feat(portfolio): LocalUnifiedProvider 代码转换+复权因子(Task0)

2026-07-23 08:05:09 +08:00
parent c2a89d01a4
commit e12c66acd5
2 changed files with 265 additions and 0 deletions
@@ -0,0 +1,120 @@
+"""LocalUnifiedProvider: 读方案A 权威数据层, 零 online, 治幸存者偏差(spec §6)。
+
+数据源(全本地 VPS ``C:\\sanguo_vnpy_v2\\data\\``):
+- 日线: ``dbbardata('d')`` raw + ``bs_adjust_factor`` 算前复权(§14.7)
+- 成份股: ``constituent_unified`` 并集(治偏差,无 date 时点)
+- 估值 pe/pb/ps/pcf: ``valuation_baostock/<year>.parquet``(baostock 权威)
+- 市值/股本: ``static/valuation`` akshare parquet(baostock 无市值列)
+- 三表: ``static/{balance,income,cashflow}`` akshare parquet(委托 LocalParquetProvider)
+
+零 online: 不 import baostock 调 online。Mac 测试用 sqlite+parquet fixture。
+"""
+from __future__ import annotations
+
+import logging
+import os
+import sqlite3
+from datetime import datetime
+from typing import Any, Dict, List, Optional, Union
+
+import numpy as np
+import pandas as pd
+
+# bullet-trade 可能未装,容错 import DataProvider(照 local_parquet_provider 模式)
+try:
+    from bullet_trade.data.providers.base import DataProvider  # type: ignore
+except ImportError:  # Mac dev 环境未装,允许模块加载
+    class DataProvider:  # type: ignore[no-redef]
+        name: str = "base"
+
+
+logger = logging.getLogger(__name__)
+
+# VPS 默认路径(Windows); Mac 测试通过 config["db_path"] / config["data_dir"] 覆盖
+_DEFAULT_DB = r"C:\sanguo_vnpy_v2\data\quant_trading.db"
+_DEFAULT_DATA_DIR = r"C:\sanguo_vnpy_v2\data"
+
+# jq 后缀 ↔ dbbardata exchange
+_JQ_SUFFIX_TO_EXC = {"XSHG": "SSE", "XSHE": "SZSE", "SH": "SSE", "SZ": "SZSE"}
+_EXC_TO_JQ_SUFFIX = {"SSE": "XSHG", "SZSE": "XSHE"}
+
+
+def jq_to_dbbardata(jq_code: str) -> tuple[str, str]:
+    """``600519.XSHG`` → ``("600519", "SSE")``。
+
+    纯 6 位按 6 开头 = sh / 0,3 开头 = sz 推断。
+    """
+    s = (jq_code or "").strip()
+    if "." not in s:
+        if len(s) == 6:
+            return s, ("SSE" if s.startswith("6") else "SZSE")
+        return s, "SSE"
+    code, suffix = s.split(".", 1)
+    return code, _JQ_SUFFIX_TO_EXC.get(suffix.upper(), "SSE")
+
+
+def dbbardata_to_jq(symbol: str, exchange: str) -> str:
+    """``("600519", "SSE")`` → ``"600519.XSHG"``。"""
+    jq_suffix = _EXC_TO_JQ_SUFFIX.get(str(exchange).upper(), "XSHG")
+    return f"{symbol}.{jq_suffix}"
+
+
+def _jq_to_bs_code(jq_code: str) -> str:
+    """``600519.XSHG`` → ``"sh.600519"``(``bs_adjust_factor.code`` 格式)。"""
+    sym, exc = jq_to_dbbardata(jq_code)
+    prefix = "sh" if exc == "SSE" else "sz"
+    return f"{prefix}.{sym}"
+
+
+def _build_qfq_factor(
+    bs_code: str,
+    conn: sqlite3.Connection,
+    dates: pd.Series,
+) -> pd.Series:
+    """构造每个 date 的前复权因子(asof 语义)。
+
+    规则:
+    - 找 ``<= d`` 的最大 dividOperateDate 的 foreAdjustFactor
+    - 全部事件 > d(早于所有事件)→ 用最早的 factor
+    - 全部事件 <= d(晚于所有事件)→ 用最新的 factor
+    - 无事件 → 全 1.0
+
+    ``qfq[t] = raw[t] * factor[t]``
+    """
+    rows = conn.execute(
+        "SELECT dividOperateDate, foreAdjustFactor FROM bs_adjust_factor "
+        "WHERE code=? ORDER BY dividOperateDate",
+        (bs_code,),
+    ).fetchall()
+    dates_ts = pd.to_datetime(dates)
+    if not rows:
+        return pd.Series([1.0] * len(dates_ts), index=dates_ts)
+    ev_dates = pd.to_datetime([r[0] for r in rows])
