hmo
b9c68a83a7
- 新增 strategy_research_methodology.md（由果及因/12维/铁律/支撑压力规范） - 新增 predictive_oversold_strategy.md（v5定稿，年化18.57%） - 新增 deployment-plan-predictive-oversold.md（整合部署计划） - 归档 docs/research/（63份研究过程文档）+ scripts/research/（19个研究脚本） - 更新 docs/README.md 文档中心（策略研究章节）
199 lines
7.6 KiB
Python
199 lines
7.6 KiB
Python
#!/usr/bin/env python3
|
||
"""step37_final_v3.py — 最终模拟 v3（阶段过滤 + 支撑压力 + 最优参数）
|
||
规则（全部数据驱动）：
|
||
- 信号: 预测信号 + 大盘阶段过滤（排除高位/牛市）
|
||
保留: mkt_dd60 <= -5（大盘已回撤，非高位）
|
||
- 入场: 信号日收盘买
|
||
- 止损: 支撑下方5%（step34验证）
|
||
- 止盈: 压力位分批卖
|
||
- 兜底: 40日
|
||
- 资金: 10槽 + 15%仓位（step35最优）
|
||
"""
|
||
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())
|
||
|
||
# 大盘回撤
|
||
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["hi60"] = idx_df["high"].rolling(60).max()
|
||
idx_df["mkt_dd60"] = (idx_df["close"] / idx_df["hi60"] - 1) * 100
|
||
dd_map = dict(zip(idx_df["date"], idx_df["mkt_dd60"]))
|
||
panel["mkt_dd60"] = panel["date"].map(dd_map)
|
||
|
||
# 信号：预测信号 + 阶段过滤（大盘已回撤，非高位）
|
||
sig_cond = (
|
||
(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) # 阶段过滤：大盘已回撤(排除高位/牛市)
|
||
)
|
||
cand = panel[sig_cond][["code", "date"]].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)]
|
||
cand["year"] = cand["date"].str[:4]
|
||
print("信号(含阶段过滤):", len(cand), flush=True)
|
||
print("月均: {:.1f}".format(len(cand)/max(len(cand["year"].unique()),1)/12), flush=True)
|
||
print("分年:", {str(y): int(c) for y, c in cand["year"].value_counts().sort_index().items()}, 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)
|
||
print("可定位:", len(cand), flush=True)
|
||
|
||
# 支撑压力
|
||
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,
|
||
"sig_close": sig_close, "support": support, "resist": resist})
|
||
|
||
sigdf = pd.DataFrame(sig_list)
|
||
print("有支撑压力:", len(sigdf), flush=True)
|
||
|
||
# ── 模拟（10槽+40日+15%+支撑保护）──
|
||
INIT_CAP = 1_000_000
|
||
SLOTS = 10
|
||
HOLD = 40
|
||
POS_FRAC = 0.15
|
||
STOP_BUF = 0.05
|
||
|
||
sig_by_date = {}
|
||
for r in sigdf.itertuples():
|
||
sig_by_date.setdefault(r.date, []).append(r)
|
||
|
||
positions = {}
|
||
cash = INIT_CAP
|
||
nav_history = []
|
||
trades = []
|
||
|
||
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]
|
||
if hi >= pos["tp"]:
|
||
sell_qty = pos["qty"] // 2
|
||
if sell_qty > 0:
|
||
cash += sell_qty * pos["tp"]
|
||
pos["qty"] -= sell_qty
|
||
trades.append({"code": code, "date": d, "ret": (pos["tp"]/pos["avg_cost"]-1)*100, "reason": "tp"})
|
||
if pos["qty"] <= 0:
|
||
del positions[code]
|
||
continue
|
||
if lo <= pos["stop"]:
|
||
cash += pos["qty"] * lo
|
||
trades.append({"code": code, "date": d, "ret": (lo/pos["avg_cost"]-1)*100, "reason": "stop"})
|
||
del positions[code]
|
||
continue
|
||
if di - pos["entry_di"] >= HOLD:
|
||
cash += pos["qty"] * cl
|
||
trades.append({"code": code, "date": d, "ret": (cl/pos["avg_cost"]-1)*100, "reason": "hold40"})
|
||
del positions[code]
|
||
continue
|
||
|
||
if d in sig_by_date:
|
||
for r in sig_by_date[d]:
|
||
if 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_FRAC
|
||
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,
|
||
}
|
||
|
||
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
|
||
nav_history.append({"date": d, "nav": nav, "n_pos": len(positions), "cash": cash})
|
||
|
||
nav_df = pd.DataFrame(nav_history)
|
||
nav_df.to_csv("/tmp/step37_nav.csv", index=False)
|
||
tr_df = pd.DataFrame(trades)
|
||
tr_df.to_csv("/tmp/step37_trades.csv", index=False)
|
||
|
||
final_nav = nav_df["nav"].iloc[-1]
|
||
total_ret = (final_nav / INIT_CAP - 1) * 100
|
||
years = (pd.to_datetime(nav_df["date"].iloc[-1]) - pd.to_datetime(nav_df["date"].iloc[0])).days / 365
|
||
cagr = ((final_nav / INIT_CAP) ** (1 / years) - 1) * 100 if years > 0 else 0
|
||
cummax = nav_df["nav"].cummax()
|
||
dd = (nav_df["nav"] / cummax - 1) * 100
|
||
max_dd = dd.min()
|
||
print("\n=== 最终v3（阶段过滤）结果 ===", flush=True)
|
||
print("总收益: {:.1f}%".format(total_ret))
|
||
print("年化(CAGR): {:.2f}%".format(cagr))
|
||
print("最大回撤: {:.1f}%".format(max_dd))
|
||
print("持仓峰值: {}".format(nav_df["n_pos"].max()))
|
||
print("交易笔数: {}".format(len(tr_df)))
|
||
if len(tr_df) > 0:
|
||
print("平均收益: {:.2f}% 胜率: {:.1f}%".format(tr_df["ret"].mean(), (tr_df["ret"]>0).mean()*100))
|
||
print("卖出原因:", tr_df["reason"].value_counts().to_dict())
|
||
nav_df["year"] = nav_df["date"].str[:4]
|
||
yr_end = nav_df.groupby("year")["nav"].last()
|
||
print("\n分年净值:")
|
||
for y, v in yr_end.items():
|
||
print(" {}: {:.0f} ({}%)".format(y, v, (v/INIT_CAP-1)*100))
|
||
print("现金占比均值: {:.1f}%".format((nav_df["cash"]/nav_df["nav"]).mean()*100))
|
||
print("\n=== 完成 ===", flush=True)
|