finish experiment 25 (exp/25-test-the-clean-data-hypothesis-that-addi)

code/MANIFEST.txt

@@ -1,31 +1,19 @@
 # TradeAC custom-qlib-code snapshot (auto-generated)
-# parent repo HEAD : fccac3e792e2a6c5e72e63ca20a0eb4b8713d561
+# parent repo HEAD : 93cb283ef322fefcf7f583168eec5648dc95d858
 #   tac-qlib/tac_qlib/contrib
 #   tac-qlib/tac_qlib/data
 # per-file hashes (git hash-object):
   1b6298c4a5652f2e863cbdc385a1014a570fcd59  tac-qlib/tac_qlib/contrib/__init__.py
-  b419ee55ed455a1c45423d1c9025ca5cc0a98576  tac-qlib/tac_qlib/contrib/__pycache__/__init__.cpython-312.pyc
   c76a9f17f680e74eea766eff27f7624359749ed6  tac-qlib/tac_qlib/contrib/data/__init__.py
-  2f6c67620aa2f9e6aaaef3369361d9b3eac3d6ca  tac-qlib/tac_qlib/contrib/data/__pycache__/__init__.cpython-312.pyc
-  fdd5923a70a399e8680913593ff111641947898e  tac-qlib/tac_qlib/contrib/data/__pycache__/handler.cpython-312.pyc
   0dd25ef161c6e0f15eafc84886e7e1381deb38c3  tac-qlib/tac_qlib/contrib/data/handler.py
   b151d139a0dcde87d74b21e7c4b729176ba5c39b  tac-qlib/tac_qlib/contrib/model/__init__.py
-  08dec87ccdf6bb5d2cf611ca3032a4280aaab8cf  tac-qlib/tac_qlib/contrib/model/__pycache__/__init__.cpython-312.pyc
-  6fb61946ea9a83dfb560de3717f5fbf482c4c00e  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_ensemble.cpython-312.pyc
-  3e80f2e08b661ddd2f58ffe5a6196063fa41ae51  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_gbdt.cpython-312.pyc
   d3f051f3a8650c42fedc7b367b966f7c74fb5789  tac-qlib/tac_qlib/contrib/model/rank_ensemble.py
-  d03e6611338918d4aac5eea4adf26f85a3763652  tac-qlib/tac_qlib/contrib/model/rank_gbdt.py
+  ccfe7d554989aa7f3e5a2128ae663e51b2207149  tac-qlib/tac_qlib/contrib/model/rank_gbdt.py
-  c4ef84ffda2a611262412fe1127689c667f3d0c1  tac-qlib/tac_qlib/contrib/strategy/__init__.py
+  4afcf9058231111c412925f4c4b84e81d656db87  tac-qlib/tac_qlib/contrib/strategy/__init__.py
-  6ad10c2ebe37c16417e67c7aeb731ad1fcb6da2f  tac-qlib/tac_qlib/contrib/strategy/__pycache__/__init__.cpython-312.pyc
-  8d684b3216b040071d9ee4fa920a0e0c7486d278  tac-qlib/tac_qlib/contrib/strategy/__pycache__/optimal_stop.cpython-312.pyc
-  896ef74ae47bcd1ed388e1e5d9c8d70c28097fe9  tac-qlib/tac_qlib/contrib/strategy/kelly_dropout.py
   79aaad9e39fcc740a773f4f63c512ce1086cfde0  tac-qlib/tac_qlib/contrib/strategy/optimal_stop.py
-  5b9acfb4340111b204249add7760bd53c6ae03f1  tac-qlib/tac_qlib/contrib/strategy/regime_gate.py
-  aa1ee880d52ceb5821d65973962099c2254f710a  tac-qlib/tac_qlib/contrib/strategy/top_bottom.py
-  fe60bacdfedd48617863be31f24b7c7daebfac5a  tac-qlib/tac_qlib/contrib/strategy/weekly_rebalance.py
   92e6e90eb0cd0a25142034560f27adb6b705b1a8  tac-qlib/tac_qlib/data/__init__.py
-  7c4e6c345fad1978efe8860c0d977d0c02d6f8d9  tac-qlib/tac_qlib/data/__pycache__/__init__.cpython-312.pyc
+  3cbc0686e6f863d306d93c589a607a5bdb7201f2  tac-qlib/tac_qlib/data/__pycache__/__init__.cpython-312.pyc
-  99e602392d51663cb06d5c425000b1ed1e5a916b  tac-qlib/tac_qlib/data/__pycache__/config.cpython-312.pyc
+  46bcdbcc173ff3a6281fed33d10c1bcac96876b0  tac-qlib/tac_qlib/data/__pycache__/config.cpython-312.pyc
-  020dcdcf288e4832c8cf2386351f78d5ceb4fe13  tac-qlib/tac_qlib/data/__pycache__/providers.cpython-312.pyc
+  6df4f88af22ab4c026c14ef1835f2e630cdf850c  tac-qlib/tac_qlib/data/__pycache__/providers.cpython-312.pyc
   53c9007a928841fd3c3b08450f9a6520ce1ac091  tac-qlib/tac_qlib/data/config.py
   8d0644f6f0d1efb94798ed444cc73e63b643459b  tac-qlib/tac_qlib/data/providers.py

code/tac-qlib/tac_qlib/contrib/model/rank_gbdt.py

@@ -53,61 +53,23 @@ from qlib.workflow import R
 __all__ = ["RankICLGBModel", "rankic_feval"]
 
 
-def _group_averaged_rank(values: np.ndarray, gid: np.ndarray, offs: np.ndarray) -> np.ndarray:
-    """Averaged (tie-corrected) rank of ``values`` within each group, vectorized.
-
-    ``gid`` maps each row to its group id; ``offs`` holds the cumulative row
-    offsets so that group ``i`` occupies rows ``[offs[i], offs[i+1])``. Returns
-    the same result as ``pandas.Series.rank(method='average')`` applied per
-    group, but in one pass (``np.lexsort`` is the only non-linear step).
-    """
-    n = len(values)
-    order = np.lexsort((values, gid))
-    ord_rank = np.empty(n, dtype=np.float64)
-    ord_rank[order] = np.arange(n, dtype=np.float64) - offs[gid[order]] + 1.0
-    sg = gid[order]
-    sv = values[order]
-    newblock = np.empty(n, dtype=bool)
-    newblock[0] = True
-    newblock[1:] = (sg[1:] != sg[:-1]) | (sv[1:] != sv[:-1])
-    blockid = np.cumsum(newblock) - 1
-    block_mean = np.bincount(blockid, weights=ord_rank[order]) / np.bincount(blockid)
-    out = np.empty(n)
-    out[order] = block_mean[blockid]
-    return out
-
-
 def _per_day_spearman(preds: np.ndarray, labels: np.ndarray, group: np.ndarray) -> float:
     """Mean per-day Spearman rank correlation of preds vs labels.
 
     ``group`` holds the number of rows of each trading day (query group), in
     order. Days with <3 valid rows or a constant pred/label are skipped.
-
-    Vectorized: per-day Spearman == Pearson of the per-day rank transforms,
-    and the Pearson moments (``sum``, ``sum`` of products/squares) aggregate
-    over each day with ``np.bincount``. Runs ~10x faster than the per-day
-    ``pd.Series.rank()`` loop that preceded it — this feval is invoked on the
-    train and valid panels every boosting round, per seed.
     """
     if group is None or len(group) == 0:
         return 0.0
     offs = np.concatenate([[0], np.cumsum(group.astype(int))])
-    gid = np.repeat(np.arange(len(group)), group.astype(int))
+    vals = []
-    rp = _group_averaged_rank(preds, gid, offs)
+    for i in range(len(group)):
-    rl = _group_averaged_rank(labels, gid, offs)
+        s = slice(offs[i], offs[i + 1])
-    n_g = group.astype(float)
+        p, l = preds[s], labels[s]
-    s_p = np.bincount(gid, weights=rp)
+        if len(p) < 3 or np.std(p) == 0 or np.std(l) == 0:
-    s_l = np.bincount(gid, weights=rl)
+            continue
-    s_pl = np.bincount(gid, weights=rp * rl)
+        vals.append(np.corrcoef(pd.Series(p).rank(), pd.Series(l).rank())[0, 1])
-    s_pp = np.bincount(gid, weights=rp * rp)
+    return float(np.mean(vals)) if vals else 0.0
-    s_ll = np.bincount(gid, weights=rl * rl)
-    cov = n_g * s_pl - s_p * s_l
-    var_p = n_g * s_pp - s_p ** 2
-    var_l = n_g * s_ll - s_l ** 2
-    denom = np.sqrt(var_p * var_l)
-    valid = (n_g >= 3) & (denom > 0)
-    corr = np.where(valid, cov / np.where(denom == 0, 1, denom), 0.0)
-    return float(corr[valid].mean()) if valid.any() else 0.0
 
 
 def rankic_feval(preds, dataset):

code/tac-qlib/tac_qlib/contrib/strategy/__init__.py

@@ -1,13 +1,3 @@
-from .kelly_dropout import FractionalKellyDropoutStrategy  # noqa: F401
 from .optimal_stop import OptimalStopControl  # noqa: F401
-from .regime_gate import RegimeGateDropoutStrategy  # noqa: F401
-from .top_bottom import TopBottomDropoutStrategy  # noqa: F401
-from .weekly_rebalance import WeeklyRebalanceDropoutStrategy  # noqa: F401
 