+    factors = [float(r[1]) for r in rows]
+    out: List[float] = []
+    for d in dates_ts:
+        mask = ev_dates <= d
+        if mask.any():
+            # <= d 的最大事件 = 最后一个 True
+            idx = int(np.where(mask)[0][-1])
+        else:
+            # 全部 > d → 用最早(第一个)
+            idx = 0
+        out.append(factors[idx])
+    return pd.Series(out, index=dates_ts)
+
+
+class LocalUnifiedProvider(DataProvider):  # type: ignore[misc]
+    """占位类(Task0 骨架; Task1-4 填充方法)。
+
+    读方案A 权威数据层, 零 online, 治幸存者偏差(spec §6 使用层)。
+    """
+
+    name: str = "sanguo_local_unified"
+    requires_live_data: bool = False
+
+    def __init__(self, config: Optional[Dict[str, Any]] = None) -> None:
+        cfg = config or {}
+        self.db_path: str = cfg.get("db_path", _DEFAULT_DB)
+        self.data_dir: str = cfg.get("data_dir", _DEFAULT_DATA_DIR)
+        self._conn: Optional[sqlite3.Connection] = None
@@ -0,0 +1,145 @@
+"""LocalUnifiedProvider 单元测试(spec §6 使用层)。
+
+Mac 本地 TDD: sqlite tmp_path + tmp parquet fixture,零 VPS 依赖,零网络。
+覆盖:
+- ``jq_to_dbbardata`` / ``dbbardata_to_jq`` / ``_jq_to_bs_code`` 代码转换
+- ``_build_qfq_factor`` 复权因子构造(asof)
+- ``get_price``           dbbardata('d') raw + fq='qfq' 前复权 + panel=False 长表
+- ``get_index_stocks``    constituent_unified 并集(治偏差,无 date 时点)
+- ``get_fundamentals_df`` pe/pb/ps/pcf←valuation_baostock + 市值←static akshare + 三表委托 LocalParquetProvider
+- 辅助方法 get_trade_days / get_all_securities / get_security_info / get_current_tick / get_split_dividend
+"""
+from __future__ import annotations
+
+import sqlite3
+from typing import Any, Dict, List
+
+import pandas as pd
+import pytest
+
+from sanguo_portfolio.providers.local_unified_provider import (
+    jq_to_dbbardata,
+    dbbardata_to_jq,
+    _jq_to_bs_code,
+    _build_qfq_factor,
+    LocalUnifiedProvider,
+)
+
+
+# ======================== Task 0: 代码转换 ========================
+class TestCodeFormat:
+    def test_jq_to_dbbardata_sh(self):
+        assert jq_to_dbbardata("600519.XSHG") == ("600519", "SSE")
+
+    def test_jq_to_dbbardata_sz(self):
+        assert jq_to_dbbardata("000001.XSHE") == ("000001", "SZSE")
+
+    def test_jq_to_dbbardata_pure_digit_sh(self):
+        # 6 开头 → SSE
+        assert jq_to_dbbardata("600519") == ("600519", "SSE")
+
+    def test_jq_to_dbbardata_pure_digit_sz(self):
+        # 0/3 开头 → SZSE
+        assert jq_to_dbbardata("000001") == ("000001", "SZSE")
+        assert jq_to_dbbardata("300001") == ("300001", "SZSE")
+
+    def test_dbbardata_to_jq_sh(self):
+        assert dbbardata_to_jq("600519", "SSE") == "600519.XSHG"
+
+    def test_dbbardata_to_jq_sz(self):
+        assert dbbardata_to_jq("000001", "SZSE") == "000001.XSHE"
+
+    def test_round_trip_jq_to_dbbardata_to_jq(self):
+        original = "600519.XSHG"
+        sym, exc = jq_to_dbbardata(original)
+        assert dbbardata_to_jq(sym, exc) == original
+
+    def test_jq_to_bs_code_sh(self):
+        # 600519.XSHG → 'sh.600519'(bs_adjust_factor.code 格式)
+        assert _jq_to_bs_code("600519.XSHG") == "sh.600519"
+
+    def test_jq_to_bs_code_sz(self):
+        assert _jq_to_bs_code("000001.XSHE") == "sz.000001"
+
+
