"""Phase 2 gap: multi-rate envelope banks on vlaai_ws 10 s classifier.

Unused vs ALREADY_TRIED / EXPERIMENTS_LOG: temporal causal EWMA bank on the
speech envelope (τ∈{0, 50, 200, 800} ms) + onset. Distinct from delta/theta
band-pass envelope channels (already tried) and from onset+dom noenv (decoder).

Prep eaP_n5_t60, sw2, random init (F=5 ≠ SPK F=3). Score LODO+AASD+Carta + hp30.

usage:
  GLIMPSE_THR=norm python mrate_env_clf.py
"""
import json
import os
import pickle
import time
from types import SimpleNamespace

import numpy as np
import torch
import torch.nn.functional as F
from scipy.signal import lfilter

import decoders
import direct_classifier as DC
import ensemble_clf_transformer_v4 as V4
import eval_external as E
import score as S
from common import DS_KEYS, SEED
from common_exp import CFG, EXP, FS, fold_file, load_trial, rows_of
from decoders import D, DEV
from e1_switch import draw_switch_times
from run_experiment import load_external, log_to

EXP_NAME = "direct_clf__eaP_n5_t60_w10b3_mrate_aug-sw2"
TAG = "_w10b3_mrate_aug-sw2"
LOG_PATH = os.path.join(EXP, "experiments", "mrate_env_clf.log")
OUT_JSON = os.path.join(EXP, "results", f"{EXP_NAME}.json")
ALL5_PT = os.path.join(EXP, "models", f"all5_direct_clf{TAG}.pt")
CKPT_DIR = os.path.join(EXP, "models", "mrate_env")
EXT_DIR = os.path.join(EXP, "results", "research")
RESULTS_MD = os.path.join(EXP, "multi_agent_opt", "results_phase2_gap.md")
MAX_EPOCHS = int(os.environ.get("MAX_EPOCHS", "16"))
MIN_EPOCHS = int(os.environ.get("MIN_EPOCHS", "6"))
P_STAY, SCALE = 0.994, 0.8
WINDOW_S = 10.0
BATCH = int(os.environ.get("BATCH", "64"))
# Causal EWMA time-constants (seconds). τ=0 → raw envelope (identity).
TAUS_S = (0.0, 0.05, 0.20, 0.80)
N_FEAT = len(TAUS_S) + 1  # + onset


def mrate_targets(tr):
    """(T, 2, F) multi-rate envelope bank + onset. All causal."""
    env = tr["env"].astype(np.float64)
    banks = []
    for tau in TAUS_S:
        if tau <= 0:
            banks.append(env.astype(np.float32))
        else:
            a = float(np.exp(-1.0 / (tau * FS)))
            sm = lfilter([1.0 - a], [1.0, -a], env, axis=0)
            banks.append(sm.astype(np.float32))
    onset = np.maximum(0.0, np.diff(tr["env"], axis=0, prepend=tr["env"][:1])).astype(np.float32)
    banks.append(onset)
    return np.stack(banks, -1)