-__all__ = [
+__all__ = ["OptimalStopControl"]
-    "OptimalStopControl",
-    "FractionalKellyDropoutStrategy",
-    "WeeklyRebalanceDropoutStrategy",
-    "TopBottomDropoutStrategy",
-    "RegimeGateDropoutStrategy",
-]

code/tac-qlib/tac_qlib/contrib/strategy/kelly_dropout.py

@@ -1,201 +0,0 @@
-"""Fractional-Kelly dropout strategy for cross-sectional signals.
-
-Sizing rule variant of ``qlib.contrib.strategy.signal_strategy.TopkDropoutStrategy``:
-the topk/n_drop SELECTION is identical to the reference, but the buy size is
-proportional to the score MAGNITUDE (edge) instead of equal-weight, capped at a
-fraction ``cap_frac`` of the equal-weight notional so a single name cannot
-over-concentrate the book.
-
-``cap_frac`` is the fraction of the equal-weight per-name notional that a top
-signal can deploy at most (e.g. 0.5 = at most half the equal-weight size).
-Names whose score is below the median of the buy set get a proportionally
-smaller slice; the residual stays in cash (that is the point of the rule:
-throw away less edge per name, deploy less capital when conviction is low).
-"""
-
-from __future__ import annotations
-
-from typing import List
-
-import numpy as np
-import pandas as pd
-
-from qlib.backtest import Order
-from qlib.backtest.decision import OrderDir, TradeDecisionWO
-from qlib.contrib.strategy.signal_strategy import TopkDropoutStrategy
-
-__all__ = ["FractionalKellyDropoutStrategy"]
-
-DEFAULT_CAP_FRAC = 0.5
-
-
-class FractionalKellyDropoutStrategy(TopkDropoutStrategy):
-    """TopkDropout selection with score-magnitude (fractional-Kelly) sizing.
-
-    Parameters
-    ----------
-    topk, n_drop, method_sell, method_buy, hold_thresh, only_tradable,
-    forbid_all_trade_at_limit : same as ``TopkDropoutStrategy``.
-    cap_frac : max buy notional as a fraction of the equal-weight notional.
-    """
-
-    def __init__(self, *, topk, n_drop, cap_frac: float = DEFAULT_CAP_FRAC, **kwargs):
-        super().__init__(topk=topk, n_drop=n_drop, **kwargs)
-        self.cap_frac = cap_frac
-
-    def generate_trade_decision(self, execute_result=None):
-        import copy
-
-        trade_step = self.trade_calendar.get_trade_step()
-        trade_start_time, trade_end_time = self.trade_calendar.get_step_time(trade_step)
-        pred_start_time, pred_end_time = self.trade_calendar.get_step_time(trade_step, shift=1)
-        pred_score = self.signal.get_signal(start_time=pred_start_time, end_time=pred_end_time)
-        if isinstance(pred_score, pd.DataFrame):
-            pred_score = pred_score.iloc[:, 0]
-        if pred_score is None:
-            return TradeDecisionWO([], self)
-
-        if self.only_tradable:
-
-            def get_first_n(li, n, reverse=False):
-                cur_n = 0
-                res = []
-                for si in reversed(li) if reverse else li:
-                    if self.trade_exchange.is_stock_tradable(
-                        stock_id=si, start_time=trade_start_time, end_time=trade_end_time
-                    ):
-                        res.append(si)
-                        cur_n += 1
-                        if cur_n >= n:
-                            break
-                return res[::-1] if reverse else res
-
-            def get_last_n(li, n):
-                return get_first_n(li, n, reverse=True)
-
-            def filter_stock(li):
-                return [
-                    si
-                    for si in li
-                    if self.trade_exchange.is_stock_tradable(
-                        stock_id=si, start_time=trade_start_time, end_time=trade_end_time
-                    )
-                ]
-
-        else:
-
-            def get_first_n(li, n):
-                return list(li)[:n]
-
-            def get_last_n(li, n):
-                return list(li)[-n:]
-
-            def filter_stock(li):
-                return li
-
-        current_temp: "object" = copy.deepcopy(self.trade_position)
-        sell_order_list: List[Order] = []
-        buy_order_list: List[Order] = []
-        cash = current_temp.get_cash()
-        current_stock_list = current_temp.get_stock_list()
-        last = pred_score.reindex(current_stock_list).sort_values(ascending=False).index
-
-        if self.method_buy == "top":
-            today = get_first_n(
-                pred_score[~pred_score.index.isin(last)].sort_values(ascending=False).index,
-                self.n_drop + self.topk - len(last),
-            )
-        elif self.method_buy == "random":
-            topk_candi = get_first_n(pred_score.sort_values(ascending=False).index, self.topk)
-            candi = list(filter(lambda x: x not in last, topk_candi))
-            n = self.n_drop + self.topk - len(last)
-            try:
-                today = np.random.choice(candi, n, replace=False)
-            except ValueError:
-                today = candi
-        else:
-            raise NotImplementedError(f"This type of input is not supported")
-
-        comb = pred_score.reindex(last.union(pd.Index(today))).sort_values(ascending=False).index
-
-        if self.method_sell == "bottom":
-            sell = last[last.isin(get_last_n(comb, self.n_drop))]
-        elif self.method_sell == "random":
-            candi = filter_stock(last)
-            try:
-                sell = pd.Index(np.random.choice(candi, self.n_drop, replace=False) if len(last) else [])
-            except ValueError:
-                sell = candi
-        else:
-            raise NotImplementedError(f"This type of input is not supported")
-
-        buy = today[: len(sell) + self.topk - len(last)]
-        for code in current_stock_list:
-            if not self.trade_exchange.is_stock_tradable(
-                stock_id=code,
-                start_time=trade_start_time,
-                end_time=trade_end_time,
-                direction=None if self.forbid_all_trade_at_limit else OrderDir.SELL,
-            ):
-                continue
-            if code in sell:
-                time_per_step = self.trade_calendar.get_freq()
-                if current_temp.get_stock_count(code, bar=time_per_step) < self.hold_thresh:
-                    continue
-                sell_amount = current_temp.get_stock_amount(code=code)
-                sell_order = Order(
-                    stock_id=code,
-                    amount=sell_amount,
-                    start_time=trade_start_time,
-                    end_time=trade_end_time,
-                    direction=Order.SELL,
-                )
-                if self.trade_exchange.check_order(sell_order):
-                    sell_order_list.append(sell_order)
-                    trade_val, trade_cost, trade_price = self.trade_exchange.deal_order(
-                        sell_order, position=current_temp
-                    )
-                    cash += trade_val - trade_cost
-
-        if len(buy) == 0:
-            return TradeDecisionWO(sell_order_list, self)
-
-        # ---- fractional-Kelly sizing --------------------------------------
-        # equal-weight notional (reference baseline)
-        eq_notional = cash * self.risk_degree / len(buy)
-        buy_scores = pred_score.reindex(buy).astype(float)
-        lo, hi = buy_scores.min(), buy_scores.max()
-        if hi == lo:
-            w = pd.Series(1.0, index=buy_scores.index)
-        else:
-            w = (buy_scores - lo) / (hi - lo)  # [0,1] edge magnitude
-            w = w.clip(lower=0.0)
-            w_max = w.max()
-            w = w / w_max if w_max > 0 else w  # max == 1.0
-        for code in buy:
-            if not self.trade_exchange.is_stock_tradable(
-                stock_id=code,
-                start_time=trade_start_time,
-                end_time=trade_end_time,
-                direction=None if self.forbid_all_trade_at_limit else OrderDir.BUY,
-            ):
-                continue
-            buy_price = self.trade_exchange.get_deal_price(
-                stock_id=code, start_time=trade_start_time, end_time=trade_end_time, direction=OrderDir.BUY
-            )
-            notional = eq_notional * min(self.cap_frac, float(w.get(code, 0.0)))
-            buy_amount = notional / buy_price
-            factor = self.trade_exchange.get_factor(
-                stock_id=code, start_time=trade_start_time, end_time=trade_end_time
-            )
-            buy_amount = self.trade_exchange.round_amount_by_trade_unit(buy_amount, factor)
-            buy_order = Order(
-                stock_id=code,
-                amount=buy_amount,
-                start_time=trade_start_time,
-                end_time=trade_end_time,
-                direction=Order.BUY,
-            )
-            buy_order_list.append(buy_order)
-
-        return TradeDecisionWO(sell_order_list + buy_order_list, self)

