PythagorasGoal/Old/scripts/games/grid_arena.py

"""
Arena del gioco GRID TRADERS (sessione 3): 100 agenti ciechi configurano una
griglia di trading secondo STRATEGIA_GRIGLIA.md su due serie anonime
(A=BTC, B=ETH, mai rivelate; gli agenti le vedono come X/Y). Torneo standard:
3 finestre TRAIN/VALID/TEST, 90 epoche di hill-climb sul TRAIN, ogni 10 epoche
l'orchestratore blocca il 10% meno profittevole in VALID, fino a 10 superstiti.
TEST = OOS puro mai toccato dall'ottimizzazione.

  uv run python -m scripts.games.grid_arena                       # 100 random (smoke)
  GAME_SPECS_DIR=... GAME_OUT=... uv run python -m scripts.games.grid_arena --from-specs
"""
from __future__ import annotations

import json
import os
import random
import sys
from pathlib import Path

from scripts.games.engine import load_anon, splits3
from scripts.games import grid_engine
from scripts.games.grid_engine import evaluate, max_levels

OUT = Path("data/games")
OUT.mkdir(parents=True, exist_ok=True)

# Spazio parametri (min, max, tipo). range_*/sl_buf/tp_buf in FRAZIONE.
PSPACE = dict(
    range_down=(0.02, 0.30, "f"),
    range_up=(0.02, 0.30, "f"),
    levels=(4, 30, "i"),
    sl_buf=(0.01, 0.15, "f"),
    tp_buf=(0.01, 0.15, "f"),
    max_bars=(48, 3000, "i"),
)
SERIES = ["A", "B"]
TIMEFRAMES = ["15m", "30m", "1h", "2h", "4h", "1d"]   # no 5m (costo computazionale)


def _rand(rng, lo, hi, typ):
    return int(rng.randint(int(lo), int(hi))) if typ == "i" else round(rng.uniform(lo, hi), 4)


def random_spec(rng):
    p = {k: _rand(rng, *v) for k, v in PSPACE.items()}
    return {"series": rng.choice(SERIES), "tf": rng.choice(TIMEFRAMES), "params": p}


def _normalize(spec):
    """Clampa la spec nello spazio valido e APPLICA il vincolo break-even (§4):
    se il passo e' troppo fitto riduce GRID_LEVELS (come da spec: 'vanno ridotti
    i GRID_LEVELS o allargato il range')."""
    out = {"series": spec.get("series") if spec.get("series") in SERIES else "A",
           "tf": spec.get("tf") if spec.get("tf") in TIMEFRAMES else "1h",
           "params": {}}
    src = spec.get("params", spec)
    for k, (lo, hi, typ) in PSPACE.items():
        v = src.get(k, (lo + hi) / 2)
        try:
            v = float(v)
        except Exception:
            v = (lo + hi) / 2
        v = max(lo, min(hi, v))
        out["params"][k] = int(round(v)) if typ == "i" else round(v, 4)
    p = out["params"]
    lmax = max_levels(p["range_down"], p["range_up"])
    if lmax >= 2:
        p["levels"] = min(p["levels"], lmax)
    return out


def mutate(spec, rng, strength=0.25):
    """Hill-climb: perturba 1-2 parametri; raramente cambia serie.
    Il timeframe e' l'identita' dell'agente -> non muta."""
    s = json.loads(json.dumps(spec))
    for k in rng.sample(list(PSPACE), k=rng.randint(1, 2)):
        lo, hi, typ = PSPACE[k]
        span = (hi - lo) * strength
        nv = max(lo, min(hi, s["params"][k] + rng.uniform(-span, span)))
        s["params"][k] = int(round(nv)) if typ == "i" else round(nv, 4)
    if rng.random() < 0.05:
        s["series"] = rng.choice(SERIES)
    return s


class Agent:
    def __init__(self, aid, spec, brief=""):
        self.id = aid
        self.spec = _normalize(spec)
        self.brief = brief
        self.train_fit = -1e9
        self.valid_fit = -1e9
        self.metrics = {}
        self.vmetrics = {}
        self.alive = True
        self.culled_epoch = None