def fit_net(train, val, log, a):
    Fs = train[0]["_S"].shape[-1]
    seed = D.get("train_seed", CFG["seed"])
    torch.manual_seed(seed)
    net = DC.DirectNet(58, Fs, a.backbone).to(DEV)
    n_param = sum(p.numel() for p in net.parameters())
    log(f"  vlaai_ws+mrate DirectNet params {n_param} F={Fs} batch {D['batch_size']}")
    aug = decoders.DNNDec.__new__(decoders.DNNDec)
    aug.W, aug.fut, aug.hop, aug.C = DC.W, DC.FUT, DC.HOP, 58
    rs = np.random.default_rng(seed)
    Xv, Sv, yv = DC.windows(val, D["val_windows"], rs, None, a.p_switch, a.zero_eeg)
    opt = torch.optim.AdamW(net.parameters(), lr=D["lr"], weight_decay=D["weight_decay"])
    sch = torch.optim.lr_scheduler.ReduceLROnPlateau(
        opt, mode="min", factor=0.5, patience=D["lr_patience"])
    best, bad, state = np.inf, 0, None
    for ep in range(D["max_epochs"]):
        t1, tl = time.time(), []
        net.train()
        for _ in range(D["steps_per_epoch"]):
            X, S_, y = [z.to(DEV) for z in DC.windows(
                train, D["batch_size"], rs, aug, a.p_switch, a.zero_eeg)]
            loss = F.binary_cross_entropy_with_logits(net(X, S_), y)
            opt.zero_grad()
            loss.backward()
            torch.nn.utils.clip_grad_norm_(net.parameters(), 5.0)
            opt.step()
            tl.append(float(loss.detach()))
        net.eval()
        with torch.no_grad():
            lv = torch.cat([
                net(Xv[i:i + 256].to(DEV), Sv[i:i + 256].to(DEV)).cpu()
                for i in range(0, len(Xv), 256)])
        vl = float(F.binary_cross_entropy_with_logits(lv, yv))
        va = float(((lv > 0).float() == yv).float().mean())
        if ep >= a.min_epochs:
            sch.step(vl)
        log(f"    epoch {ep:02d} train {np.mean(tl):.4f} val BCE {vl:.4f} acc {va:.3f} "
            f"({time.time() - t1:.0f}s)")
        if vl < best - 1e-4:
            best, bad, state = vl, 0, {k: v.detach().clone() for k, v in net.state_dict().items()}
        elif ep >= a.min_epochs:
            bad += 1
            if bad >= D["patience"]:
                break
    if state is None:
        state = {k: v.detach().clone() for k, v in net.state_dict().items()}
    net.load_state_dict(state)
    net.eval()
    return net, best


def configure():
    DC.W = int(WINDOW_S * FS)
    DC.POS0, DC.LAB = DC.W - DC.FUT - DC.HOP, DC.W - FS
    # Label only — actual features come from mrate_targets (F=5).
    D["targets"] = ["mrate0", "mrate50", "mrate200", "mrate800", "onset"]
    D["augment"] = {**CFG["dnn_augment"], **CFG["aug_variants"]["cluster"], "clf_p_switch2": 0.5}
    D["train_seed"] = int(CFG["seed"])
    D["model_blocks"] = 3
    D["max_epochs"] = MAX_EPOCHS
    D["steps_per_epoch"] = 250
    D["batch_size"] = BATCH
    D["patience"] = 6
    decoders.apply_overrides(["model_blocks=3"], ["clf_p_switch2=0.5"])


def namespace():
    return SimpleNamespace(
        backbone="vlaai_ws", p_switch=0.5, zero_eeg=False, min_epochs=MIN_EPOCHS,
        init_from=None, prep="eaP_n5_t60", tag=TAG,
    )


