feat: signal abstraction layer + sizer + HS300 universe + PnL/IC reports

2026-06-07 09:44:33 +08:00
parent 085e51abf1
commit da01312292
20 changed files with 610 additions and 23 deletions
@@ -0,0 +1,38 @@
+"""CSI 300 (HS300) universe helpers."""
+import logging
+
+import baostock as bs
+import pandas as pd
+
+logger = logging.getLogger(__name__)
+
+# First 30 HS300 constituents (large caps) in 'shXXXXXX' / 'szXXXXXX' format.
+# Hardcoded for fast, deterministic smoke tests. Use get_hs300_stocks() for the
+# live, full list — downloading daily bars for all ~300 takes roughly 10 minutes.
+SYMBOLS = [
+    "sh600000", "sh600009", "sh600010", "sh600028", "sh600030",
+    "sh600036", "sh600048", "sh600050", "sh600104", "sh600276",
+    "sh600309", "sh600519", "sh600585", "sh600887", "sh600900",
+    "sh601012", "sh601166", "sh601288", "sh601318", "sh601398",
+    "sh601628", "sh601668", "sh601857", "sh601888", "sh601988",
+    "sz000001", "sz000002", "sz000333", "sz000651", "sz000858",
+]
+
+
+def get_hs300_stocks() -> pd.DataFrame:
+    """Fetch the current CSI 300 constituents from baostock.
+
+    Returns:
+        DataFrame with columns ``code`` (e.g. ``sh600000``), ``name``, ``date``.
+    """
+    bs.login()
+    try:
+        rs = bs.query_hs300_stocks()
+        stocks = []
+        while rs.next():
+            stocks.append(rs.get_row_data())
+    finally:
+        bs.logout()
+    df = pd.DataFrame(stocks, columns=["code", "name", "date"])
+    df["code"] = df["code"].str.replace(".", "", regex=False)
+    return df