    @property
    def tf(self):
        return self.spec["tf"]

    def score(self, datasets, sm):
        data = datasets[self.tf]
        tr, va, _ = sm[self.tf]
        self.metrics = evaluate(data, self.spec, tr)
        self.vmetrics = evaluate(data, self.spec, va)
        self.train_fit = self.metrics["fitness"]
        self.valid_fit = self.vmetrics["fitness"]


def run_tournament(specs, briefs=None, seed=2026, epochs=90, cull_every=10,
                   cull_n=10, out_name="grid_result.json", log=print):
    rng = random.Random(seed)
    used_tfs = sorted({_normalize(s)["tf"] for s in specs})
    datasets = {tf: load_anon(tf) for tf in used_tfs}
    sm = {tf: splits3(datasets[tf], 0.60, 0.20) for tf in used_tfs}
    briefs = briefs or [""] * len(specs)
    agents = [Agent(i, s, briefs[i] if i < len(briefs) else "")
              for i, s in enumerate(specs)]
    for a in agents:
        a.score(datasets, sm)
    alive = lambda: [a for a in agents if a.alive]
    log(f"[epoch 0] {len(alive())} agenti | best VALID "
        f"{max(a.valid_fit for a in agents):.1f}")
    history = []
    for ep in range(1, epochs + 1):
        for a in alive():
            cand = _normalize(mutate(a.spec, rng))
            data = datasets[a.tf]
            tr, va, _ = sm[a.tf]
            m = evaluate(data, cand, tr)
            if m["fitness"] > a.train_fit:
                a.spec, a.metrics, a.train_fit = cand, m, m["fitness"]
                a.vmetrics = evaluate(data, a.spec, va)
                a.valid_fit = a.vmetrics["fitness"]
        if ep % cull_every == 0:
            av = sorted(alive(), key=lambda a: a.valid_fit)
            k = cull_n if len(av) - cull_n >= 10 else max(0, len(av) - 10)
            for a in av[:k]:
                a.alive = False
                a.culled_epoch = ep
            log(f"[epoch {ep:2d}] cull {k:2d} -> {len(alive()):3d} vivi | "
                f"best VALID {max(a.valid_fit for a in alive()):.1f} | "
                f"worst-alive {min(a.valid_fit for a in alive()):.1f}")
        history.append({"epoch": ep, "alive": len(alive()),
                        "best_valid": max(a.valid_fit for a in alive())})
    survivors = sorted(alive(), key=lambda a: a.valid_fit, reverse=True)
    results = []
    for rank, a in enumerate(survivors, 1):
        data = datasets[a.tf]
        _, _, te = sm[a.tf]
        results.append({"rank": rank, "agent": a.id, "spec": a.spec,
                        "brief": a.brief, "tf": a.tf,
                        "train": a.metrics, "valid": a.vmetrics,
                        "test": evaluate(data, a.spec, te),
                        "full": evaluate(data, a.spec, None)})
    payload = {"n_agents": len(specs), "epochs": epochs,
               "survivors": len(survivors), "results": results,
               "history": history, "game": "grid",
               "rule": "STRATEGIA_GRIGLIA.md",
               "reveal": {"A": "BTC", "B": "ETH"}}
    (OUT / out_name).write_text(json.dumps(payload, indent=2))
    return payload


def leaderboard(payload, top=10, log=print):
    log("\n========== CLASSIFICA GRID TRADERS (top %d) ==========" % top)
    log("VALID = finestra del giudice | TEST = OOS puro (mai ottimizzato)")
    log(f"{'#':>2} {'ag':>4} {'tf':>4} {'ser':>3} {'rng-/+':>11} {'lvl':>3} "
        f"{'sl/tp buf':>11} {'mbars':>5} {'TEpnl%':>7} {'TEwin':>5} "
        f"{'TEtpm':>6} {'TEsh':>5} {'VApnl%':>7}")
    for r in payload["results"][:top]:
        sp = r["spec"]; p = sp["params"]; te = r["test"]; va = r["valid"]
        log(f"{r['rank']:>2} {r['agent']:>4} {sp['tf']:>4} {sp['series']:>3} "
            f"{p['range_down']*100:>4.1f}/{p['range_up']*100:>4.1f}% {p['levels']:>3} "
            f"{p['sl_buf']*100:>4.1f}/{p['tp_buf']*100:>4.1f}% {p['max_bars']:>5} "
            f"{te['pnl_pct']:>7.0f} {te['win_rate']*100:>4.0f}% {te['tpm']:>6.1f} "
            f"{te['sharpe']:>5.1f} {va['pnl_pct']:>7.0f}")