def run_fold(held, exp, log, a):
    rng = np.random.default_rng(CFG["seed"] + DS_KEYS.index(held))
    train, val = [], []
    for ds in DS_KEYS:
        if ds == held:
            continue
        rows = rows_of(ds)
        vs = rng.choice(sorted(rows.subject.unique()))
        for _, r in rows.iterrows():
            (val if r["subject"] == vs else train).append(load_trial(a.prep, r["key"]))
    train += load_external(["Fuglsang2020"], a.prep, log)
    for tr in train + val:
        tr["_S"] = mrate_targets(tr)
    log(f"  fold held-out={held}: {len(train)} train / {len(val)} val, W={DC.W / FS:g}s "
        f"F={train[0]['_S'].shape[-1]}")
    t0 = time.time()
    net, best = fit_net(train, val, log, a)
    t_fit = time.time() - t0
    del train, val
    os.makedirs(CKPT_DIR, exist_ok=True)
    ckpt = os.path.join(CKPT_DIR, f"held-{held}.pt")
    torch.save(net.state_dict(), ckpt)
    log(f"  saved {ckpt}")
    srng = np.random.default_rng(SEED + DS_KEYS.index(held))
    ev, ctl = {}, {k: {} for k in ("normal", "zero_eeg", "shift_eeg", "no_frontal")}
    for _, r in rows_of(held).iterrows():
        tr = load_trial(a.prep, r["key"])
        Sfeat, x, att, T128 = mrate_targets(tr), tr["eeg"], tr["att"].astype(int), int(r["n"])
        times = draw_switch_times(srng, T128 / 128)
        srng.integers(0, 2)
        st128, cur, prev = np.zeros(T128, bool), False, 0
        for tt in times:
            s0 = min(T128 - 1, int(round(tt * 128)))
            st128[prev:s0] = cur
            cur, prev = not cur, s0
        st128[prev:] = cur
        st = st128[np.minimum(T128 - 1, np.round((np.arange(len(x)) / FS + tr["t0"]) * 128).astype(int))]
        Ssw = np.where(st[:, None, None], Sfeat[:, ::-1], Sfeat)
        lg, starts = DC.logits(net, x, Ssw)
        truth = (att ^ st)[np.maximum(starts - DC.HOP, 0)]
        n10 = len(lg) // 40
        ev[r["key"]] = dict(
            r0=lg / 2, r1=-lg / 2, att=truth.astype(np.int8),
            t_end=(starts / FS + tr["t0"]).astype(np.float32),
            r0_10=lg[:n10 * 40].reshape(n10, 40).mean(1) / 2,
            r1_10=-lg[:n10 * 40].reshape(n10, 40).mean(1) / 2,
            att10=(truth[:n10 * 40].reshape(n10, 40).mean(1) > 0.5).astype(np.int8),
            pre_switched=True)
        xf = x.copy()
        xf[:, DC.FRONTAL] = 0.0
        for name, xc in (("normal", x), ("zero_eeg", np.zeros_like(x)),
                         ("shift_eeg", np.roll(x, len(x) // 2, 0)), ("no_frontal", xf)):
            l1, s1 = DC.logits(net, xc, Sfeat, step=4)
            ctl[name].setdefault(r["subj_uid"], []).append(
                (l1 > 0) == (att[np.maximum(s1 - DC.HOP, 0)] == 0))
    controls = {
        k: dict(pooled=float(np.mean(np.concatenate([np.concatenate(v) for v in d.values()]))),
                subject_median=float(np.median([np.mean(np.concatenate(v)) for v in d.values()])))
        for k, d in ctl.items()}
    info = dict(decoder="direct_clf", prep=a.prep, held_out=held, fit_s=t_fit,
                total_s=time.time() - t0, lookahead_s=(DC.FUT + DC.HOP) / FS,
                best_val=best, channels=58, window_s=WINDOW_S, backbone="vlaai_ws",
                speech="mrate_env_bank+onset", taus_s=list(TAUS_S), controls=controls)
    from common_exp import save_pickle
    save_pickle(dict(evidence={"causal": ev}, info=info), fold_file(exp, held))
    log(f"  fold held-out={held} done in {info['total_s']:.0f}s best_val {best:.4f} "
        + "  ".join(f"{k} {v['pooled']:.3f}" for k, v in controls.items()))
    del net
    if DEV.type == "cuda":
        torch.cuda.empty_cache()


def score_hp30(ev, la, log):
    hp_ev = {}
    for ds in DS_KEYS:
        hp_ev[ds] = {}
        for key, e in ev[ds].items():
            signed = (e["r0"] - e["r1"]).astype(np.float64)
            hp = V4.highpass(signed[:, None], tau=30.0, hop=0.25)[:, 0]
            hp_ev[ds][key] = dict(e)
            hp_ev[ds][key]["r0"] = (hp / 2).astype(np.float32)
            hp_ev[ds][key]["r1"] = (-hp / 2).astype(np.float32)
    per = {}
    for ds in DS_KEYS:
        A = np.concatenate([(e["r0"] - e["r1"]) * np.where(e["att"] == 0, 1.0, -1.0)
                            for d in DS_KEYS if d != ds for e in hp_ev[d].values()])
        mu, sd = float(A.mean()), float(A.std())
        r = S.score_dataset(ds, hp_ev, la, emis=(mu, sd * SCALE), p_stay=P_STAY)
        per[ds] = r
        log(f"  HP30 LODO {ds}  H {r['H']:.4f}  Acc {r['Acc']:.2f}")
    mH = float(np.mean([per[d]["H"] for d in DS_KEYS]))
    mA = float(np.mean([per[d]["Acc"] for d in DS_KEYS]))
    log(f"  HP30 LODO MEAN  H {mH:.4f}  Acc {mA:.2f}")
    return per, mH, mA


