"""Lean version: 15-alpha grid, TLB cost, cold vs warm, omit-size then synth-full."""
from __future__ import annotations
import json, sys, time
sys.path.insert(0, "/home/yurenh2/emm")
import numpy as np, ot, torch
from scipy.optimize import linear_sum_assignment
from worldalign.synth_fast_gate import ClosedFormEnergy, fast_pair_descent
from worldalign.synth_triangle_gate import standardized

DEV = torch.device("cuda:1")
ALPHAS = [0.0, 0.2, 0.4, 0.6, 0.75, 0.85, 0.88, 0.90, 0.92, 0.94, 0.95,
          0.96, 0.97, 0.98, 0.99, 1.0]


def standardise(m):
    mask = ~np.eye(len(m), dtype=bool); v = m[mask]
    o = (m - v.mean()) / v.std(); np.fill_diagonal(o, 0.0); return o


def tlb(V, S):
    n = len(V); a = np.sort(V, 1); b = np.sort(S, 1)
    return (a * a).sum(1)[:, None] / n + (b * b).sum(1)[None, :] / n - 2 * (a @ b.T) / n


def run(path, label, trial=0):
    st = torch.load(path, map_location="cpu", weights_only=False)
    V = standardise(st["visual_field"].double().numpy())
    T = standardise(st["text_field"].double().numpy())
    n = len(V); w = ot.unif(n)
    rng = np.random.default_rng(trial); hid = rng.permutation(n)
    S = T[np.ix_(hid, hid)]
    Vg = standardized(torch.from_numpy(V).to(DEV)).double()
    Sg = standardized(torch.from_numpy(S).to(DEV)).double()
    en = ClosedFormEnergy(Sg, Vg, 1.0, 0.0, 64)
    M = tlb(V, S); M = M / M.max()

    def acc(c): return float((hid[c] == np.arange(n)).mean())

    def refine(c):
        f = fast_pair_descent(Sg, Vg, torch.from_numpy(np.ascontiguousarray(c)).to(DEV),
                              600).cpu().numpy()
        e = float(en.energy(torch.from_numpy(np.ascontiguousarray(f)).to(DEV)[None])[0])
        return e, acc(f)

    et = float(en.energy(torch.from_numpy(np.ascontiguousarray(np.argsort(hid))).to(DEV)[None])[0])
    print(f"# {label} trial{trial}  E_truth={et:.4f}", flush=True)

    out = {"label": label, "E_truth": et, "cold": [], "warm": []}
    for mode in ("cold", "warm"):
        G = np.outer(w, w)
        prev = None
        for a in ALPHAS:
            t0 = time.time()
            g0 = None if mode == "cold" else G
            G2 = ot.gromov.fused_gromov_wasserstein(M, V, S, w, w, "square_loss",
                                                    alpha=a, G0=g0, max_iter=200,
                                                    tol_rel=1e-9)
            if mode == "warm":
                G = G2
            _, cols = linear_sum_assignment(-G2)
            e, ar = refine(cols)
            same = (prev is not None and np.array_equal(cols, prev))
            prev = cols
            rec = {"alpha": a, "raw": acc(cols), "refined": ar, "E": e,
                   "sec": round(time.time() - t0, 1), "same_as_prev": bool(same)}
            out[mode].append(rec)
            print(f"  {mode} a={a:<5} raw={rec['raw']:.4f} ref={ar:.4f} E={e:.4f}"
                  f" {'FROZEN' if same else ''} ({rec['sec']}s)", flush=True)
        good = out[mode]
        best = min(good, key=lambda x: x["E"])
        print(f"  == {mode}: blind-by-E refined={best['refined']:.4f} (alpha={best['alpha']}),"
              f" oracle-best={max(x['refined'] for x in good):.4f}", flush=True)
    return out


if __name__ == "__main__":
    base = "/home/yurenh2/emm/artifacts/synth_v1/"
    res = []
    for p, l in [("omit_size.pt", "omit-size"), ("omit_none.pt", "synth-full")]:
        res.append(run(base + p, l))
    scratch = ("/tmp/claude-1273071/-home-yurenh2-emm/"
               "bb97201d-d9b5-46e6-82fc-981d37e7ab98/scratchpad/")
    json.dump(res, open(scratch + "lean.json", "w"))
    print(json.dumps({"done": True}))