code/tac-qlib/tac_qlib/contrib/strategy/regime_gate.py

@@ -1,231 +0,0 @@
-"""HMM-regime overlay TopkDropout strategy.
-
-Regime-gate overlay on ``qlib.contrib.strategy.signal_strategy.TopkDropoutStrategy``:
-selection and sizing are identical to the reference, but a name is only BOUGHT
-(entry gate) when its per-symbol HMM regime posterior ``sp_hmm_p_regime1`` on
-the signal date is >= ``regime_threshold``; otherwise it is held in cash instead
-of being opened.
-
-The regime posterior is read from the lake feature provider on the fly via
-``qlib.data.D.features`` (field ``$sp_hmm_p_regime1``) for the signal window, so
-no regime column needs to enter the model's ``feature_fields`` — the gate is a
-pure overlay (book ch.01: regime flags regressed as model features, survived
-only as an overlay). The HMM itself was fit with ``fit_end=<train end>`` when
-the lake features were backfilled, so there is no lookahead.
-
-Names already held are NOT force-sold when the regime turns unfavourable
-(entry gate only, matching the queue-10 design).
-"""
-
-from __future__ import annotations
-
-from typing import List
-
-import numpy as np
-import pandas as pd
-
-from qlib.backtest import Order
-from qlib.backtest.decision import OrderDir, TradeDecisionWO
-from qlib.contrib.strategy.signal_strategy import TopkDropoutStrategy
-
-try:
-    from qlib.data import D
-except ImportError:  # pragma: no cover - qlib always present in this stack
-    D = None
-
-__all__ = ["RegimeGateDropoutStrategy"]
-
-DEFAULT_REGIME_THRESHOLD = 0.5
-REGIME_FIELD = "$sp_hmm_p_regime1"
-
-
-class RegimeGateDropoutStrategy(TopkDropoutStrategy):
-    """TopkDropout with an HMM-regime entry gate on buy candidates.
-
-    Parameters
-    ----------
-    topk, n_drop, method_sell, method_buy, hold_thresh, only_tradable,
-    forbid_all_trade_at_limit : same as ``TopkDropoutStrategy``.
-    regime_threshold : minimum ``sp_hmm_p_regime1`` posterior required to open a
-        new position (default 0.5).
-    """
-
-    def __init__(self, *, topk, n_drop, regime_threshold: float = DEFAULT_REGIME_THRESHOLD, **kwargs):
-        super().__init__(topk=topk, n_drop=n_drop, **kwargs)
-        self.regime_threshold = regime_threshold
-
-    def _regime_for(self, codes, pred_start, pred_end) -> pd.Series:
-        """Return {code: sp_hmm_p_regime1} for the signal window (last day)."""
-        if D is None:
-            return pd.Series(dtype=float)
-        try:
-            df = D.features(list(codes), [REGIME_FIELD], start_time=pred_start, end_time=pred_end, freq="day")
-        except Exception:  # noqa: BLE001 - a regime read failure should gate open, not crash
-            return pd.Series(dtype=float)
-        if df is None or len(df) == 0:
-            return pd.Series(dtype=float)
-        # df index is MultiIndex (datetime, instrument); take the last day's values
-        df = df.reset_index()
-        ts_col = "datetime" if "datetime" in df.columns else df.columns[0]
-        sym_col = "instrument" if "instrument" in df.columns else df.columns[1]
-        last_ts = df[ts_col].max()
-        last = df[df[ts_col] == last_ts]
-        out = {}
-        for _, row in last.iterrows():
-            sym = str(row[sym_col]).split("/")[-1].upper()
-            val = row.iloc[-1]
-            out[sym] = float(val) if val == val else np.nan
-        return pd.Series(out)
-
-    def generate_trade_decision(self, execute_result=None):
-        import copy
-
-        trade_step = self.trade_calendar.get_trade_step()
-        trade_start_time, trade_end_time = self.trade_calendar.get_step_time(trade_step)
-        pred_start_time, pred_end_time = self.trade_calendar.get_step_time(trade_step, shift=1)
-        pred_score = self.signal.get_signal(start_time=pred_start_time, end_time=pred_end_time)
-        if isinstance(pred_score, pd.DataFrame):
-            pred_score = pred_score.iloc[:, 0]
-        if pred_score is None:
-            return TradeDecisionWO([], self)
-
-        if self.only_tradable:
-
-            def get_first_n(li, n, reverse=False):
-                cur_n = 0
-                res = []
-                for si in reversed(li) if reverse else li:
-                    if self.trade_exchange.is_stock_tradable(
-                        stock_id=si, start_time=trade_start_time, end_time=trade_end_time
-                    ):
-                        res.append(si)
-                        cur_n += 1
-                        if cur_n >= n:
-                            break
-                return res[::-1] if reverse else res
-
-            def get_last_n(li, n):
-                return get_first_n(li, n, reverse=True)
-
-            def filter_stock(li):
-                return [
-                    si
-                    for si in li
-                    if self.trade_exchange.is_stock_tradable(
-                        stock_id=si, start_time=trade_start_time, end_time=trade_end_time
-                    )
-                ]
-
-        else:
-
-            def get_first_n(li, n):
-                return list(li)[:n]
-
-            def get_last_n(li, n):
-                return list(li)[-n:]
-
-            def filter_stock(li):
-                return li
-
-        current_temp: "object" = copy.deepcopy(self.trade_position)
-        sell_order_list: List[Order] = []
-        buy_order_list: List[Order] = []
-        cash = current_temp.get_cash()
-        current_stock_list = current_temp.get_stock_list()
-        last = pred_score.reindex(current_stock_list).sort_values(ascending=False).index
-
-        if self.method_buy == "top":
-            today = get_first_n(
-                pred_score[~pred_score.index.isin(last)].sort_values(ascending=False).index,
-                self.n_drop + self.topk - len(last),
-            )
-        elif self.method_buy == "random":
-            topk_candi = get_first_n(pred_score.sort_values(ascending=False).index, self.topk)
-            candi = list(filter(lambda x: x not in last, topk_candi))
-            n = self.n_drop + self.topk - len(last)
-            try:
-                today = np.random.choice(candi, n, replace=False)
-            except ValueError:
-                today = candi
-        else:
-            raise NotImplementedError(f"This type of input is not supported")
-
-        comb = pred_score.reindex(last.union(pd.Index(today))).sort_values(ascending=False).index
-
-        if self.method_sell == "bottom":
-            sell = last[last.isin(get_last_n(comb, self.n_drop))]
-        elif self.method_sell == "random":
-            candi = filter_stock(last)
-            try:
-                sell = pd.Index(np.random.choice(candi, self.n_drop, replace=False) if len(last) else [])
-            except ValueError:
-                sell = candi
-        else:
-            raise NotImplementedError(f"This type of input is not supported")
-
-        buy = today[: len(sell) + self.topk - len(last)]
-
-        # ---- regime gate -----------------------------------------------------
-        if buy:
-            regime = self._regime_for(buy, pred_start_time, pred_end_time)
-            gated = [c for c in buy if regime.get(c, np.nan) >= self.regime_threshold]
-        else:
-            gated = []
-
-        for code in current_stock_list:
-            if not self.trade_exchange.is_stock_tradable(
-                stock_id=code,
-                start_time=trade_start_time,
-                end_time=trade_end_time,
-                direction=None if self.forbid_all_trade_at_limit else OrderDir.SELL,
-            ):
-                continue
-            if code in sell:
-                time_per_step = self.trade_calendar.get_freq()
-                if current_temp.get_stock_count(code, bar=time_per_step) < self.hold_thresh:
-                    continue
-                sell_amount = current_temp.get_stock_amount(code=code)
-                sell_order = Order(
-                    stock_id=code,
-                    amount=sell_amount,
-                    start_time=trade_start_time,
-                    end_time=trade_end_time,
-                    direction=Order.SELL,
-                )
-                if self.trade_exchange.check_order(sell_order):
-                    sell_order_list.append(sell_order)
-                    trade_val, trade_cost, trade_price = self.trade_exchange.deal_order(
-                        sell_order, position=current_temp
-                    )
-                    cash += trade_val - trade_cost
-
-        if len(gated) == 0:
-            return TradeDecisionWO(sell_order_list, self)
-
-        value = cash * self.risk_degree / len(gated)
-        for code in gated:
-            if not self.trade_exchange.is_stock_tradable(
-                stock_id=code,
-                start_time=trade_start_time,
-                end_time=trade_end_time,
-                direction=None if self.forbid_all_trade_at_limit else OrderDir.BUY,
-            ):
-                continue
-            buy_price = self.trade_exchange.get_deal_price(
-                stock_id=code, start_time=trade_start_time, end_time=trade_end_time, direction=OrderDir.BUY
-            )
-            buy_amount = value / buy_price
-            factor = self.trade_exchange.get_factor(
-                stock_id=code, start_time=trade_start_time, end_time=trade_end_time
-            )
-            buy_amount = self.trade_exchange.round_amount_by_trade_unit(buy_amount, factor)
-            buy_order = Order(
-                stock_id=code,
-                amount=buy_amount,
-                start_time=trade_start_time,
-                end_time=trade_end_time,
-                direction=Order.BUY,
-            )
-            buy_order_list.append(buy_order)
-
-        return TradeDecisionWO(sell_order_list + buy_order_list, self)