def score_preset(log, a):
    la = (DC.FUT + DC.HOP) / FS
    ev, _ = S.load_folds(EXP_NAME, "causal")
    per = {}
    for ds in DS_KEYS:
        A = np.concatenate([(e["r0"] - e["r1"]) * np.where(e["att"] == 0, 1.0, -1.0)
                            for d in DS_KEYS if d != ds for e in ev[d].values()])
        mu, sd = float(A.mean()), float(A.std())
        r = S.score_dataset(ds, ev, la, emis=(mu, sd * SCALE), p_stay=P_STAY)
        per[ds] = r
        log(f"  PRESET LODO {ds}  H {r['H']:.4f}  Acc {r['Acc']:.2f}  L {r['L']:.3f}  SDT {r['SDT']:.2f}")
    mH = float(np.mean([per[d]["H"] for d in DS_KEYS]))
    mA = float(np.mean([per[d]["Acc"] for d in DS_KEYS]))
    log(f"  PRESET LODO MEAN  H {mH:.4f}  Acc {mA:.2f}")
    hp_per, hp_mH, hp_mA = score_hp30(ev, la, log)

    A = np.concatenate([(e["r0"] - e["r1"]) * np.where(e["att"] == 0, 1.0, -1.0)
                        for ds in DS_KEYS for e in ev[ds].values()])
    mu, sd = float(A.mean()), float(A.std())
    log(f"  external emissions mu {mu:.4f} sd {sd:.4f} scale {SCALE}")
    E.CONF.update(prep=a.prep, targets=list(D["targets"]))
    os.makedirs(EXT_DIR, exist_ok=True)
    ev_paths = {ds: os.path.join(EXT_DIR, f"ext_clf_{ds}{TAG}_evidence.pkl") for ds in ("AASD", "Carta2026")}
    if any(not os.path.exists(p) for p in ev_paths.values()):
        if os.path.exists(ALL5_PT):
            net = DC.DirectNet(58, N_FEAT, "vlaai_ws").to(DEV)
            net.load_state_dict(torch.load(ALL5_PT, map_location=DEV, weights_only=False))
            net.eval()
            log(f"  loaded {ALL5_PT}")
        else:
            rng = np.random.default_rng(CFG["seed"] + 99)
            train, val = [], []
            for ds in DS_KEYS:
                rows = rows_of(ds)
                vs = rng.choice(sorted(rows.subject.unique()))
                for _, r in rows.iterrows():
                    (val if r["subject"] == vs else train).append(load_trial(a.prep, r["key"]))
            train += load_external(["Fuglsang2020"], a.prep, log)
            for tr in train + val:
                tr["_S"] = mrate_targets(tr)
            log(f"  all-5 train {len(train)} / val {len(val)}")
            net, best = fit_net(train, val, log, a)
            torch.save(net.state_dict(), ALL5_PT)
            log(f"  saved {ALL5_PT} best val {best:.4f}")
            del train, val
        for ds, path in ev_paths.items():
            if os.path.exists(path):
                continue
            EV = {}
            trials = E.ext_trials(ds)
            log(f"  external {ds}: {len(trials)} trials")
            for i, tr in enumerate(trials):
                lg, starts = DC.logits(net, tr["eeg"], mrate_targets(tr))
                truth = tr["att"].astype(int)[np.maximum(starts - DC.HOP, 0)]
                EV[tr["key"]] = dict(
                    r0=lg / 2, r1=-lg / 2, att=truth.astype(np.int8),
                    t_end=(starts / FS + tr["t0"]).astype(np.float32),
                    att128=tr["att128"], n128=tr["n128"], subject=tr["subject"])
                if (i + 1) % 40 == 0 or i + 1 == len(trials):
                    log(f"    {ds} {i + 1}/{len(trials)}")
            with open(path, "wb") as fh:
                pickle.dump(EV, fh)
            log(f"  wrote {path}")
        del net
        if DEV.type == "cuda":
            torch.cuda.empty_cache()

    hp_parts = []
    for ds in DS_KEYS:
        for e in ev[ds].values():
            signed = (e["r0"] - e["r1"]).astype(np.float64)
            hp = V4.highpass(signed[:, None], tau=30.0, hop=0.25)[:, 0]
            hp_parts.append(hp * np.where(e["att"] == 0, 1.0, -1.0))
    mu_hp = float(np.concatenate(hp_parts).mean())
    sd_hp = float(np.concatenate(hp_parts).std())

