akg-factor-bridge/plan.py

"""每日选股计划（R4）：数据装配 / Markdown 渲染 / 产出，三段分离。

  collect()   -> dict   结构化计划——api.py 直接当 JSON 返回
  render_md() -> str    从 dict 渲染 Markdown
  generate()            CLI 与 cron 的入口：collect + render + 落盘 + 打印

数据全部来自已落库的表，不重算：
  平台因子表  t_factor_akg_score / _gate / _upside / _heat   —— 当日截面
  基座只读视图 v_factor_transmission                          —— 传导证据
  基座 industry_pools                                         —— 股票名称
升降档一节对比前一交易日的档位表——数据到达本身是信号（首次覆盖 /
新进传导链即升档）。
"""
import json
import os

import pandas as pd

import common
import config
import db


# 分数编码（与 factors.build_score 一致）：主榜 = 200 + 传导档位×20 + 组内分，
# 观察档 = 100 + 组内分，组内分 clip ±9.9。150 落在两带中间的空档上，用作分界。
_MAIN_MIN = 150.0


def _factor(table: str, ds: str) -> pd.Series:
    df = db.read_mysql(
        "factor",
        f"SELECT stock_code, factor_value FROM {table} WHERE trade_date = %s", (ds,))
    if df.empty:
        return pd.Series(dtype=float)
    return df.set_index("stock_code")["factor_value"].astype(float)


def _latest_date(table: str, upto: str | None = None):
    if upto:
        df = db.read_mysql(
            "factor", f"SELECT MAX(trade_date) d FROM {table} "
                      f"WHERE trade_date <= %s", (upto,))
    else:
        df = db.read_mysql("factor", f"SELECT MAX(trade_date) d FROM {table}")
    v = None if df.empty else df.iloc[0, 0]
    return None if v is None or pd.isna(v) else pd.Timestamp(v).date().isoformat()


def _prev_date(table: str, before: str):
    df = db.read_mysql(
        "factor", f"SELECT MAX(trade_date) d FROM {table} "
                  f"WHERE trade_date < %s", (before,))
    v = None if df.empty else df.iloc[0, 0]
    return None if v is None or pd.isna(v) else pd.Timestamp(v).date().isoformat()


def _names() -> dict:
    out = {}
    pools = db.read_pg("SELECT members FROM industry_pools")
    for _, r in pools.iterrows():
        ms = r["members"]
        if isinstance(ms, str):
            ms = json.loads(ms)
        for m in ms or []:
            ts, name = (m or {}).get("ts_code"), (m or {}).get("name")
            if ts and name:
                out.setdefault(common.to_prefix(ts), str(name))
    return out


def _evidence(ds: str):
    """每股最强一条传导证据：主题、源数、已动比例；另返回涉及的行情快照日。"""
    tr = db.read_pg(
        "SELECT ts_code, target, n_sources, moved_ratio, mkt_trade_date "
        "FROM v_factor_transmission WHERE scan_date = %s", (ds,))
    if tr.empty:
        return {}, set()
    tr["k"] = tr["ts_code"].map(common.to_prefix)
    tr["n_sources"] = pd.to_numeric(tr["n_sources"], errors="coerce").fillna(0)
    tr["moved_ratio"] = pd.to_numeric(tr["moved_ratio"], errors="coerce").fillna(0)
    tr["strength"] = tr["n_sources"] * (1.0 - tr["moved_ratio"])
    tr = tr.sort_values("strength", ascending=False).drop_duplicates("k")
    ev = {r.k: (str(r.target), int(r.n_sources), float(r.moved_ratio))
          for r in tr.itertuples()}
    days = {str(x) for x in tr["mkt_trade_date"].dropna().unique()}
    return ev, days


def _tier_label(score: float) -> str:
    return {0: "无传导", 1: "弱传导", 2: "强传导"}.get(
        int((score - 190.0) // 20), "?")


