MoFin/scripts/research/step42_atm_position.py

#!/usr/bin/env python3
"""step42_atm_position.py — 气氛分级仓位（保留信号量，控制风险）
不硬砍信号，改为按气氛分级仓位：
- 气氛好(新闻>=中位 + 连跌<=3): 满仓15%
- 气氛中(新闻>=中位 或 连跌<=3): 半仓8%
- 气氛差(新闻<中位 且 连跌>3): 迷你仓4% 或 不买
"""
import numpy as np
import pandas as pd
import sqlite3
import sys
sys.path.insert(0, "/tmp")
from sr_calculator import SRCalculator

print("=== 加载 ===", flush=True)
panel = pd.read_pickle("/tmp/panel_12d.pkl")
panel = panel.sort_values(["code", "date"]).reset_index(drop=True)
panel["_key"] = panel["code"] + "_" + panel["date"]
pos_map = {k: i for i, k in enumerate(panel["_key"])}
dates = sorted(panel["date"].unique())

conn = sqlite3.connect("file:/home/hmo/MoFin/data/mofin.db?mode=ro", uri=True)
idx_df = pd.read_sql("SELECT date, close, high FROM stock_daily WHERE code='sh000001' ORDER BY date", conn)
idx_df["date"] = idx_df["date"].astype(str)
idx_df["mkt_ret5"] = idx_df["close"].pct_change(5) * 100
idx_df["hi60"] = idx_df["high"].rolling(60).max()
idx_df["mkt_dd60"] = (idx_df["close"] / idx_df["hi60"] - 1) * 100
close_arr = idx_df["close"].values
down_days, streak, prev = [], 0, None
for c in close_arr:
    streak = streak + 1 if (prev is not None and c < prev) else 0
    down_days.append(streak)
    prev = c
idx_df["mkt_down_days"] = down_days
dd_map = dict(zip(idx_df["date"], idx_df["mkt_dd60"]))
down_map = dict(zip(idx_df["date"], idx_df["mkt_down_days"]))
panel["mkt_dd60"] = panel["date"].map(dd_map)
panel["mkt_down_days"] = panel["date"].map(down_map)

news_cnt = pd.read_sql("SELECT substr(date,1,10) d, COUNT(*) c FROM stock_news GROUP BY d", conn)
news_cnt["d"] = news_cnt["d"].astype(str)
news_cnt["mkt_news5"] = news_cnt["c"].rolling(5, min_periods=1).mean()
news_map = dict(zip(news_cnt["d"], news_cnt["mkt_news5"]))
panel["mkt_news5"] = panel["date"].map(lambda d: news_map.get(d, np.nan))

sig_pool = (
    (panel["mkt_rsi"] < 50) & (panel["mcap_q"] < 0.2) & (panel["pe_q"] < 0.2) &
    (panel["news3"] >= 1) & (panel["sec_ret20"] < 0) & (panel["bias60"] < -20) &
    (panel["mkt_dd60"] <= -5)
)
news_med = panel.loc[sig_pool, "mkt_news5"].median()
print("新闻中位:", news_med, flush=True)

# 气氛标签
panel["atm"] = "差"
panel.loc[(panel["mkt_news5"] >= news_med) & (panel["mkt_down_days"] <= 3), "atm"] = "好"
panel.loc[((panel["mkt_news5"] >= news_med) | (panel["mkt_down_days"] <= 3)) & (panel["atm"]=="差"), "atm"] = "中"

cand = panel[sig_pool][["code", "date", "atm"]].copy()
cand = cand.sort_values(["code", "date"])
cand["prev"] = cand.groupby("code")["date"].shift(1)
cand["gap"] = (pd.to_datetime(cand["date"]) - pd.to_datetime(cand["prev"])).dt.days
cand = cand[(cand["prev"].isna()) | (cand["gap"] > 30)]
print("信号:", len(cand), "气氛分布:", cand["atm"].value_counts().to_dict(), flush=True)

codes = cand["code"].unique().tolist()
ph = ",".join("?" * len(codes))
df = pd.read_sql("SELECT code, date, close, high, low FROM stock_daily WHERE code IN ({}) ORDER BY code, date".format(ph), conn, params=codes)
df["date"] = df["date"].astype(str)
df["code"] = df["code"].astype(str).str.zfill(6)
df = df.sort_values(["code", "date"]).reset_index(drop=True)
df["_key"] = df["code"] + "_" + df["date"]
dpos = {k: i for i, k in enumerate(df["_key"])}
closes = df["close"].values
highs = df["high"].values
lows = df["low"].values
cand["kidx"] = (cand["code"] + "_" + cand["date"]).map(dpos)
cand = cand.dropna(subset=["kidx"]).copy()
cand["kidx"] = cand["kidx"].astype(int)