+# ======================== Task 0: 复权因子 asof ========================
+class TestBuildQfqFactor:
+    def test_asof_before_all_events_uses_earliest(self, tmp_path):
+        # 2 除权事件, 最新=1.0
+        db = tmp_path / "t.db"
+        c = sqlite3.connect(str(db))
+        c.execute(
+            "CREATE TABLE bs_adjust_factor(code TEXT, dividOperateDate TEXT, "
+            "foreAdjustFactor REAL, backAdjustFactor REAL, adjustFactor REAL)"
+        )
+        c.executemany(
+            "INSERT INTO bs_adjust_factor VALUES(?,?,?,?,?)",
+            [
+                ("sh.600519", "2024-06-19", 0.90, 0, 0),
+                ("sh.600519", "2025-06-19", 1.00, 0, 0),
+            ],
+        )
+        c.commit()
+        c.close()
+        # 2023 早于所有事件 → 用最早 factor=0.90
+        dates = pd.to_datetime(["2023-01-01"])
+        f = _build_qfq_factor("sh.600519", sqlite3.connect(str(db)), dates)
+        assert abs(f.iloc[0] - 0.90) < 1e-6
+
+    def test_asof_between_events(self, tmp_path):
+        db = tmp_path / "t.db"
+        c = sqlite3.connect(str(db))
+        c.execute(
+            "CREATE TABLE bs_adjust_factor(code TEXT, dividOperateDate TEXT, "
+            "foreAdjustFactor REAL, backAdjustFactor REAL, adjustFactor REAL)"
+        )
+        c.executemany(
+            "INSERT INTO bs_adjust_factor VALUES(?,?,?,?,?)",
+            [
+                ("sh.600519", "2024-06-19", 0.90, 0, 0),
+                ("sh.600519", "2025-06-19", 1.00, 0, 0),
+            ],
+        )
+        c.commit()
+        c.close()
+        # 2024-07 在两事件之间 → ≤ 的最大事件是 2024-06-19, factor=0.90
+        dates = pd.to_datetime(["2024-07-01"])
+        f = _build_qfq_factor("sh.600519", sqlite3.connect(str(db)), dates)
+        assert abs(f.iloc[0] - 0.90) < 1e-6
+
+    def test_asof_after_all_events_uses_latest(self, tmp_path):
+        db = tmp_path / "t.db"
+        c = sqlite3.connect(str(db))
+        c.execute(
+            "CREATE TABLE bs_adjust_factor(code TEXT, dividOperateDate TEXT, "
+            "foreAdjustFactor REAL, backAdjustFactor REAL, adjustFactor REAL)"
+        )
+        c.executemany(
+            "INSERT INTO bs_adjust_factor VALUES(?,?,?,?,?)",
+            [
+                ("sh.600519", "2024-06-19", 0.90, 0, 0),
+                ("sh.600519", "2025-06-19", 1.00, 0, 0),
+            ],
+        )
+        c.commit()
+        c.close()
+        # 2025-07 晚于所有事件 → 最新 factor=1.00
+        dates = pd.to_datetime(["2025-07-01"])
+        f = _build_qfq_factor("sh.600519", sqlite3.connect(str(db)), dates)
+        assert abs(f.iloc[0] - 1.00) < 1e-6
+
+    def test_no_events_returns_ones(self, tmp_path):
+        db = tmp_path / "t.db"
+        c = sqlite3.connect(str(db))
+        c.execute(
+            "CREATE TABLE bs_adjust_factor(code TEXT, dividOperateDate TEXT, "
+            "foreAdjustFactor REAL, backAdjustFactor REAL, adjustFactor REAL)"
+        )
+        c.commit()
+        c.close()
+        # 无事件 → 全 1.0
+        dates = pd.to_datetime(["2024-01-01", "2024-06-01"])
+        f = _build_qfq_factor("sh.600519", sqlite3.connect(str(db)), dates)
+        assert len(f) == 2
+        assert abs(f.iloc[0] - 1.0) < 1e-6
+        assert abs(f.iloc[1] - 1.0) < 1e-6