code/tac-qlib/tac_qlib/contrib/strategy/top_bottom.py

@@ -1,169 +0,0 @@
-"""Market-neutral top/bottom long-short strategy for cross-sectional signals.
-
-Captures the cross-sectional long-short spread net of costs: buys the top-ranked
-``topk`` names and shorts the bottom-ranked ``topk`` names, equal-weight per
-side, sized to ``risk_degree`` of total value per side. Rebalances daily to the
-current rank (dropout-free: the book converges to the latest top/bottom sets).
-
-The long and short legs use equal notional per side (gross exposure ~2x
-``risk_degree`` of NAV, i.e. approximately market neutral before transaction
-costs). Benchmark neutrality (SPY beta ~ 0) is the secondary sanity metric.
-"""
-
-from __future__ import annotations
-
-from typing import List
-
-import copy
-
-import pandas as pd
-
-from qlib.backtest import Order
-from qlib.backtest.decision import OrderDir, TradeDecisionWO
-from qlib.contrib.strategy.signal_strategy import BaseSignalStrategy
-
-__all__ = ["TopBottomDropoutStrategy"]
-
-DEFAULT_SHORT_LEG = True
-DEFAULT_REBALANCE_DAILY = True
-
-
-class TopBottomDropoutStrategy(BaseSignalStrategy):
-    """Long top-k / short bottom-k equal-weight market-neutral book.
-
-    Parameters
-    ----------
-    topk : number of names on each side (long top-k and short bottom-k).
-    short_leg : whether to open the short side (if False, long-only topk).
-    rebalance_daily : if True rebalance to current rank every day; else keep
-        positions and only refresh on score changes (dropout-style).
-    risk_degree : fraction of total value deployed per side.
-    """
-
-    def __init__(
-        self,
-        *,
-        topk: int = 10,
-        short_leg: bool = DEFAULT_SHORT_LEG,
-        rebalance_daily: bool = DEFAULT_REBALANCE_DAILY,
-        **kwargs,
-    ):
-        super().__init__(**kwargs)
-        self.topk = topk
-        self.short_leg = short_leg
-        self.rebalance_daily = rebalance_daily
-        self._prev_longs = set()
-        self._prev_shorts = set()
-
-    def generate_trade_decision(self, execute_result=None):
-        trade_step = self.trade_calendar.get_trade_step()
-        trade_start_time, trade_end_time = self.trade_calendar.get_step_time(trade_step)
-        pred_start_time, pred_end_time = self.trade_calendar.get_step_time(trade_step, shift=1)
-        pred_score = self.signal.get_signal(start_time=pred_start_time, end_time=pred_end_time)
-        if isinstance(pred_score, pd.DataFrame):
-            pred_score = pred_score.iloc[:, 0]
-        if pred_score is None or len(pred_score) == 0:
-            return TradeDecisionWO([], self)
-
-        # rank all names; topk longs and topk shorts
-        ranked = pred_score.sort_values(ascending=False)
-        longs = list(ranked.index[: self.topk])
-        shorts = list(ranked.index[-self.topk :]) if self.short_leg else []
-
-        current_temp: "object" = copy.deepcopy(self.trade_position)
-        current_codes = set(current_temp.get_stock_list())
-        holdings = {c: current_temp for c in current_codes if abs(current_temp.get_stock_amount(c)) > 1e-6}
-
-        sell_orders: List[Order] = []
-        buy_orders: List[Order] = []
-
-        def _tradable(code, direction):
-            try:
-                return self.trade_exchange.is_stock_tradable(
-                    stock_id=code, start_time=trade_start_time, end_time=trade_end_time, direction=direction
-                )
-            except TypeError:
-                return self.trade_exchange.is_stock_tradable(
-                    stock_id=code, start_time=trade_start_time, end_time=trade_end_time
-                )
-
-        # determine target set (long/short)
-        target_longs = set(longs)
-        target_shorts = set(shorts)
-
-        # close positions not in the target book
-        for code in list(holdings):
-            if code in target_longs or code in target_shorts:
-                continue
-            amt = abs(current_temp.get_stock_amount(code))
-            o = Order(
-                stock_id=code,
-                amount=amt,
-                start_time=trade_start_time,
-                end_time=trade_end_time,
-                direction=Order.SELL if code in target_longs else Order.SELL,
-            )
-            if self.trade_exchange.check_order(o):
-                sell_orders.append(o)
-                self.trade_exchange.deal_order(o, position=current_temp)
-
-        # equal-weight notional per side
-        total_value = current_temp.get_cash()
-        for code, pos in holdings.items():
-            if code in target_longs or code in target_shorts:
-                mark = self.trade_exchange.get_deal_price(
-                    stock_id=code, start_time=trade_start_time, end_time=trade_end_time, direction=Order.SELL
-                )
-                if mark is not None and mark == mark:
-                    total_value += abs(current_temp.get_stock_amount(code)) * mark
-
-        side_notional = total_value * self.risk_degree / max(1, self.topk)
-
-        for code in longs:
-            if code in holdings and abs(current_temp.get_stock_amount(code)) > 1e-6:
-                continue
-            px = self.trade_exchange.get_deal_price(
-                stock_id=code, start_time=trade_start_time, end_time=trade_end_time, direction=Order.BUY
-            )
-            if px is None or px != px or px <= 0:
-                continue
-            amount = side_notional / px
-            factor = self.trade_exchange.get_factor(
-                stock_id=code, start_time=trade_start_time, end_time=trade_end_time
-            )
-            amount = self.trade_exchange.round_amount_by_trade_unit(amount, factor)
-            o = Order(
-                stock_id=code,
-                amount=amount,
-                start_time=trade_start_time,
-                end_time=trade_end_time,
-                direction=Order.BUY,
-            )
-            if self.trade_exchange.check_order(o):
-                buy_orders.append(o)
-
-        if self.short_leg:
-            for code in shorts:
-                if code in holdings and abs(current_temp.get_stock_amount(code)) > 1e-6:
-                    continue
-                px = self.trade_exchange.get_deal_price(
-                    stock_id=code, start_time=trade_start_time, end_time=trade_end_time, direction=Order.SELL
-                )
-                if px is None or px != px or px <= 0:
-                    continue
-                amount = side_notional / px
-                factor = self.trade_exchange.get_factor(
-                    stock_id=code, start_time=trade_start_time, end_time=trade_end_time
-                )
-                amount = self.trade_exchange.round_amount_by_trade_unit(amount, factor)
-                o = Order(
-                    stock_id=code,
-                    amount=amount,
-                    start_time=trade_start_time,
-                    end_time=trade_end_time,
-                    direction=Order.SELL,
-                )
-                if self.trade_exchange.check_order(o):
-                    sell_orders.append(o)
-
-        return TradeDecisionWO(sell_orders + buy_orders, self)