sr = SRCalculator()
print("=== 计算支撑压力 ===", flush=True)
sig_list = []
for r in cand.itertuples():
    bars_code = sr.get_bars(r.code)
    d_idx = bars_code.index[bars_code["date"] == r.date]
    if len(d_idx) == 0:
        continue
    sr_full = sr.sr_full(r.code, d_idx[0])
    pv = sr_full["pivot"]
    chip = sr_full["chip"]
    if not pv:
        continue
    sig_close = closes[r.kidx]
    support = pv["s2"]
    if chip and chip["chip_ss"] < sig_close:
        support = max(pv["s2"], chip["chip_ss"])
    resist = pv["r2"]
    if chip and chip["chip_sr"] > sig_close:
        resist = min(pv["r2"], chip["chip_sr"])
    if support >= sig_close or resist <= sig_close:
        continue
    sig_list.append({"code": r.code, "date": r.date, "kidx": r.kidx, "atm": r.atm,
                     "sig_close": sig_close, "support": support, "resist": resist})

sigdf = pd.DataFrame(sig_list)
print("有支撑压力:", len(sigdf), flush=True)
sig_by_date = {}
for r in sigdf.itertuples():
    sig_by_date.setdefault(r.date, []).append(r)

def run_sim(pos_map_atm, max_daily=5, slots=10, hold=40, stop_buf=0.05):
    """pos_map_atm: {'好':0.15, '中':0.08, '差':0.04}"""
    INIT_CAP = 1_000_000
    positions = {}
    cash = INIT_CAP
    navs = []
    for di, d in enumerate(dates):
        for code in list(positions.keys()):
            pos = positions[code]
            k = dpos.get(code + "_" + d)
            if k is None:
                continue
            hi, lo, cl = highs[k], lows[k], closes[k]
            exited = False
            if hi >= pos["tp"]:
                sell_qty = pos["qty"] // 2
                if sell_qty > 0:
                    cash += sell_qty * pos["tp"]
                    pos["qty"] -= sell_qty
                if pos["qty"] <= 0:
                    del positions[code]
                    exited = True
            if not exited and lo <= pos["stop"]:
                cash += pos["qty"] * lo
                del positions[code]
                exited = True
            if not exited and di - pos["entry_di"] >= hold:
                cash += pos["qty"] * cl
                del positions[code]
        if d in sig_by_date:
            bought = 0
            for r in sig_by_date[d]:
                if bought >= max_daily or len(positions) >= slots:
                    break
                if r.code in positions:
                    continue
                cur_nav = cash
                for c, p in positions.items():
                    k = dpos.get(c + "_" + d)
                    px = closes[k] if k is not None else p["avg_cost"]
                    cur_nav += p["qty"] * px
                pos_val = cur_nav * pos_map_atm.get(r.atm, 0.05)
                price = r.sig_close
                if price <= 0:
                    continue
                qty = int(pos_val / price)
                if qty <= 0 or qty * price > cash:
                    continue
                cash -= qty * price
                positions[r.code] = {
                    "entry_di": di, "qty": qty, "avg_cost": price,
                    "stop": r.support * (1 - stop_buf), "tp": r.resist,
                }
                bought += 1
        nav = cash
        for c, p in positions.items():
            k = dpos.get(c + "_" + d)
            px = closes[k] if k is not None else p["avg_cost"]
            nav += p["qty"] * px
        navs.append(nav)
    nav_arr = np.array(navs)
    final = nav_arr[-1]
    years = len(navs) / 250
    cagr = ((final / INIT_CAP) ** (1 / years) - 1) * 100 if final > 0 else -100
    cummax = np.maximum.accumulate(nav_arr)
    dd = ((nav_arr - cummax) / cummax).min() * 100
    cash_ratio = np.mean([1 for _ in navs])  # placeholder
    return cagr, dd

print("\n=== 气氛分级仓位 ===", flush=True)
# 方案1: 好15/中8/差4
c, d = run_sim({"好": 0.15, "中": 0.08, "差": 0.04})
print("好15/中8/差4: 年化={:.2f}% 回撤={:.1f}%".format(c, d), flush=True)
# 方案2: 好15/中10/差6
c, d = run_sim({"好": 0.15, "中": 0.10, "差": 0.06})
print("好15/中10/差6: 年化={:.2f}% 回撤={:.1f}%".format(c, d), flush=True)
# 方案3: 好15/中12/差8
c, d = run_sim({"好": 0.15, "中": 0.12, "差": 0.08})
print("好15/中12/差8: 年化={:.2f}% 回撤={:.1f}%".format(c, d), flush=True)
# 方案4: 好15/中15/差0（只差气氛不买）
c, d = run_sim({"好": 0.15, "中": 0.15, "差": 0.0})
print("好15/中15/差0: 年化={:.2f}% 回撤={:.1f}%".format(c, d), flush=True)
# 方案5: 全部15（基准，无分级）
c, d = run_sim({"好": 0.15, "中": 0.15, "差": 0.15})
print("全部15(基准): 年化={:.2f}% 回撤={:.1f}%".format(c, d), flush=True)

print("\n=== 完成 ===", flush=True)