    ext = {}
    for ds, path in ev_paths.items():
        with open(path, "rb") as fh:
            EV = pickle.load(fh)
        r = E.score(EV, mu, sd * SCALE, P_STAY, 0.75)
        EV_hp = {}
        for key, e in EV.items():
            signed = (e["r0"] - e["r1"]).astype(np.float64)
            hp = V4.highpass(signed[:, None], tau=30.0, hop=0.25)[:, 0]
            EV_hp[key] = dict(e)
            EV_hp[key]["r0"] = (hp / 2).astype(np.float32)
            EV_hp[key]["r1"] = (-hp / 2).astype(np.float32)
        r_hp = E.score(EV_hp, mu_hp, sd_hp * SCALE, P_STAY, 0.75)
        ext[ds] = dict(raw=r, hp30=r_hp)
        log(f"  PRESET EXT {ds}  H {r['H']:.4f} Acc {r['Acc']:.2f}")
        log(f"  PRESET EXT_hp30 {ds}  H {r_hp['H']:.4f} Acc {r_hp['Acc']:.2f}")
    return per, ext, mu, sd, mH, mA, hp_per, hp_mH, hp_mA


def write_results(per, ext, mH, mA, hp_per, hp_mH, hp_mA):
    stem = dict(AVGC=(0.7945, 74.06), DTU=(0.9061, 89.85), KUL=(0.8755, 82.33),
                UHD=(0.8407, 79.47), USTC=(0.9219, 86.36))
    fuse = (0.8725, 82.58)
    lines = [
        "# results_phase2_gap",
        "",
        "**Choice: multi-rate envelope banks** on `vlaai_ws` 10 s. "
        "Causal EWMA speech envelopes at τ∈{0, 50, 200, 800} ms + onset (F=5). "
        "Verified unused: not in ALREADY_TRIED; EXPERIMENTS_LOG delta/theta are spectral "
        "bands on env (DO NOT REPEAT), not temporal multi-rate; onset+dom noenv was decoder-only. "
        "DeepConvNet Phase 1 abandoned at chance → this gap run.",
        "",
        f"Prep `eaP_n5_t60`, 3 blocks, sw2, random init (F≠SPK), "
        f"max {MAX_EPOCHS} / min {MIN_EPOCHS} ×250 steps, batch {BATCH}. "
        f"HMM p_stay {P_STAY} scale {SCALE}. Also causal hp30.",
        "",
        "Code: `mrate_env_clf.py`. Checkpoints: `models/mrate_env/held-*.pt`, "
        f"`models/all5_direct_clf{TAG}.pt`. JSON: `{OUT_JSON}`.",
        "",
        "## LODO (preset)",
        "",
        "| Held-out | H | Acc % | hp30 H/Acc | vs stem_ms96 |",
        "|---|---:|---:|---|---|",
    ]
    for ds in DS_KEYS:
        r, h = per[ds], hp_per[ds]
        sh, sa = stem[ds]
        lines.append(
            f"| {ds} | {r['H']:.4f} | {r['Acc']:.2f} | {h['H']:.4f}/{h['Acc']:.2f} | "
            f"stem {sh:.4f}/{sa:.2f} |")
    lines += [
        f"| **mean** | **{mH:.4f}** | **{mA:.2f}** | **{hp_mH:.4f}/{hp_mA:.2f}** | "
        f"stem 0.8677/82.42; fuse {fuse[0]:.4f}/{fuse[1]:.2f} |",
        "",
        "## External (preset)",
        "",
        "| Set | H | Acc % | hp30 H/Acc | linear_hp30 | stem_ms96 |",
        "|---|---:|---:|---|---|---|",
        f"| AASD | {ext['AASD']['raw']['H']:.4f} | {ext['AASD']['raw']['Acc']:.2f} | "
        f"{ext['AASD']['hp30']['H']:.4f}/{ext['AASD']['hp30']['Acc']:.2f} | "
        f"0.6422/53.12 | 0.6158/51.54 |",
        f"| Carta2026 | {ext['Carta2026']['raw']['H']:.4f} | {ext['Carta2026']['raw']['Acc']:.2f} | "
        f"{ext['Carta2026']['hp30']['H']:.4f}/{ext['Carta2026']['hp30']['Acc']:.2f} | "
        f"0.6520/60.54 | 0.5695/51.03 |",
        "",
        "## Targets",
        "",
        "| Target | Result |",
        "|---|---|",
        f"| AVGC H>=0.85 Acc>=78 | "
        f"{'met' if per['AVGC']['H'] >= 0.85 and per['AVGC']['Acc'] >= 78 else 'miss'} "
        f"({per['AVGC']['H']:.4f}/{per['AVGC']['Acc']:.2f}) |",
        f"| UHD H>=0.85 | "
        f"{'met' if per['UHD']['H'] >= 0.85 else 'miss'} ({per['UHD']['H']:.4f}) |",
        f"| AASD Acc>60 with H>0.63 | "
        f"{'met' if ext['AASD']['raw']['Acc'] > 60 and ext['AASD']['raw']['H'] > 0.63 else 'miss'} "
        f"({ext['AASD']['raw']['H']:.4f}/{ext['AASD']['raw']['Acc']:.2f}; "
        f"hp30 {ext['AASD']['hp30']['H']:.4f}/{ext['AASD']['hp30']['Acc']:.2f}) |",
        f"| LODO mean vs fuse 0.8725/82.58 | {mH:.4f}/{mA:.2f} |",
        "",
    ]
    open(RESULTS_MD, "w").write("\n".join(lines) + "\n")
    return RESULTS_MD