def _val(series: pd.Series, k: str):
    v = series.get(k)
    return None if v is None or pd.isna(v) else float(v)


def collect(date: str | None = None, top: int = 20, obs_top: int = 10,
            theme_cap: int = 5) -> dict:
    """装配一天的计划为结构化字典。数据缺失抛 RuntimeError（api 侧转 404）。"""
    ds = date or _latest_date("t_factor_akg_score")
    if not ds:
        raise RuntimeError("t_factor_akg_score 还没有数据——先 build akg_score。")
    score = _factor("t_factor_akg_score", ds)
    gate = _factor("t_factor_akg_gate", ds)
    if score.empty or gate.empty:
        raise RuntimeError(f"{ds} 缺 akg_score / akg_gate——先 build 该日再出计划。")
    upside = _factor("t_factor_akg_upside", ds)
    if upside.empty:
        # 当日 upside 表为空时现算兜底（as-of 口径不变：consensus<=当日、当日收盘价）
        import factors
        df_up = factors.build_upside(ds, ds)
        if df_up is not None and not df_up.empty:
            x = df_up.copy()
            x["k"] = x["stock_code"].map(common.to_prefix)
            upside = x.groupby("k")["factor_value"].max().astype(float)
    hd = _latest_date("t_factor_akg_heat", ds)
    heat = _factor("t_factor_akg_heat", hd) if hd else pd.Series(dtype=float)
    names = _names()
    ev, mkt_days = _evidence(ds)

    main = score[score >= _MAIN_MIN].sort_values(ascending=False)
    obs = score[score < _MAIN_MIN].sort_values(ascending=False)

    def _pick(ranked: pd.Series, n: int):
        """分数从高到低取 n 条；每个传导主题最多 theme_cap 条（0=不设限）——
        传导目标是环节级、同环节成员共享同一条证据，不限额会被少数环节刷屏。"""
        out, cnt = [], {}
        for k, s in ranked.items():
            e = ev.get(k)
            theme = e[0] if e else "（无传导）"
            if theme_cap and cnt.get(theme, 0) >= theme_cap:
                continue
            cnt[theme] = cnt.get(theme, 0) + 1
            out.append((k, s))
            if len(out) >= n:
                break
        return out

    def _row(rank: int, k: str, s: float, with_tier: bool) -> dict:
        e = ev.get(k)
        r = {"rank": rank, "code": k, "name": names.get(k),
             "score": round(float(s), 2),
             "evidence": ({"theme": e[0], "n_sources": e[1],
                           "moved_ratio": round(e[2], 4)} if e else None),
             "heat": _val(heat, k), "upside": _val(upside, k)}
        if with_tier:
            r["tier"] = _tier_label(s)
        return r

    changes = None
    prev_ds = _prev_date("t_factor_akg_gate", ds)
    if prev_ds:
        prev = _factor("t_factor_akg_gate", prev_ds)
        both = pd.concat([prev.rename("prev"), gate.rename("cur")],
                         axis=1).fillna(-1.0)          # -1 = 当日不在面板
        lab = {-1.0: "池外", 0.0: "不采纳", 1.0: "观察档", 2.0: "主榜"}
        up_df = both[both["cur"] > both["prev"]].sort_values("cur", ascending=False)
        down_df = both[both["cur"] < both["prev"]].sort_values("prev", ascending=False)

