start experiment 58 (exp/58-signal-quality-gate-5-year-walk-forward)

2026-08-20 23:24:38 +00:00
parent fd5382caa4
commit e952feed0a
43 changed files with 2887 additions and 0 deletions
@@ -0,0 +1,117 @@
+"""Realized-IC circuit breaker TopkDropout strategy.
+
+Subclass of ``qlib.contrib.strategy.signal_strategy.TopkDropoutStrategy`` that
+holds the book (issues NO orders) while the streaming realized RankIC of the
+deployed signal is below threshold — i.e. the model's cross-sectional
+predictions are no longer earning against realized forward returns. When the
+gate is open it behaves exactly like the reference TopkDropoutStrategy.
+
+The gate is evaluated per trade step on the trailing mean realized RankIC of
+the signal over the last ``ic_window`` trading days whose label is fully
+realized as of the decision date (no lookahead — a 5d fwd label ``close[t+6]/
+close[t+1]-1`` is only known at ``t+6``).
+
+Two wiring modes:
+
+* ``ic_gate``: a precomputed ``pd.Series`` indexed by datetime of booleans
+  (True = gate open / trade allowed). Computed once by the caller (e.g.
+  ``rd_backtest``) and looked up per step. Missing dates default to open.
+* realized-IC self-computation: when ``ic_min_rankic`` is given but no
+  ``ic_gate``, the strategy computes the per-date realized RankIC itself from
+  ``self.signal`` (the pred scores) and the lake 1d bars via
+  ``tac_qlib.risk_limits.realized_rankic_series``, then applies the same
+  trailing-window comparison. Works when instantiated from a workflow YAML
+  PortAnaRecord config (``lake_root`` / ``market`` must be provided).
+"""
+
+from __future__ import annotations
+
+import pandas as pd
+
+from qlib.backtest.decision import TradeDecisionWO
+from qlib.contrib.strategy.signal_strategy import TopkDropoutStrategy
+
+from tac_qlib.risk_limits import ic_circuit_breaker, realized_rankic_series
+
+__all__ = ["ICGateTopkDropoutStrategy"]
+
+
+class ICGateTopkDropoutStrategy(TopkDropoutStrategy):
+    """TopkDropout with a streaming realized-IC circuit breaker.
+
+    Parameters
+    ----------
+    topk, n_drop, method_sell, method_buy, hold_thresh, only_tradable,
+    forbid_all_trade_at_limit : same as ``TopkDropoutStrategy``.
+    ic_min_rankic : float — pause new trading while trailing realized RankIC is
+        below this threshold (0 disables the gate).
+    ic_window : int — trailing window for the realized RankIC mean (default 22).
+    ic_label_horizon : int — label horizon in trading days (default 6).
+    ic_min_obs : int — min realized labels before the gate arms (default 10).
+    ic_gate : pd.Series, optional — precomputed per-date gate (bool indexed by
+        datetime). When provided, it overrides self-computation.
+    lake_root, market : str — lake location for self-computed realized IC.
+    """
+
+    def __init__(
+        self,
+        *,
+        topk,
+        n_drop,
+        ic_min_rankic: float = 0.0,
+        ic_window: int = 22,
+        ic_label_horizon: int = 6,
+        ic_min_obs: int = 10,
+        ic_gate=None,
+        lake_root: str = "",
+        market: str = "US",
+        **kwargs,
+    ):
+        super().__init__(topk=topk, n_drop=n_drop, **kwargs)
+        self.ic_min_rankic = float(ic_min_rankic or 0.0)
+        self.ic_window = int(ic_window or 22)
+        self.ic_label_horizon = int(ic_label_horizon or 6)
+        self.ic_min_obs = int(ic_min_obs or 10)
+        self._ic_gate = ic_gate
+        self._realized_ic = None
+        self.lake_root = lake_root or ""
+        self.market = market or "US"
+
+    def _load_realized_ic(self):
+        if self._realized_ic is None:
+            pred_start_time, pred_end_time = self.trade_calendar.get_step_time(
+                self.trade_calendar.get_trade_step(), shift=-self.ic_label_horizon
+            )
+            pred = self.signal.get_signal(start_time=pred_start_time, end_time=pred_end_time)
+            if isinstance(pred, pd.DataFrame):
+                pred = pred.iloc[:, 0]
+            self._realized_ic = realized_rankic_series(
+                pred, self.lake_root, self.market, label_horizon=self.ic_label_horizon
+            )
+        return self._realized_ic
+
+    def _gate_open(self, trade_start_time) -> bool:
+        ts = pd.Timestamp(trade_start_time)
+        if self._ic_gate is not None:
+            # precomputed gate series: look up the latest known decision date <= ts
+            known = self._ic_gate[self._ic_gate.index <= ts]
+            if len(known):
+                return bool(known.iloc[-1])
+            return True
+        if self.ic_min_rankic <= 0:
+            return True
+        realized = self._load_realized_ic()
+        limits = {
+            "ic_min_rankic": self.ic_min_rankic,
+            "ic_window": self.ic_window,
+            "ic_min_obs": self.ic_min_obs,
+        }
+        tripped, _reason, _trail = ic_circuit_breaker(realized, ts, limits)
+        return not tripped
+
+    def generate_trade_decision(self, execute_result=None):
+        trade_step = self.trade_calendar.get_trade_step()
+        trade_start_time, _ = self.trade_calendar.get_step_time(trade_step)
+        if not self._gate_open(trade_start_time):
+            return TradeDecisionWO([], self)
+        return super().generate_trade_decision(execute_result)