def main():
    configure()
    log = log_to(LOG_PATH)
    a = namespace()
    log(f"=== {EXP_NAME} mrate-env vlaai_ws 10s device {DEV} max_epochs {MAX_EPOCHS} "
        f"min_epochs {MIN_EPOCHS} W={DC.W} FS={FS} F={N_FEAT} taus={TAUS_S} ===")

    # shape / antisym smoke
    net = DC.DirectNet(58, N_FEAT, "vlaai_ws").to(DEV)
    with torch.no_grad():
        E = torch.randn(4, DC.W, 58, device=DEV)
        A = torch.randn(4, DC.W, N_FEAT, device=DEV)
        B = torch.randn(4, DC.W, N_FEAT, device=DEV)
        y_ab = net.g(E, A, B) - net.g(E, B, A)
        y_ba = net.g(E, B, A) - net.g(E, A, B)
        anti = float((y_ab + y_ba).abs().mean())
        delta = float((net.g(E, A, B) - net.g(E, B, A)).abs().mean())
    log(f"swap-test params {sum(p.numel() for p in net.parameters())} "
        f"anti_err {anti:.3e} swap_delta {delta:.4f}")
    if anti > 1e-5 or delta < 1e-4:
        raise RuntimeError(f"swap/antisym failed anti={anti} delta={delta}")
    del net
    if DEV.type == "cuda":
        torch.cuda.empty_cache()
    log("forward check ok")

    for held in DS_KEYS:
        path = fold_file(EXP_NAME, held)
        if os.path.exists(path):
            log(f"  fold held-out={held}: cached {path}")
            continue
        run_fold(held, EXP_NAME, log, a)

    per, ext, mu, sd, mH, mA, hp_per, hp_mH, hp_mA = score_preset(log, a)
    rpath = write_results(per, ext, mH, mA, hp_per, hp_mH, hp_mA)
    out = dict(
        experiment=EXP_NAME, decoder="direct_clf", prep="eaP_n5_t60",
        targets=D["targets"], speech="mrate_env_bank+onset", taus_s=list(TAUS_S),
        p_switch=0.5, init_from=None, min_epochs=MIN_EPOCHS,
        max_epochs=MAX_EPOCHS, backbone="vlaai_ws", window_s=WINDOW_S, batch=BATCH,
        train_seed=D["train_seed"], extra_train="Fuglsang2020", augment=D["augment"],
        preset=dict(p_stay=P_STAY, scale=SCALE, emis_mu=mu, emis_sd=sd,
                    lodo={d: per[d] for d in DS_KEYS},
                    lodo_hp30={d: hp_per[d] for d in DS_KEYS},
                    external=ext),
        mean_H=mH, mean_Acc=mA, hp30_mean_H=hp_mH, hp30_mean_Acc=hp_mA,
    )
    os.makedirs(os.path.dirname(OUT_JSON), exist_ok=True)
    with open(OUT_JSON, "w") as fh:
        json.dump(out, fh, indent=1, default=float)
    log(f"wrote {OUT_JSON} and {rpath}")


if __name__ == "__main__":
    main()