code/tac-qlib/tac_qlib/contrib/strategy/weekly_rebalance.py

@@ -1,202 +0,0 @@
-"""Weekly-rebalance TopkDropout strategy.
-
-Turnover-reduction variant of ``qlib.contrib.strategy.signal_strategy.TopkDropoutStrategy``:
-the topk/n_drop selection and sizing are identical to the reference, but the
-target book is recomputed only on the first trading day of each ISO week; on the
-other days the strategy issues NO orders (holds the book untouched).
-
-The weekly cadence is derived from the qlib trade calendar: a rebalance happens
-when the current trade step's date belongs to a different ISO ``(year, week)``
-than the previous trade step. ``hold_band_pct`` (default 0) optionally skips
-tiny rebalances: when a name's existing position differs from the new target by
-less than this fraction, no order is generated for it.
-"""
-
-from __future__ import annotations
-
-from typing import List
-
-import numpy as np
-import pandas as pd
-
-from qlib.backtest import Order
-from qlib.backtest.decision import OrderDir, TradeDecisionWO
-from qlib.contrib.strategy.signal_strategy import TopkDropoutStrategy
-
-__all__ = ["WeeklyRebalanceDropoutStrategy"]
-
-DEFAULT_HOLD_BAND_PCT = 0.0
-
-
-class WeeklyRebalanceDropoutStrategy(TopkDropoutStrategy):
-    """TopkDropout rebalanced once per ISO week; holds otherwise.
-
-    Parameters
-    ----------
-    topk, n_drop, method_sell, method_buy, hold_thresh, only_tradable,
-    forbid_all_trade_at_limit : same as ``TopkDropoutStrategy``.
-    hold_band_pct : skip order for a name whose deviation from target weight is
-        below this fraction of the target (no-trade buffer band).
-    """
-
-    def __init__(self, *, topk, n_drop, hold_band_pct: float = DEFAULT_HOLD_BAND_PCT, **kwargs):
-        super().__init__(topk=topk, n_drop=n_drop, **kwargs)
-        self.hold_band_pct = hold_band_pct
-
-    @staticmethod
-    def _iso_week(ts) -> tuple:
-        return (ts.year, ts.week)
-
-    def generate_trade_decision(self, execute_result=None):
-        import copy
-
-        trade_step = self.trade_calendar.get_trade_step()
-        trade_start_time, trade_end_time = self.trade_calendar.get_step_time(trade_step)
-
-        cur_week = self._iso_week(trade_start_time)
-        prev_week = getattr(self, "_last_week", None)
-        self._last_week = cur_week
-
-        if prev_week is not None and prev_week == cur_week:
-            # not the first trading day of this ISO week -> hold
-            return TradeDecisionWO([], self)
-
-        pred_start_time, pred_end_time = self.trade_calendar.get_step_time(trade_step, shift=1)
-        pred_score = self.signal.get_signal(start_time=pred_start_time, end_time=pred_end_time)
-        if isinstance(pred_score, pd.DataFrame):
-            pred_score = pred_score.iloc[:, 0]
-        if pred_score is None:
-            return TradeDecisionWO([], self)
-
-        if self.only_tradable:
-
-            def get_first_n(li, n, reverse=False):
-                cur_n = 0
-                res = []
-                for si in reversed(li) if reverse else li:
-                    if self.trade_exchange.is_stock_tradable(
-                        stock_id=si, start_time=trade_start_time, end_time=trade_end_time
-                    ):
-                        res.append(si)
-                        cur_n += 1
-                        if cur_n >= n:
-                            break
-                return res[::-1] if reverse else res
-
-            def get_last_n(li, n):
-                return get_first_n(li, n, reverse=True)
-
-            def filter_stock(li):
-                return [
-                    si
-                    for si in li
-                    if self.trade_exchange.is_stock_tradable(
-                        stock_id=si, start_time=trade_start_time, end_time=trade_end_time
-                    )
-                ]
-
-        else:
-
-            def get_first_n(li, n):
-                return list(li)[:n]
-
-            def get_last_n(li, n):
-                return list(li)[-n:]
-
-            def filter_stock(li):
-                return li
-
-        current_temp: "object" = copy.deepcopy(self.trade_position)
-        sell_order_list: List[Order] = []
-        buy_order_list: List[Order] = []
-        cash = current_temp.get_cash()
-        current_stock_list = current_temp.get_stock_list()
-        last = pred_score.reindex(current_stock_list).sort_values(ascending=False).index
-
-        if self.method_buy == "top":
-            today = get_first_n(
-                pred_score[~pred_score.index.isin(last)].sort_values(ascending=False).index,
-                self.n_drop + self.topk - len(last),
-            )
-        elif self.method_buy == "random":
-            topk_candi = get_first_n(pred_score.sort_values(ascending=False).index, self.topk)
-            candi = list(filter(lambda x: x not in last, topk_candi))
-            n = self.n_drop + self.topk - len(last)
-            try:
-                today = np.random.choice(candi, n, replace=False)
-            except ValueError:
-                today = candi
-        else:
-            raise NotImplementedError(f"This type of input is not supported")
-
-        comb = pred_score.reindex(last.union(pd.Index(today))).sort_values(ascending=False).index
-
-        if self.method_sell == "bottom":
-            sell = last[last.isin(get_last_n(comb, self.n_drop))]
-        elif self.method_sell == "random":
-            candi = filter_stock(last)
-            try:
-                sell = pd.Index(np.random.choice(candi, self.n_drop, replace=False) if len(last) else [])
-            except ValueError:
-                sell = candi
-        else:
-            raise NotImplementedError(f"This type of input is not supported")
-
-        buy = today[: len(sell) + self.topk - len(last)]
-        for code in current_stock_list:
-            if not self.trade_exchange.is_stock_tradable(
-                stock_id=code,
-                start_time=trade_start_time,
-                end_time=trade_end_time,
-                direction=None if self.forbid_all_trade_at_limit else OrderDir.SELL,
-            ):
-                continue
-            if code in sell:
-                time_per_step = self.trade_calendar.get_freq()
-                if current_temp.get_stock_count(code, bar=time_per_step) < self.hold_thresh:
-                    continue
-                sell_amount = current_temp.get_stock_amount(code=code)
-                sell_order = Order(
-                    stock_id=code,
-                    amount=sell_amount,
-                    start_time=trade_start_time,
-                    end_time=trade_end_time,
-                    direction=Order.SELL,
-                )
-                if self.trade_exchange.check_order(sell_order):
-                    sell_order_list.append(sell_order)
-                    trade_val, trade_cost, trade_price = self.trade_exchange.deal_order(
-                        sell_order, position=current_temp
-                    )
-                    cash += trade_val - trade_cost
-
-        if len(buy) == 0:
-            return TradeDecisionWO(sell_order_list, self)
-
-        value = cash * self.risk_degree / len(buy)
-        for code in buy:
-            if not self.trade_exchange.is_stock_tradable(
-                stock_id=code,
-                start_time=trade_start_time,
-                end_time=trade_end_time,
-                direction=None if self.forbid_all_trade_at_limit else OrderDir.BUY,
-            ):
-                continue
-            buy_price = self.trade_exchange.get_deal_price(
-                stock_id=code, start_time=trade_start_time, end_time=trade_end_time, direction=OrderDir.BUY
-            )
-            buy_amount = value / buy_price
-            factor = self.trade_exchange.get_factor(
-                stock_id=code, start_time=trade_start_time, end_time=trade_end_time
-            )
-            buy_amount = self.trade_exchange.round_amount_by_trade_unit(buy_amount, factor)
-            buy_order = Order(
-                stock_id=code,
-                amount=buy_amount,
-                start_time=trade_start_time,
-                end_time=trade_end_time,
-                direction=Order.BUY,
-            )
-            buy_order_list.append(buy_order)
-
-        return TradeDecisionWO(sell_order_list + buy_order_list, self)