def load_specs(specs_dir, n=100):
    """Carica le spec proposte dagli agenti ciechi (X->A, Y->B, pct->frazione)."""
    rng = random.Random(7)
    specs, briefs = [], []
    for i in range(n):
        f = Path(specs_dir) / f"agent_{i}.json"
        spec = None
        if f.exists():
            try:
                raw = json.loads(f.read_text())
                src = raw.get("params", raw)
                params = {
                    "range_down": float(src.get("range_down_pct", src.get("range_down", 10))) ,
                    "range_up": float(src.get("range_up_pct", src.get("range_up", 10))),
                    "levels": src.get("grid_levels", src.get("levels", 10)),
                    "sl_buf": float(src.get("sl_buf_pct", src.get("sl_buf", 5))),
                    "tp_buf": float(src.get("tp_buf_pct", src.get("tp_buf", 5))),
                    "max_bars": src.get("max_bars", 500),
                }
                # gli agenti parlano in percentuale -> frazione
                for k in ("range_down", "range_up", "sl_buf", "tp_buf"):
                    if params[k] > 1.0:
                        params[k] = params[k] / 100.0
                spec = _normalize({
                    "series": {"X": "A", "Y": "B"}.get(raw.get("series"), raw.get("series")),
                    "tf": raw.get("tf", "1h"), "params": params})
                briefs.append(str(raw.get("hypothesis", ""))[:300])
            except Exception:
                spec = None
        if spec is None:
            spec = random_spec(rng)
            briefs.append("(spec mancante -> sostituto casuale)")
        specs.append(spec)
    n_real = sum(1 for b in briefs if "mancante" not in b)
    print(f"caricati {n_real}/{n} spec da agenti reali, {n - n_real} sostituiti casuali")
    return specs, briefs


def main():
    slip = float(os.environ.get("GAME_SLIP", "0.0"))
    grid_engine.set_slippage(slip)
    if slip > 0:
        print(f"SLIPPAGE attivo: {slip*100:.3f}%/lato")
    epochs = int(os.environ.get("GAME_EPOCHS", "90"))
    if "--from-specs" in sys.argv:
        sd = os.environ.get("GAME_SPECS_DIR", "data/games/specs_grid")
        on = os.environ.get("GAME_OUT", "grid_result.json")
        specs, briefs = load_specs(sd)
        payload = run_tournament(specs, briefs=briefs, epochs=epochs, out_name=on)
    else:
        rng = random.Random(42)
        payload = run_tournament([random_spec(rng) for _ in range(100)],
                                 seed=42, epochs=epochs)
    leaderboard(payload)
    rev = payload["reveal"]
    w = payload["results"][0]
    sp = w["spec"]; p = sp["params"]
    print(f"\n>>> RIVELAZIONE: Serie X = {rev['A']}, Serie Y = {rev['B']}. "
          f"Gli agenti non lo sapevano. <<<")
    print(f"\nVINCITORE: agente #{w['agent']} su {sp['tf']} serie {sp['series']} | "
          f"griglia -{p['range_down']*100:.1f}%/+{p['range_up']*100:.1f}% "
          f"x{p['levels']} livelli, SL buf {p['sl_buf']*100:.1f}%, "
          f"TP buf {p['tp_buf']*100:.1f}%, max {p['max_bars']} barre")
    print(f"  ipotesi dell'agente: {w['brief']}")
    print(f"  TEST(OOS): PnL {w['test']['pnl_pct']:.0f}% | win "
          f"{w['test']['win_rate']*100:.0f}% | {w['test']['tpm']:.1f} trade/mese | "
          f"Sharpe {w['test']['sharpe']:.1f}")


if __name__ == "__main__":
    main()