akg-factor-bridge/review_targets.py

116 lines
5.2 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

"""个股深度评析的目标名单(2026-09-09 方案附录甲):每早出计划时把主榜与观察档写进 153 库一张小表,
数据基座的 00:45 任务读它选目标(178 的容器打不到 155 的接口,只能走库)。
表 t_akg_review_targets:plan_date、ts_code(点后缀式 600000.SH)、source(main / observe / manual)、rank、name。
幂等:删该日行再整批插。写失败不拦计划(try 包住)。"""
from __future__ import annotations
import json
import os
import config
import db
TABLE = os.environ.get("REVIEW_TARGETS_TABLE", "t_akg_review_targets")
TOP_MAIN = int(os.environ.get("REVIEW_TARGETS_MAIN", "100")) # 主榜按原始分前一百只(跟着雷达走)
TOP_MAIN_RANK = int(os.environ.get("REVIEW_TARGETS_MAIN_RANK", "50")) # 主榜按新序前五十只(好公司报告保持新鲜)
TOP_OBS = int(os.environ.get("REVIEW_TARGETS_OBS", "20")) # 观察档前二十只
COLUMNS = ("plan_date", "ts_code", "source", "rank", "name")
_CREATE = """
CREATE TABLE IF NOT EXISTS {t} (
plan_date DATE NOT NULL,
ts_code VARCHAR(16) NOT NULL,
source VARCHAR(16) NOT NULL,
`rank` INT NOT NULL,
name VARCHAR(64),
PRIMARY KEY (plan_date, ts_code)
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4
"""
def to_dot(code: str) -> str:
s = (code or "").strip().upper()
if len(s) == 8 and s[:2] in ("SH", "SZ", "BJ") and s[2:].isdigit():
return f"{s[2:]}.{s[:2]}"
return s
def build_rows(ds: str, main_rows: list, obs_rows: list, user_rows=None) -> list[dict]:
from user_candidates import normalize
seen: set = set()
out: list[dict] = []
for src, rows in (("main", main_rows), ("observe", obs_rows), ("manual", user_rows)):
for i, r in enumerate(rows or [], 1):
try:
code = to_dot(normalize(r.get('code')))
except ValueError:
continue
if code in seen:
continue
seen.add(code)
out.append({"plan_date": ds, "ts_code": code, "source": src, "rank": i, "name": (r.get("name") or "")[:64]})
return out
def save(ds: str, rows: list, conn_factory=None) -> None:
factory = conn_factory or db.factor_conn
cols = ",".join(f"`{c}`" for c in COLUMNS)
marks = ",".join(["%s"] * len(COLUMNS))
payload = [tuple(r.get(c) for c in COLUMNS) for r in rows]
with factory() as conn:
with conn.cursor() as cur:
cur.execute(_CREATE.format(t=TABLE))
conn.commit()
with conn.cursor() as cur:
cur.execute(f"DELETE FROM {TABLE} WHERE plan_date = %s", (ds,))
if payload:
cur.executemany(f"INSERT INTO {TABLE} ({cols}) VALUES ({marks})", payload)
conn.commit()
def pick_main_targets(main_rows: list, axis: str, top_score: int, top_rank: int) -> list:
"""评析目标名单的主榜取法(纯函数,2026-09-17)。评析覆盖不能被排序轴锁死——只取新序前列的话,
新被指向的公司永远排在已评析公司后面、永远拿不到报告,所以名单要与排序轴解耦。
both(默认):按 score 降序前 top_score(跟着雷达走)∪ 按 rank 升序前 top_rank(好公司报告保持新鲜),
去重后按 rank 升序排。score:只按 score 降序前 top_score(逐字回旧)。"""
def _score(r):
return -(r.get("score") or 0.0)
def _rank(r):
return r.get("rank") if r.get("rank") is not None else 1 << 60
if axis != "both":
return sorted(main_rows, key=_score)[:top_score]
seen: set = set()
union: list = []
for r in sorted(main_rows, key=_score)[:top_score] + sorted(main_rows, key=_rank)[:top_rank]:
code = r.get("code")
if code not in seen:
seen.add(code)
union.append(r)
union.sort(key=_rank)
return union
def persist(ds: str, snap: dict, write=None, user_rows=None) -> dict:
"""目标是主榜(按 REVIEW_TARGETS_AXIS 取,both 是原始分前 TOP_MAIN ∪ 新序前 TOP_MAIN_RANK)加观察档前
TOP_OBS 只(快照里的 main / observe 已是新序全部行,每行带 score 与 rank),约一百二十到一百五十家。"""
main_sel = pick_main_targets(snap.get("main") or [], config.REVIEW_TARGETS_AXIS, TOP_MAIN, TOP_MAIN_RANK)
rows = build_rows(ds, main_sel, (snap.get("observe") or [])[:TOP_OBS],
snap.get('user_candidates', []) if user_rows is None else user_rows)
(write or save)(ds, rows)
n_main = sum(1 for r in rows if r["source"] == "main")
n_manual = sum(1 for r in rows if r['source'] == 'manual')
n_obs = len(rows) - n_main - n_manual
print(f" 评析目标名单 {ds}:主榜 {n_main},观察 {n_obs},人工关注 {n_manual},写入 {TABLE}")
return {"date": ds, "rows": len(rows), "main": n_main, 'observe': n_obs, 'manual': n_manual}
def from_plan_file(ds: str, plan_dir: str | None = None, write=None) -> dict:
"""从已生成的计划文件补写(手工入口 run.py review-targets --date)。"""
path = os.path.join(plan_dir or config.PLAN_SNAPSHOT_DIR, f"plan_{ds}.json")
with open(path, encoding="utf-8") as f:
snap = json.load(f)
return persist(ds, snap, write=write)