chore: 重构前基线 — 9 个 sync task 全部 ok + akshare 移除 + mairui 资金流接入

状态： - 9 个 sync task（stock_basic / kline_daily / kline_index / kline_5min / moneyflow / industry_sector / sector_features / share_snapshot / market_regime） - 数据源：baostock + mairui + 雪球(pysnowball) + 新浪（4 个） - 项目级约束：永远不用 akshare（已落实） - kline_5min 改用 DB 快照统一全量/增量逻辑 - 零后端 Chrome 扩展 xueqiu_sync（独立项目）
2026-06-15 15:36:09 +08:00
commit 05635b76b9
55 changed files with 6307 additions and 0 deletions
@@ -0,0 +1,113 @@
+"""同步任务：市场情绪（market_regime_daily，衍生源）。
+
+基于本地 kline_stock 数据聚合：advancers / decliners / turnover / advance_ratio。"""
+from __future__ import annotations
+
+from datetime import datetime
+from typing import Any
+
+import numpy as np
+import pandas as pd
+
+from app.core.db import ops as db_ops
+from app.core.sync.base import SyncTask
+from app.core.utils.logging import get_logger
+
+logger = get_logger("sync.market_regime")
+
+DEFAULT_START = "2018-01-01"
+EXTREME_PANIC_ADV = 0.2
+EXTREME_PANIC_TURN = 1.5
+
+
+def _is_extreme_panic(row: pd.Series) -> int:
+    ar = pd.to_numeric(row.get("advance_ratio"), errors="coerce")
+    tr = pd.to_numeric(row.get("turnover_ratio_5d"), errors="coerce")
+    if pd.isna(ar) or pd.isna(tr):
+        return 0
+    return int(ar < EXTREME_PANIC_ADV and tr > EXTREME_PANIC_TURN)
+
+
+class SyncMarketRegime(SyncTask):
+    dataset_id = "market_regime"
+
+    def _run(self, *, trigger_source: str = "manual", start: str = DEFAULT_START, **kwargs) -> dict[str, Any]:
+        end = datetime.now().strftime("%Y-%m-%d")
+        self._progress(message=f"构建 market_regime {start} ~ {end}...")
+
+        # 1. 取所有非退市股票代码
+        codes = list(db_ops.iter_stock_codes(active_only=True))
+        if not codes:
+            return {"status": "error", "message": "stocks 表为空"}
+
+        # 2. 拉所有 K 线（按股票）- 这里用 SQL GROUP BY 一次性算 daily turnover
+        from app.core.db.connection import get_mysql
+
+        sql = """
+            SELECT
+                stock_code,
+                trade_date,
+                `close`,
+                volume
+            FROM kline_stock
+            WHERE trade_date BETWEEN %s AND %s
+            ORDER BY stock_code, trade_date
+        """
+        with get_mysql().cursor() as cur:
+            cur.execute(sql, (start, end))
+            rows = cur.fetchall()
+        if not rows:
+            return {"status": "warning", "message": f"kline_stock 在 {start} ~ {end} 区间无数据"}
+
+        df = pd.DataFrame(rows)
+        df["trade_date"] = pd.to_datetime(df["trade_date"], errors="coerce")
+        df["close"] = pd.to_numeric(df["close"], errors="coerce")
+        df["volume"] = pd.to_numeric(df["volume"], errors="coerce").fillna(0.0)
+        df = df.dropna(subset=["trade_date", "close"]).sort_values(["stock_code", "trade_date"])
+        df["prev_close"] = df.groupby("stock_code")["close"].shift(1)
+        df = df.dropna(subset=["prev_close"])
+        df["advancers"] = (df["close"] > df["prev_close"]).astype(int)
+        df["decliners"] = (df["close"] < df["prev_close"]).astype(int)
+        df["turnover"] = df["close"] * df["volume"]
+
+        daily = df.groupby("trade_date", as_index=False)[["advancers", "decliners", "turnover"]].sum()
+        total = daily["advancers"] + daily["decliners"]
+        daily["advance_ratio"] = np.where(total > 0, daily["advancers"] / total, np.nan)
+        daily["turnover_avg_5d"] = daily["turnover"].rolling(5, min_periods=5).mean()
+        daily["turnover_ratio_5d"] = np.where(
+            daily["turnover_avg_5d"] > 0,
+            daily["turnover"] / daily["turnover_avg_5d"],
+            np.nan,
+        )
+        daily["source"] = "local_kline_proxy"
+        daily["is_extreme_panic"] = daily.apply(_is_extreme_panic, axis=1)
+        daily["trade_date"] = daily["trade_date"].dt.strftime("%Y-%m-%d")
+
+        rows_out = [
+            {
+                "trade_date": r["trade_date"],
+                "advancers": float(r["advancers"]),
+                "decliners": float(r["decliners"]),
+                "advance_ratio": float(r["advance_ratio"]) if pd.notna(r["advance_ratio"]) else 0,
+                "turnover": float(r["turnover"]),
+                "turnover_avg_5d": float(r["turnover_avg_5d"]) if pd.notna(r["turnover_avg_5d"]) else 0,
+                "turnover_ratio_5d": float(r["turnover_ratio_5d"]) if pd.notna(r["turnover_ratio_5d"]) else 0,
+                "source": r["source"],
+                "is_extreme_panic": int(r["is_extreme_panic"]),
+            }
+            for _, r in daily.iterrows()
+        ]
+
+        try:
+            db_ops.upsert_market_regime_rows(rows_out)
+        except Exception as e:
+            return {"status": "error", "message": f"写库失败: {e}"}
+
+        msg = f"market_regime {len(rows_out)} 天 ({rows_out[0]['trade_date']} ~ {rows_out[-1]['trade_date']})"
+        return {
+            "status": "ok",
+            "message": msg,
+            "rows": len(rows_out),
+            "date_min": rows_out[0]["trade_date"],
+            "date_max": rows_out[-1]["trade_date"],
+        }