initial import: etf strategy project

scripts/tushare_download_universe.py

@@ -0,0 +1,47 @@
+from __future__ import annotations
+
+import argparse
+import json
+from pathlib import Path
+
+import pandas as pd
+
+from qfr.data.tushare_client import fetch_fund_daily, load_tushare_config
+
+
+def main() -> None:
+    p = argparse.ArgumentParser()
+    p.add_argument("--env", default=None, help="Path to .env")
+    p.add_argument("--config", default="configs/etf_universe.json")
+    p.add_argument("--start", dest="start_date", default=None, help="YYYYMMDD")
+    p.add_argument("--end", dest="end_date", default=None, help="YYYYMMDD")
+    p.add_argument("--outdir", default="data/raw")
+    args = p.parse_args()
+
+    cfg = load_tushare_config(args.env)
+
+    conf = json.loads(Path(args.config).read_text(encoding="utf-8"))
+    assets = conf["assets"]
+    outdir = Path(args.outdir)
+    outdir.mkdir(parents=True, exist_ok=True)
+
+    for a in assets:
+        ts_code = a["ts_code"]
+        df = fetch_fund_daily(cfg, ts_code=ts_code, start_date=args.start_date, end_date=args.end_date)
+        if df is None or df.empty:
+            print(f"skip {ts_code}: empty")
+            continue
+
+        # standardize columns expected by backtest
+        # fund_daily provides: ts_code, trade_date, open, high, low, close, vol, amount
+        keep = [c for c in ["ts_code", "trade_date", "open", "high", "low", "close", "vol", "amount"] if c in df.columns]
+        df = df[keep].copy()
+        df = df.sort_values("trade_date")
+
+        out = outdir / f"{ts_code.replace('.', '')}.parquet"
+        df.to_parquet(out, index=False)
+        print(f"wrote {ts_code}: {len(df)} rows -> {out}")
+
+
+if __name__ == "__main__":
+    main()