feat: B组挖掘加模拟验证门槛——好果率提升须通过模拟交易(胜率≥50%/收益>0)才算候选,防止扫描噪声当策略

evolution/b_group_miner.py

@@ -84,6 +84,45 @@ def scan3(market, regime, panel, min_n=500):
     return results[:5]
 
 
+def _simulate_verify(market, regime, panel, cond, tp=10, sl=5, maxh=20):
+    """模拟验证：候选条件在目标温区的模拟交易胜率/收益
+    返回 (trades, win_rate, avg_pnl) 或 None
+    """
+    rm = load_regime_map(market)
+    sub = panel.copy()
+    sub["_regime"] = sub["date"].map(rm)
+    sub = sub[(sub["_regime"] == regime) & cond].copy()
+    if len(sub) < 200:
+        return None
+    sub = sub.sort_values(["code", "date"])
+    trades = []
+    for code, g in sub.groupby("code"):
+        g = g.sort_values("date")
+        idxs = list(g.index)
+        for k, i in enumerate(idxs):
+            fut = g.iloc[k+1:k+maxh+1]
+            if len(fut) < 2:
+                continue
+            ep = g.loc[i, "close"]
+            if ep <= 0:
+                continue
+            res = None
+            for _, fb in fut.iterrows():
+                if fb["close"] <= ep * (1 - sl / 100):
+                    res = -sl
+                    break
+                if fb["close"] >= ep * (1 + tp / 100):
+                    res = tp
+                    break
+            if res is None:
+                res = (fut.iloc[-1]["close"] / ep - 1) * 100
+            trades.append(res)
+    if not trades:
+        return None
+    wins = [x for x in trades if x > 0]
+    return len(trades), len(wins) / len(trades) * 100, sum(trades) / len(trades)
+
+
 def to_entry(cond_dict):
     entry = {}
     for feat, (op, val) in cond_dict.items():
@@ -99,14 +138,33 @@ def mine(market="a", regimes=None):
     for rg in regimes:
         combos = scan3(market, rg, panel)
         for cond, n, rate, avg, extra in combos[:3]:
-            cand = {
-                "regime": rg, "market": market, "group": "B", "status": "candidate",
-                "entry": to_entry(cond), "trades_est": n, "good_rate": rate,
-                "avg60": avg, "excess_pp": extra,
-                "hypothesis": f"[{rg}] 由果及因三因子: {list(cond.keys())} → 60日前20%占比{rate}%(超额+{extra}pp)",
-            }
-            out["candidates"].append(cand)
-            print(f"  [{rg}] {list(cond.keys())} n={n} 好果率{rate}% 超额+{extra}pp")
+            # ── 模拟验证门槛（2026-08-16 教训：好果率≠能赚钱，须模拟胜率≥50%且收益>0）──
+            # 构造条件 Series
+            c = pd.Series(True, index=panel.index)
+            for feat, (op, val) in cond.items():
+                if feat not in panel.columns:
+                    c = None
+                    break
+                c &= (panel[feat] < val) if op == "<" else (panel[feat] > val)
+            verified = None
+            if c is not None:
+                verified = _simulate_verify(market, rg, panel, c)
+            if verified:
+                tn, twr, tavg = verified
+                if twr < 50 or tavg <= 0:
+                    print(f"  [{rg}] {list(cond.keys())} 模拟未达标(胜率{twr:.0f}%/均{tavg:.2f}%) 剔除", flush=True)
+                    continue
+                cand = {
+                    "regime": rg, "market": market, "group": "B", "status": "verified",
+                    "entry": to_entry(cond), "trades_est": n, "good_rate": rate,
+                    "avg60": avg, "excess_pp": extra,
+                    "sim_trades": tn, "sim_win_rate": round(twr, 1), "sim_avg_pnl": round(tavg, 2),
+                    "hypothesis": f"[{rg}] 由果及因三因子: {list(cond.keys())} → 好果率{rate}% 模拟胜率{twr:.0f}%/均{tavg:.2f}%",
+                }
+                out["candidates"].append(cand)
+                print(f"  [{rg}] {list(cond.keys())} ✅模拟达标 胜率{twr:.0f}% 均{tavg:.2f}%", flush=True)
+            else:
+                print(f"  [{rg}] {list(cond.keys())} 样本不足或条件无效 剔除", flush=True)
     return out