        # ---- 升降原因（07-31 加）：区分首次覆盖 / 估值转正 / 新进传导链等。
        # 依据前一日的 upside / 传导因子表；表空时现算兜底。原因是启发式归类
        # （取最主要的一条），精确审计以档位表与因子表为准。
        prev_up = _factor("t_factor_akg_upside", prev_ds)
        if prev_up.empty:
            try:
                import factors
                dfu = factors.build_upside(prev_ds, prev_ds)
                if dfu is not None and not dfu.empty:
                    x = dfu.copy()
                    x["k"] = x["stock_code"].map(common.to_prefix)
                    prev_up = x.groupby("k")["factor_value"].max().astype(float)
            except Exception:  # noqa: BLE001 —— 兜底失败则原因退化为通用文案
                pass
        prev_tr = _factor("t_factor_akg_transmission", prev_ds)
        # 赛道闸与风险闸的成员集合（07-31 修：赛道闸开启后，"不在赛道"曾被
        # 误标成"风险闸/档位调整"、"赛道锚生效"曾被误标成"新进传导链"）。
        # 两个集合都尊重各自开关：闸没开时对应原因自然不会出现。
        tset, risk = None, set()
        try:
            import factors
            tset = factors._track_set()   # noqa: SLF001 —— 同仓自用
            risk = factors._risk_set()    # noqa: SLF001
        except Exception:  # noqa: BLE001 —— 拿不到就退化为通用文案
            pass

        def _why(k: str, pg: float, cg: float) -> str:
            if cg == 2.0:                              # 升入主榜
                pu = _val(prev_up, k)
                if pu is None:
                    return "首次覆盖"
                return "估值转正" if pu < 0 else "重获资格"
            if cg == 1.0:                              # 升入观察档
                if k in ev:                            # 今天真在传导链上
                    pt = _val(prev_tr, k)
                    return "新进传导链" if pt is None or pt <= 0 else "档位调整"
                if tset is not None and k in tset:
                    return "赛道锚生效"                # 赛道成员身份给的锚（闸切换/成员变动）
                return "档位调整"
            if pg == 2.0:                              # 从主榜降出
                if k in risk:
                    return "风险闸"
                cu = _val(upside, k)
                if cu is None:
                    return "覆盖脱落"
                if cu < 0:
                    return "估值转负"
                if tset is not None and k not in tset:
                    return "赛道闸外"                  # 有覆盖也不贵，但不在十赛道内
                return "档位调整"
            if pg == 1.0:                              # 从观察档降出
                if k in risk:
                    return "风险闸"
                if k not in ev and (tset is None or k not in tset):
                    return "离开传导链"
                return "档位调整"
            return "出入面板"

        def _mv(d: pd.DataFrame):
            return [{"code": k, "name": names.get(k),
                     "from": lab.get(r["prev"], "?"), "to": lab.get(r["cur"], "?"),
                     "reason": _why(k, r["prev"], r["cur"])}
                    for k, r in d.iterrows()]

        changes = {"base_date": prev_ds,
                   "upgrades_total": int(len(up_df)),
                   "downgrades_total": int(len(down_df)),
                   "upgrades": _mv(up_df.head(15)),
                   "downgrades": _mv(down_df.head(15))}

    return {
        "date": ds,
        "counts": {"main": int(len(main)), "observe": int(len(obs)),
                   "gate_covered": int(len(gate))},
        "market_snapshot_days": sorted(mkt_days),
        "heat_date": hd,
        "theme_cap": theme_cap,
        "main": [_row(i, k, s, True)
                 for i, (k, s) in enumerate(_pick(main, top), 1)],
        "observe": [_row(i, k, s, False)
                    for i, (k, s) in enumerate(_pick(obs, obs_top), 1)],
        "changes": changes,
        "gate_on": bool(config.ENABLE_TRACK_GATE),
        "encoding": "主榜分=200+传导档位×20+组内分（还没热、还便宜）；"
                    "观察档分=100+0.6z(传导)+0.4z(−热度)",
    }


def _fmt_pct(v) -> str:
    return "—" if v is None else f"{v:+.0%}"


def _fmt_num(v) -> str:
    return "—" if v is None else f"{v:.2f}"


def _fmt_ev(e) -> str:
    if not e:
        return "—"
    return f"{e['theme']}（{e['n_sources']} 源，已动 {e['moved_ratio']:.0%}）"


