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/fetch_us_sectors.py

@@ -0,0 +1,43 @@
+"""Fetch GICS-like sectors from Yahoo for S&P 500 ever-members missing from
+data/us_sectors.csv. Writes data/research/us_sectors_extra.csv.
+
+    uv run python -m research.lab.fetch_us_sectors
+"""
+
+import os
+import pickle
+
+import pandas as pd
+import yfinance as yf
+
+from research.lab.fetch_us import _proxy_env
+
+# Yahoo sector names → GICS sector names used in data/us_sectors.csv
+YAHOO_TO_GICS = {
+    "Technology": "Information Technology", "Healthcare": "Health Care",
+    "Financial Services": "Financials", "Consumer Cyclical": "Consumer Discretionary",
+    "Consumer Defensive": "Consumer Staples", "Basic Materials": "Materials",
+    "Communication Services": "Communication Services", "Industrials": "Industrials",
+    "Energy": "Energy", "Utilities": "Utilities", "Real Estate": "Real Estate",
+}
+
+
+def main() -> None:
+    _proxy_env()
+    with open(os.path.join("data", "research", "us_ohlcv.pkl"), "rb") as fh:
+        tickers = list(pickle.load(fh)["close"].columns)
+    known = set(pd.read_csv(os.path.join("data", "us_sectors.csv"))["ticker"])
+    rows = []
+    for t in sorted(set(tickers) - known):
+        try:
+            s = yf.Ticker(t).info.get("sector")
+        except Exception:  # noqa: BLE001
+            s = None
+        rows.append({"ticker": t, "sector": YAHOO_TO_GICS.get(s, s)})
+    out = pd.DataFrame(rows)
+    out.to_csv(os.path.join("data", "research", "us_sectors_extra.csv"), index=False)
+    print(out["sector"].value_counts(dropna=False))
+
+
+if __name__ == "__main__":
+    main()