workflows/ablate_baseline_all_sp_fields.yaml

@@ -0,0 +1,133 @@
+# -----------------------------------------------------------------------------
+# ABLATION A (baseline): LightGBM with RankIC early-stopping on the 50-ETF SP-5d
+# panel, using ALL 24 sp_* feature columns (ou,hmm,jump,har,trend,hurst,
+# signature). Copy of the canonical workflow_lgb_sp5d_rankic.yaml with a
+# distinct experiment name so the ablation runs are isolated.
+#
+# Run:
+#   rd_run_workflow config_path=tac-qlib/workflows/ablate_baseline_all_sp_fields.yaml \
+#       experiment_name=tac-rd-rank-ablate
+# -----------------------------------------------------------------------------
+{%- set LAKE = TAC_LAKE_DIR %}
+{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
+{%- set SP_FIELDS = "sp_ret,sp_ou_zscore,sp_ou_half_life,sp_ou_revert,sp_hmm_p_regime1,sp_hmm_state,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
+
+qlib_init:
+    provider_uri: "{{ LAKE }}"
+    region: us
+    expression_cache: null
+    dataset_cache: null
+
+    calendar_provider:
+        class: tac_qlib.data.providers.LakeCalendarProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+    instrument_provider:
+        class: tac_qlib.data.providers.LakeInstrumentProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+            markets: {}
+    feature_provider:
+        class: tac_qlib.data.providers.LakeFeatureProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+
+    exp_manager:
+        class: MLflowExpManager
+        module_path: qlib.workflow.expm
+        kwargs:
+            uri: "sqlite:///{{ LAKE }}/mlruns.db"
+            default_exp_name: "tac-rd-rank-ablate"
+
+task:
+    model:
+        class: RankICLGBModel
+        module_path: tac_qlib.contrib.model.rank_gbdt
+        kwargs:
+            loss: mse
+            learning_rate: 0.02
+            num_leaves: 31
+            n_estimators: 3000
+            num_boost_round: 3000
+            early_stopping_rounds: 200
+            min_data_in_leaf: 20
+            lambda_l2: 0.5
+            colsample_bytree: 0.8
+            subsample: 0.8
+            subsample_freq: 1
+            reg_alpha: 0.1
+            reg_lambda: 1.0
+            seed: 42
+
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: TACHandler
+                module_path: tac_qlib.contrib.data.handler
+                kwargs:
+                    instruments: "{{ UNIVERSE }}"
+                    start_time: 2015-01-03
+                    end_time: 2026-08-10
+                    fit_start_time: 2015-01-03
+                    fit_end_time: 2025-09-01
+                    freq: day
+                    lake_root: "{{ LAKE }}"
+                    market: US
+                    label: "Ref($close,-6)/Ref($close,-1)-1"
+                    feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
+                    infer_processors:
+                        - class: DropAllNaN
+                          kwargs: {}
+                        - class: ProcessInf
+                          kwargs: {}
+                        - class: CSRankNorm
+                          kwargs: {}
+                        - class: ZScoreNorm
+                          kwargs: {}
+                        - class: Fillna
+                          kwargs: {}
+            segments:
+                train: [2015-01-03, 2025-09-01]
+                valid: [2025-09-03, 2026-01-03]
+                test: [2026-01-04, 2026-08-10]
+
+    record:
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: {}
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              ana_long_short: true
+              ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              config:
+                  strategy:
+                      class: TopkDropoutStrategy
+                      module_path: qlib.contrib.strategy
+                      kwargs:
+                          signal: "<PRED>"
+                          topk: 10
+                          n_drop: 2
+                          only_tradable: true
+                          risk_degree: 0.95
+                  backtest:
+                      start_time: 2026-01-04
+                      end_time: 2026-08-10
+                      account: 1000000
+                      benchmark: SPY
+                      exchange_kwargs:
+                          codes: "{{ UNIVERSE }}"
+                          deal_price: $close
+                          freq: day
+                          open_cost: 0.0005
+                          close_cost: 0.0015
+                          min_cost: 5.0
+              risk_analysis_freq: 1d

workflows/ablate_generic_only_sp_fields.yaml

@@ -0,0 +1,134 @@
+# -----------------------------------------------------------------------------
+# ABLATION B (generic-only): same panel/model as the baseline, but feature
+# fields restricted to the model-free / generic stochastic-process families
+# (jump,har,trend,hurst,signature). Drops the model-specific ou (OU/AR-1
+# half-life) and hmm (2-state regime) families to test whether the generic
+# families alone dominate the rank dimension.
+#
+# Run:
+#   rd_run_workflow config_path=tac-qlib/workflows/ablate_generic_only_sp_fields.yaml \
+#       experiment_name=tac-rd-rank-ablate
+# -----------------------------------------------------------------------------
+{%- set LAKE = TAC_LAKE_DIR %}
+{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
+{%- set SP_FIELDS = "sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
+
+qlib_init:
+    provider_uri: "{{ LAKE }}"
+    region: us
+    expression_cache: null
+    dataset_cache: null
+
+    calendar_provider:
+        class: tac_qlib.data.providers.LakeCalendarProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+    instrument_provider:
+        class: tac_qlib.data.providers.LakeInstrumentProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+            markets: {}
+    feature_provider:
+        class: tac_qlib.data.providers.LakeFeatureProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+
+    exp_manager:
+        class: MLflowExpManager
+        module_path: qlib.workflow.expm
+        kwargs:
+            uri: "sqlite:///{{ LAKE }}/mlruns.db"
+            default_exp_name: "tac-rd-rank-ablate"
+
+task:
+    model:
+        class: RankICLGBModel
+        module_path: tac_qlib.contrib.model.rank_gbdt
+        kwargs:
+            loss: mse
+            learning_rate: 0.02
+            num_leaves: 31
+            n_estimators: 3000
+            num_boost_round: 3000
+            early_stopping_rounds: 200
+            min_data_in_leaf: 20
+            lambda_l2: 0.5
+            colsample_bytree: 0.8
+            subsample: 0.8
+            subsample_freq: 1
+            reg_alpha: 0.1
+            reg_lambda: 1.0
+            seed: 42
+
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: TACHandler
+                module_path: tac_qlib.contrib.data.handler
+                kwargs:
+                    instruments: "{{ UNIVERSE }}"
+                    start_time: 2015-01-03
+                    end_time: 2026-08-10
+                    fit_start_time: 2015-01-03
+                    fit_end_time: 2025-09-01
+                    freq: day
+                    lake_root: "{{ LAKE }}"
+                    market: US
+                    label: "Ref($close,-6)/Ref($close,-1)-1"
+                    feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
+                    infer_processors:
+                        - class: DropAllNaN
+                          kwargs: {}
+                        - class: ProcessInf
+                          kwargs: {}
+                        - class: CSRankNorm
+                          kwargs: {}
+                        - class: ZScoreNorm
+                          kwargs: {}
+                        - class: Fillna
+                          kwargs: {}
+            segments:
+                train: [2015-01-03, 2025-09-01]
+                valid: [2025-09-03, 2026-01-03]
+                test: [2026-01-04, 2026-08-10]
+
+    record:
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: {}
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              ana_long_short: true
+              ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              config:
+                  strategy:
+                      class: TopkDropoutStrategy
+                      module_path: qlib.contrib.strategy
+                      kwargs:
+                          signal: "<PRED>"
+                          topk: 10
+                          n_drop: 2
+                          only_tradable: true
+                          risk_degree: 0.95
+                  backtest:
+                      start_time: 2026-01-04
+                      end_time: 2026-08-10
+                      account: 1000000
+                      benchmark: SPY
+                      exchange_kwargs:
+                          codes: "{{ UNIVERSE }}"
+                          deal_price: $close
+                          freq: day
+                          open_cost: 0.0005
+                          close_cost: 0.0015
+                          min_cost: 5.0
+              risk_analysis_freq: 1d