def render_md(d: dict) -> str:
    L = [f"# 每日选股计划 · {d['date']}", ""]
    c = d["counts"]
    L.append(f"主榜 {c['main']} 只 / 观察档 {c['observe']} 只 / "
             f"全池档位覆盖 {c['gate_covered']} 只。")
    stale = [x for x in d["market_snapshot_days"] if x != d["date"]]
    if stale:
        L.append(f"注：本日传导用的行情快照 = {'、'.join(stale)}"
                 f"（与计划日不同——历史降级日口径）。")
    L.append("")

    cap_txt = f"，每主题限额 {d['theme_cap']}" if d["theme_cap"] else ""
    gate_txt = "、在十五五赛道内" if d.get("gate_on") else ""
    L.append(f"## 主榜 Top {len(d['main'])}"
             f"（有券商预期、目标价不低于现价{gate_txt}{cap_txt}）")
    L.append("")
    L.append("| # | 代码 | 名称 | 总分 | 档位 | 传导证据 | 热度 | 预期空间 |")
    L.append("|---|------|------|------|------|----------|------|----------|")
    for r in d["main"]:
        L.append(f"| {r['rank']} | {r['code']} | {r['name'] or '—'} | {r['score']:.1f} "
                 f"| {r['tier']} | {_fmt_ev(r['evidence'])} "
                 f"| {_fmt_num(r['heat'])} | {_fmt_pct(r['upside'])} |")
    L.append("")

    L.append(f"## 观察档 Top {len(d['observe'])}"
             f"（无券商预期、但{'在赛道或传导链上' if d.get('gate_on') else '在传导链上'}"
             f"——没有估值锚，置信度低{cap_txt}）")
    L.append("")
    L.append("| # | 代码 | 名称 | 分 | 传导证据 | 热度 |")
    L.append("|---|------|------|----|----------|------|")
    for r in d["observe"]:
        L.append(f"| {r['rank']} | {r['code']} | {r['name'] or '—'} | {r['score']:.1f} "
                 f"| {_fmt_ev(r['evidence'])} | {_fmt_num(r['heat'])} |")
    L.append("")

    L.append("## 今日升降档")
    L.append("")
    ch = d["changes"]
    if not ch:
        L.append("（没有更早的档位表可比，升降档从下一个交易日开始。）")
    else:
        L.append(f"对比 {ch['base_date']}：升档 {ch['upgrades_total']} 只，"
                 f"降档 {ch['downgrades_total']} 只。"
                 f"升档=拿到新锚（首次覆盖 / 新进传导链），本身就是值得看的信号。")
        if ch["upgrades"]:
            L.append("")
            L.append("**升档**：")
            L += [f"- {m['code']} {m['name'] or ''}：{m['from']} → {m['to']}"
                  f"（{m.get('reason', '—')}）"
                  for m in ch["upgrades"]]
            if ch["upgrades_total"] > len(ch["upgrades"]):
                L.append(f"- ……共 {ch['upgrades_total']} 只，其余见档位表")
        if ch["downgrades"]:
            L.append("")
            L.append("**降档**：")
            L += [f"- {m['code']} {m['name'] or ''}：{m['from']} → {m['to']}"
                  f"（{m.get('reason', '—')}）"
                  for m in ch["downgrades"]]
            if ch["downgrades_total"] > len(ch["downgrades"]):
                L.append(f"- ……共 {ch['downgrades_total']} 只，其余见档位表")
    L.append("")
    L.append("---")
    L.append(f"口径：{d['encoding']}。")
    return "\n".join(L)


def generate(date: str | None = None, top: int = 20, obs_top: int = 10,
             theme_cap: int = 5) -> str:
    try:
        data = collect(date, top, obs_top, theme_cap)
    except RuntimeError as e:
        raise SystemExit(str(e))
    text = render_md(data)
    os.makedirs("data/plan", exist_ok=True)
    out = f"data/plan/plan_{data['date']}.md"
    with open(out, "w", encoding="utf-8") as f:
        f.write(text + "\n")
    print(text)
    print(f"\n已写入 {out}")
    return out