSISTENCY_IOD_BOOMBUST || 1.30);

function classifyIoD(iod) {
  if (iod < IOD_ELITE_MAX) return { consistency: 'elite', score: 1.0 };
  if (iod < IOD_RELIABLE_MAX) return { consistency: 'reliable', score: 0.7 };
  if (iod <= IOD_BOOMBUST_MIN) return { consistency: 'volatile', score: 0.4 };
  return { consistency: 'boom_bust', score: 0.1 };
}

/**
 * IoD is itself noisy at tiny samples (its sampling sd ≈ sqrt(2/(n−1)) for a
 * Poisson process). Below this many games we abstain ('unknown') rather than
 * trade a scale bug for a small-sample bug — the same refusal discipline the
 * old CV floor used. 8 games + a clear departure from 1.0 is the noise buffer.
 */
const MIN_GAMES_FOR_IOD = Number(process.env.CONSISTENCY_MIN_GAMES_IOD || 8);

/**
 * Session 63 — the CV thresholds above are NBA-calibrated (points ~20/game,
 * cv ~0.2-0.4). They are MEANINGLESS for a low-count stat.
 *
 * For a Poisson-ish counting stat, cv ≈ 1/sqrt(mean). So mean < 4 forces
 * cv > 0.5 — i.e. EVERY such stat classifies 'boom_bust' no matter how the
 * player actually behaves. Verified against real logs: Alonso hits
 * [0,0,0,1,2,1,0,1,1,0] → mean 0.60, cv 1.17 → boom_bust; Henderson
 * [1,0,0,3,1,1,0,0,1,0] → mean 0.70, cv 1.36 → boom_bust.
 *
 * When the estimator path was revived, this would have stamped a blanket
 * -1.0 on nearly every MLB prop — a systematic downgrade masquerading as a
 * signal. That is why the CV floor returned 'unknown' below mean 4.
 *
 * RESOLVED (consistency classifier fix): the low-mean branch no longer
 * abstains blindly — it now classifies with the index of dispersion
 * (`classifyIoD`), the scale-free statistic for counts. The floor below is
 * kept as the CV/IoD SPLIT POINT (which statistic to use), not as a blanket
 * refusal: mean ≥ 4 uses CV, mean < 4 uses IoD (games-floored).
 */
const MIN_MEAN_FOR_CV = Number(process.env.CONSISTENCY_MIN_MEAN || 4);

function cvIsMeaningful(mean) {
  return Number.isFinite(mean) && Math.abs(mean) >= MIN_MEAN_FOR_CV;
}

function statsFor(values) {
  const clean = values.filter((v) => Number.isFinite(v));
  if (clean.length < 2) return null;
  const mean = clean.reduce((a, b) => a + b, 0) / clean.length;
  if (mean === 0) return null;
  const variance = clean.reduce((s, v) => s + (v - mean) ** 2, 0) / (clean.length - 1);
  const stddev = Math.sqrt(variance);
  return {
    mean,
    stddev,
    variance,
    cv: stddev / Math.abs(mean),
    iod: variance / Math.abs(mean), // index of dispersion (Poisson baseline 1.0)
    games: clean.length,
  };
}

async function getConsistency(input = {}) {
  const { playerName, sport, statType, gameLogs: providedLogs } = input;
  const logs = providedLogs || await gameLogService.getGameLogs(playerName, sport, 20);
  if (!logs || logs.length < 2) {
    return { consistency: 'unknown', score: null, games: logs?.length ?? 0 };
  }
  const values = logs.map((row) => statFromGameLog(row, statType)).filter((v) => v != null);
  const s = statsFor(values);
  if (!s) return { consistency: 'unknown', score: null, games: values.length };
  // LOW-MEAN regime: CV is scale-broken here, so classify with the index of
  // dispersion (scale-appropriate for counts). Abstain if the sample is too
  // thin for IoD — absent beats a small-sample guess.
  if (!cvIsMeaningful(s.mean)) {
    if (s.games < MIN_GAMES_FOR_IOD) {
      return { ...s, consistency: 'unknown', score: null, reason: 'low_mean_thin_sample', method: 'iod' };
    }
    return { ...s, ...classifyIoD(s.iod), method: 'iod' };
  }
  // HIGH-MEAN regime: CV with the NBA-calibrated thresholds (unchanged).
  return { ...s, ...classify(s.cv), method: 'cv' };
}

module.exports = {
  getConsistency, classify, classifyIoD, statsFor, statFromGameLog, cvIsMeaningful,
  MIN_MEAN_FOR_CV, MIN_GAMES_FOR_IOD, IOD_ELITE_MAX, IOD_RELIABLE_MAX, IOD_BOOMBUST_MIN,
};