workflows/exp12_isolation_ensemble.yaml

@@ -0,0 +1,141 @@
+# -----------------------------------------------------------------------------
+# ISOLATION: multi-seed RankIC ensemble, ablate-B generic-only feature set.
+#
+# Isolates the ensemble effect on the SP-5d rank signal. Same panel, segments,
+# history (full backfilled 2016+) and feature set as the exp-9 ablate-B winner
+# (generic-only sp_* families: jump,har,trend,hurst,signature), but replaces the
+# single RankICLGBModel with a 5-seed RankICEnsembleLGBModel (42,7,2026,99,123)
+# that averages per-day predictions.
+#
+# Differs from exp-15 (tac-rd-rank-ensemble, mlflow exp 15) ONLY by dropping the
+# TA subset (rsi_14,roc_10,macd_hist,willr_14,atr_14) and the inter-asset xr_*
+# features, so any change vs exp-15 is attributable to the feature set alone,
+# and any change vs exp-9 is attributable to the ensemble + full history alone.
+#
+# Run:
+#   rd_run_workflow config_path=experiments/workflows/exp12_isolation_ensemble.yaml \
+#       experiment_name=tac-rd-rank-ensemble-isolated
+# -----------------------------------------------------------------------------
+{%- set LAKE = TAC_LAKE_DIR %}
+{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
+{%- set SP_FIELDS = "sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
+
+qlib_init:
+    provider_uri: "{{ LAKE }}"
+    region: us
+    expression_cache: null
+    dataset_cache: null
+
+    calendar_provider:
+        class: tac_qlib.data.providers.LakeCalendarProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+    instrument_provider:
+        class: tac_qlib.data.providers.LakeInstrumentProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+            markets: {}
+    feature_provider:
+        class: tac_qlib.data.providers.LakeFeatureProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+
+    exp_manager:
+        class: MLflowExpManager
+        module_path: qlib.workflow.expm
+        kwargs:
+            uri: "sqlite:///mlruns.db"
+            default_exp_name: "tac-rd-rank-ensemble-isolated"
+
+task:
+    model:
+        class: RankICEnsembleLGBModel
+        module_path: tac_qlib.contrib.model.rank_ensemble
+        kwargs:
+            loss: mse
+            learning_rate: 0.02
+            num_leaves: 31
+            n_estimators: 3000
+            num_boost_round: 3000
+            early_stopping_rounds: 200
+            min_data_in_leaf: 20
+            lambda_l2: 0.5
+            colsample_bytree: 0.8
+            subsample: 0.8
+            subsample_freq: 1
+            reg_alpha: 0.1
+            reg_lambda: 1.0
+            seeds: "42,7,2026,99,123"
+
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: TACHandler
+                module_path: tac_qlib.contrib.data.handler
+                kwargs:
+                    instruments: "{{ UNIVERSE }}"
+                    start_time: 2015-01-03
+                    end_time: 2026-08-14
+                    fit_start_time: 2016-01-04
+                    fit_end_time: 2025-09-01
+                    freq: day
+                    lake_root: "{{ LAKE }}"
+                    market: US
+                    label: "Ref($close,-6)/Ref($close,-1)-1"
+                    feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
+                    infer_processors:
+                        - class: DropAllNaN
+                          kwargs: {}
+                        - class: ProcessInf
+                          kwargs: {}
+                        - class: CSRankNorm
+                          kwargs: {}
+                        - class: ZScoreNorm
+                          kwargs: {}
+                        - class: Fillna
+                          kwargs: {}
+            segments:
+                train: [2016-01-04, 2025-09-01]
+                valid: [2025-09-03, 2026-01-03]
+                test: [2026-01-04, 2026-08-10]
+
+    record:
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: {}
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              ana_long_short: true
+              ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              config:
+                  strategy:
+                      class: TopkDropoutStrategy
+                      module_path: qlib.contrib.strategy
+                      kwargs:
+                          signal: "<PRED>"
+                          topk: 10
+                          n_drop: 2
+                          only_tradable: true
+                          risk_degree: 0.95
+                  backtest:
+                      start_time: 2026-01-04
+                      end_time: 2026-08-10
+                      account: 1000000
+                      benchmark: SPY
+                      exchange_kwargs:
+                          codes: "{{ UNIVERSE }}"
+                          deal_price: $close
+                          freq: day
+                          open_cost: 0.0005
+                          close_cost: 0.0015
+                          min_cost: 5.0
+              risk_analysis_freq: 1d

workflows/exp22/workflow.yaml

@@ -0,0 +1,97 @@
+# Re-run of experiment 16 with validated family=ta and family=sp lake features.
+{%- set LAKE = TAC_LAKE_DIR %}
+{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
+{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sma_5,sma_20,ema_12,ema_26,rsi_14,macd,macd_signal,macd_hist,bb_upper,bb_middle,bb_lower,atr_14,adx_14,sp_ret,sp_ou_half_life,sp_ou_revert,sp_ou_zscore,sp_hmm_p_regime1,sp_hmm_state,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_down,sp_max_move,sp_max_up,sp_rv1,sp_rv5,sp_rv22,sp_rv_ac1,sp_rv_cv_22,sp_vol_ratio_1_22,sp_vol_ratio_5_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_rskew_5,sp_rskew_22,sp_rkurt_5,sp_rkurt_22,sp_dsv_1,sp_dsv_5,sp_dsv_22,sp_dsv_ratio_1,sp_dsv_ratio_5,sp_dsv_ratio_22,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead,sp_sig_level2_lead_lag_5,sp_sig_level2_lag_lead_5" %}
+
+qlib_init:
+    provider_uri: "{{ LAKE }}"
+    region: us
+    expression_cache: null
+    dataset_cache: null
+    calendar_provider:
+        class: tac_qlib.data.providers.LakeCalendarProvider
+        kwargs: { lake_root: "{{ LAKE }}", market: US }
+    instrument_provider:
+        class: tac_qlib.data.providers.LakeInstrumentProvider
+        kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
+    feature_provider:
+        class: tac_qlib.data.providers.LakeFeatureProvider
+        kwargs: { lake_root: "{{ LAKE }}", market: US }
+    exp_manager:
+        class: MLflowExpManager
+        module_path: qlib.workflow.expm
+        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-exp16-db-ta-sp" }
+
+task:
+    model:
+        class: RankICEnsembleLGBModel
+        module_path: tac_qlib.contrib.model.rank_ensemble
+        kwargs:
+            loss: mse
+            learning_rate: 0.02
+            num_leaves: 31
+            n_estimators: 3000
+            num_boost_round: 3000
+            early_stopping_rounds: 200
+            min_data_in_leaf: 20
+            lambda_l2: 0.5
+            colsample_bytree: 0.8
+            subsample: 0.8
+            subsample_freq: 1
+            reg_alpha: 0.1
+            reg_lambda: 1.0
+            seeds: "42,7,2026,99,123"
+
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: TACHandler
+                module_path: tac_qlib.contrib.data.handler
+                kwargs:
+                    instruments: "{{ UNIVERSE }}"
+                    start_time: 2015-01-03
+                    end_time: 2026-08-10
+                    fit_start_time: 2016-01-04
+                    fit_end_time: 2025-09-01
+                    freq: day
+                    lake_root: "{{ LAKE }}"
+                    market: US
+                    label: "Ref($close,-6)/Ref($close,-1)-1"
+                    feature_fields: "{{ FEATURES }}"
+                    infer_processors:
+                        - { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
+                        - { class: ProcessInf, kwargs: {} }
+                        - { class: CSRankNorm, kwargs: {} }
+                        - { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
+                        - { class: Fillna, kwargs: {} }
+            segments:
+                train: [2016-01-04, 2025-09-01]
+                valid: [2025-09-03, 2026-01-03]
+                test: [2026-01-04, 2026-08-10]
+
+    record:
+        - { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
+        - { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              config:
+                  strategy:
+                      class: TopkDropoutStrategy
+                      module_path: qlib.contrib.strategy
+                      kwargs: { signal: "<PRED>", topk: 10, n_drop: 2, only_tradable: true, risk_degree: 0.95 }
+                  backtest:
+                      start_time: 2026-01-04
+                      end_time: 2026-08-10
+                      account: 1000000
+                      benchmark: SPY
+                      exchange_kwargs:
+                          codes: "{{ UNIVERSE }}"
+                          deal_price: $close
+                          freq: day
+                          open_cost: 0.0005
+                          close_cost: 0.0015
+                          min_cost: 5.0
+              risk_analysis_freq: 1d

