research: point-in-time factor research harness (research/lab)

Event-driven long-only simulator with next-open fills, CN tradability
(halts, limit-up/down, stamp duty), PIT S&P 500 / CSI 300 membership,
rebalance-phase averaging, factor IC scans, maximin stepwise composite
search across 5-year blocks, walk-forward LightGBM/ridge combiners,
overlays, and deflated Sharpe. Fetchers pull 20y US OHLCV from Yahoo and
CSI 300/500 ever-members (membership snapshot from baostock, bars from
Yahoo). Research data lives in data/research/ (ignored).

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

research/lab/baselines.py

@@ -0,0 +1,47 @@
+"""
+Re-run the existing factor_combo champions under the research engine, with
+the same rules every new candidate gets: next-open execution, PIT universe,
+costs, and averaging over rebalance phases.
+
+    PYTHONPATH=. uv run python -m research.lab.baselines --market us
+"""
+
+import argparse
+import warnings
+
+import pandas as pd
+
+from research.lab.factor_scan import load, phase_avg
+from research.lab.report import fmt
+from strategies.factor_combo import SIGNAL_REGISTRY
+
+warnings.filterwarnings("ignore")
+
+CHAMPIONS = {
+    "us": ["rec_mfilt+deep_upvol", "ma200+mom7m+rec126", "rec_mfilt+ma200", "mom7m+rec126"],
+    "cn": ["up_cap+quality_mom", "down_resil+qual_mom", "rec63+mom_gap", "up_cap+mom_gap"],
+}
+
+
+def baseline_scores(p, market: str) -> dict[str, pd.DataFrame]:
+    mk = "us" if market == "us" else "cn"
+    # factor_combo signals were built on prices masked to index membership
+    px = p.close.where(p.member).ffill(limit=5)
+    return {name: SIGNAL_REGISTRY[name](px) for name in CHAMPIONS[mk]}
+
+
+def main() -> None:
+    ap = argparse.ArgumentParser()
+    ap.add_argument("--market", default="us")
+    args = ap.parse_args()
+    p, periods = load(args.market)
+    scores = baseline_scores(p, args.market)
+    for name, s in scores.items():
+        for every, label in [(5, "weekly"), (21, "monthly")]:
+            for per, (a, b) in periods.items():
+                st = phase_avg(p, s, a, b, 10, every)
+                print(f"{name:22s} top10 {label:8s} {per:8s} {fmt(st)}", flush=True)
+
+
+if __name__ == "__main__":
+    main()