#!/usr/bin/env bash
# Walk-forward CV for the Phase E.4.A.T10 compose backtest.
#
# Slides a fixed-size window across the fxcache. Each fold trains DQN
# from scratch on the front of the window and evaluates on the back.
# Fold C is the cleanest stacker-OOS test (eval bars 1.62M..1.9M lie
# entirely past the stacker training cut at 1.57M).
#
# Outputs per-fold JSON to /tmp/cv_fold_*.json. Run from repo root.

set -euo pipefail

FXCACHE="${FXCACHE:-/home/jgrusewski/Work/foxhunt/test_data/feature-cache/9297017b6db6795f75e57be8aefb03e45e6427513f42c08e22521e58fa025d5e.fxcache}"
ALPHA="${ALPHA:-config/ml/alpha_logits_cache.bin}"
FILL="${FILL:-config/ml/alpha_fill_coeffs.json}"
BIN="${BIN:-./target/release/examples/alpha_compose_backtest}"

WINDOW=700000
TRAIN_FRAC=0.6      # 420K train, 280K eval per fold

declare -a FOLDS=(
  "A:0"
  "B:600000"
  "C:1200000"
)

for fold_spec in "${FOLDS[@]}"; do
  name="${fold_spec%%:*}"
  offset="${fold_spec##*:}"
  out="/tmp/cv_fold_${name}.json"
  echo "===================================================================="
  echo "Fold ${name}: offset=${offset}  window=${WINDOW}  train_frac=${TRAIN_FRAC}"
  echo "===================================================================="
  SQLX_OFFLINE=true RUST_LOG=info "$BIN" \
    --fxcache-path "$FXCACHE" \
    --alpha-cache "$ALPHA" \
    --fill-coeffs "$FILL" \
    --data-start-offset "$offset" \
    --max-snapshots "$WINDOW" \
    --train-frac "$TRAIN_FRAC" \
    --c51 --temporal --window-k 16 --isv-continual \
    --out-path "$out"
done

echo
echo "===================================================================="
echo "Walk-forward summary (best Sharpe_ann per cost, per fold)"
echo "===================================================================="
python3 - <<'PY'
import json, statistics
folds = ["A", "B", "C"]
rows = []
for f in folds:
    with open(f"/tmp/cv_fold_{f}.json") as fh:
        j = json.load(fh)
    by_cost = {}
    for b in j["bins"]:
        c = b["cost"]
        if c not in by_cost or b["sharpe_annualised"] > by_cost[c][1]:
            by_cost[c] = (b["threshold"], b["sharpe_annualised"], b["win_rate"], b["avg_n_trades"])
    rows.append((f, by_cost))

costs = sorted(rows[0][1].keys())
print(f"{'cost':>8}   " + "    ".join(f"fold-{f}" for f, _ in rows))
for c in costs:
    cells = []
    for _, by_cost in rows:
        tau, sa, wr, tp = by_cost[c]
        cells.append(f"τ={tau:.2f} S={sa:+6.2f} ({wr*100:.0f}%/{tp:.0f})")
    print(f"{c:>8.4f}   " + "    ".join(cells))

print()
print("Per-cost mean Sharpe_ann ± stddev across folds:")
for c in costs:
    sas = [by_cost[c][1] for _, by_cost in rows]
    m = statistics.mean(sas)
    sd = statistics.stdev(sas) if len(sas) > 1 else 0.0
    print(f"  cost={c:.4f}  mean Sharpe_ann = {m:+7.2f} ± {sd:5.2f}")
PY