workflows/exp23/workflow.yaml

@@ -0,0 +1,97 @@
+# General stochastic-process feature ablation: no TA, HMM, or OU fields.
+{%- set LAKE = TAC_LAKE_DIR %}
+{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
+{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_down,sp_max_move,sp_max_up,sp_rv1,sp_rv5,sp_rv22,sp_rv_ac1,sp_rv_cv_22,sp_vol_ratio_1_22,sp_vol_ratio_5_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_rskew_5,sp_rskew_22,sp_rkurt_5,sp_rkurt_22,sp_dsv_1,sp_dsv_5,sp_dsv_22,sp_dsv_ratio_1,sp_dsv_ratio_5,sp_dsv_ratio_22,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead,sp_sig_level2_lead_lag_5,sp_sig_level2_lag_lead_5" %}
+
+qlib_init:
+    provider_uri: "{{ LAKE }}"
+    region: us
+    expression_cache: null
+    dataset_cache: null
+    calendar_provider:
+        class: tac_qlib.data.providers.LakeCalendarProvider
+        kwargs: { lake_root: "{{ LAKE }}", market: US }
+    instrument_provider:
+        class: tac_qlib.data.providers.LakeInstrumentProvider
+        kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
+    feature_provider:
+        class: tac_qlib.data.providers.LakeFeatureProvider
+        kwargs: { lake_root: "{{ LAKE }}", market: US }
+    exp_manager:
+        class: MLflowExpManager
+        module_path: qlib.workflow.expm
+        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-exp22-stochastic-general" }
+
+task:
+    model:
+        class: RankICEnsembleLGBModel
+        module_path: tac_qlib.contrib.model.rank_ensemble
+        kwargs:
+            loss: mse
+            learning_rate: 0.02
+            num_leaves: 31
+            n_estimators: 3000
+            num_boost_round: 3000
+            early_stopping_rounds: 200
+            min_data_in_leaf: 20
+            lambda_l2: 0.5
+            colsample_bytree: 0.8
+            subsample: 0.8
+            subsample_freq: 1
+            reg_alpha: 0.1
+            reg_lambda: 1.0
+            seeds: "42,7,2026,99,123"
+
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: TACHandler
+                module_path: tac_qlib.contrib.data.handler
+                kwargs:
+                    instruments: "{{ UNIVERSE }}"
+                    start_time: 2015-01-03
+                    end_time: 2026-08-10
+                    fit_start_time: 2016-01-04
+                    fit_end_time: 2025-09-01
+                    freq: day
+                    lake_root: "{{ LAKE }}"
+                    market: US
+                    label: "Ref($close,-6)/Ref($close,-1)-1"
+                    feature_fields: "{{ FEATURES }}"
+                    infer_processors:
+                        - { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
+                        - { class: ProcessInf, kwargs: {} }
+                        - { class: CSRankNorm, kwargs: {} }
+                        - { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
+                        - { class: Fillna, kwargs: {} }
+            segments:
+                train: [2016-01-04, 2025-09-01]
+                valid: [2025-09-03, 2026-01-03]
+                test: [2026-01-04, 2026-08-10]
+
+    record:
+        - { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
+        - { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              config:
+                  strategy:
+                      class: TopkDropoutStrategy
+                      module_path: qlib.contrib.strategy
+                      kwargs: { signal: "<PRED>", topk: 10, n_drop: 2, only_tradable: true, risk_degree: 0.95 }
+                  backtest:
+                      start_time: 2026-01-04
+                      end_time: 2026-08-10
+                      account: 1000000
+                      benchmark: SPY
+                      exchange_kwargs:
+                          codes: "{{ UNIVERSE }}"
+                          deal_price: $close
+                          freq: day
+                          open_cost: 0.0005
+                          close_cost: 0.0015
+                          min_cost: 5.0
+              risk_analysis_freq: 1d

workflows/exp24/workflow.yaml

@@ -0,0 +1,97 @@
+# Exact compact stochastic feature set requested for a new run in MLflow exp 25.
+{%- set LAKE = TAC_LAKE_DIR %}
+{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
+{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
+
+qlib_init:
+    provider_uri: "{{ LAKE }}"
+    region: us
+    expression_cache: null
+    dataset_cache: null
+    calendar_provider:
+        class: tac_qlib.data.providers.LakeCalendarProvider
+        kwargs: { lake_root: "{{ LAKE }}", market: US }
+    instrument_provider:
+        class: tac_qlib.data.providers.LakeInstrumentProvider
+        kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
+    feature_provider:
+        class: tac_qlib.data.providers.LakeFeatureProvider
+        kwargs: { lake_root: "{{ LAKE }}", market: US }
+    exp_manager:
+        class: MLflowExpManager
+        module_path: qlib.workflow.expm
+        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-exp22-stochastic-general" }
+
+task:
+    model:
+        class: RankICEnsembleLGBModel
+        module_path: tac_qlib.contrib.model.rank_ensemble
+        kwargs:
+            loss: mse
+            learning_rate: 0.02
+            num_leaves: 31
+            n_estimators: 3000
+            num_boost_round: 3000
+            early_stopping_rounds: 200
+            min_data_in_leaf: 20
+            lambda_l2: 0.5
+            colsample_bytree: 0.8
+            subsample: 0.8
+            subsample_freq: 1
+            reg_alpha: 0.1
+            reg_lambda: 1.0
+            seeds: "42,7,2026,99,123"
+
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: TACHandler
+                module_path: tac_qlib.contrib.data.handler
+                kwargs:
+                    instruments: "{{ UNIVERSE }}"
+                    start_time: 2015-01-03
+                    end_time: 2026-08-10
+                    fit_start_time: 2016-01-04
+                    fit_end_time: 2025-09-01
+                    freq: day
+                    lake_root: "{{ LAKE }}"
+                    market: US
+                    label: "Ref($close,-6)/Ref($close,-1)-1"
+                    feature_fields: "{{ FEATURES }}"
+                    infer_processors:
+                        - { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
+                        - { class: ProcessInf, kwargs: {} }
+                        - { class: CSRankNorm, kwargs: {} }
+                        - { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
+                        - { class: Fillna, kwargs: {} }
+            segments:
+                train: [2016-01-04, 2025-09-01]
+                valid: [2025-09-03, 2026-01-03]
+                test: [2026-01-04, 2026-08-10]
+
+    record:
+        - { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
+        - { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              config:
+                  strategy:
+                      class: TopkDropoutStrategy
+                      module_path: qlib.contrib.strategy
+                      kwargs: { signal: "<PRED>", topk: 10, n_drop: 2, only_tradable: true, risk_degree: 0.95 }
+                  backtest:
+                      start_time: 2026-01-04
+                      end_time: 2026-08-10
+                      account: 1000000
+                      benchmark: SPY
+                      exchange_kwargs:
+                          codes: "{{ UNIVERSE }}"
+                          deal_price: $close
+                          freq: day
+                          open_cost: 0.0005
+                          close_cost: 0.0015
+                          min_cost: 5.0
+              risk_analysis_freq: 1d

workflows/exp25/workflow.yaml

@@ -0,0 +1,98 @@
+# Compact stochastic feature set + sp_ou_zscore (OU mean-reversion) for a new run in MLflow exp 25.
+# Same setup as exp24 (compact baseline) plus the stable 5-day mean-reversion feature sp_ou_zscore.
+{%- set LAKE = TAC_LAKE_DIR %}
+{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
+{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead,sp_ou_zscore" %}
+
+qlib_init:
+    provider_uri: "{{ LAKE }}"
+    region: us
+    expression_cache: null
+    dataset_cache: null
+    calendar_provider:
+        class: tac_qlib.data.providers.LakeCalendarProvider
+        kwargs: { lake_root: "{{ LAKE }}", market: US }
+    instrument_provider:
+        class: tac_qlib.data.providers.LakeInstrumentProvider
+        kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
+    feature_provider:
+        class: tac_qlib.data.providers.LakeFeatureProvider
+        kwargs: { lake_root: "{{ LAKE }}", market: US }
+    exp_manager:
+        class: MLflowExpManager
+        module_path: qlib.workflow.expm
+        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-exp22-stochastic-general" }
+
+task:
+    model:
+        class: RankICEnsembleLGBModel
+        module_path: tac_qlib.contrib.model.rank_ensemble
+        kwargs:
+            loss: mse
+            learning_rate: 0.02
+            num_leaves: 31
+            n_estimators: 3000
+            num_boost_round: 3000
+            early_stopping_rounds: 200
+            min_data_in_leaf: 20
+            lambda_l2: 0.5
+            colsample_bytree: 0.8
+            subsample: 0.8
+            subsample_freq: 1
+            reg_alpha: 0.1
+            reg_lambda: 1.0
+            seeds: "42,7,2026,99,123"
+
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: TACHandler
+                module_path: tac_qlib.contrib.data.handler
+                kwargs:
+                    instruments: "{{ UNIVERSE }}"
+                    start_time: 2015-01-03
+                    end_time: 2026-08-10
+                    fit_start_time: 2016-01-04
+                    fit_end_time: 2025-09-01
+                    freq: day
+                    lake_root: "{{ LAKE }}"
+                    market: US
+                    label: "Ref($close,-6)/Ref($close,-1)-1"
+                    feature_fields: "{{ FEATURES }}"
+                    infer_processors:
+                        - { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
+                        - { class: ProcessInf, kwargs: {} }
+                        - { class: CSRankNorm, kwargs: {} }
+                        - { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
+                        - { class: Fillna, kwargs: {} }
+            segments:
+                train: [2016-01-04, 2025-09-01]
+                valid: [2025-09-03, 2026-01-03]
+                test: [2026-01-04, 2026-08-10]
+
+    record:
+        - { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
+        - { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              config:
+                  strategy:
+                      class: TopkDropoutStrategy
+                      module_path: qlib.contrib.strategy
+                      kwargs: { signal: "<PRED>", topk: 10, n_drop: 2, only_tradable: true, risk_degree: 0.95 }
+                  backtest:
+                      start_time: 2026-01-04
+                      end_time: 2026-08-10
+                      account: 1000000
+                      benchmark: SPY
+                      exchange_kwargs:
+                          codes: "{{ UNIVERSE }}"
+                          deal_price: $close
+                          freq: day
+                          open_cost: 0.0005
+                          close_cost: 0.0015
+                          min_cost: 5.0
+              risk_analysis_freq: 1d