finish experiment 28 (exp/28-isolate-the-seed-count-effect-on-the-ndr)

code/MANIFEST.txt

@@ -1,29 +1,27 @@
 # TradeAC custom-qlib-code snapshot (auto-generated)
-# parent repo HEAD : 125be7b96fb5975e798a0b4301eeb5809a8a181c
+# parent repo HEAD : ea75065fb517388e417ad0fea76acf2731fef84e
 #   tac-qlib/tac_qlib/contrib
 #   tac-qlib/tac_qlib/data
 # per-file hashes (git hash-object):
   1b6298c4a5652f2e863cbdc385a1014a570fcd59  tac-qlib/tac_qlib/contrib/__init__.py
-  b8112569f9b2537c45b6535e1a505a207878d322  tac-qlib/tac_qlib/contrib/__pycache__/__init__.cpython-312.pyc
+  b5e28b7c0a10ab553eaa6303013a880731742378  tac-qlib/tac_qlib/contrib/__pycache__/__init__.cpython-312.pyc
   c76a9f17f680e74eea766eff27f7624359749ed6  tac-qlib/tac_qlib/contrib/data/__init__.py
-  8d5333ebd2b44165c50cba639ca2d4ac3fc7cfec  tac-qlib/tac_qlib/contrib/data/__pycache__/__init__.cpython-312.pyc
-  18cb37c0354184c49fa2e598396d7df0634cce0f  tac-qlib/tac_qlib/contrib/data/__pycache__/handler.cpython-312.pyc
-  871ff1e163c29261f140c3f53d42a41e6504c779  tac-qlib/tac_qlib/contrib/data/handler.py
+  715ab312125a446af751b928fe41cf41b99ffcd0  tac-qlib/tac_qlib/contrib/data/__pycache__/__init__.cpython-312.pyc
+  a82a6a236db93097d48748e541c2cf9caa4e48b5  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
-  ab958203f33a99d12c7d923b6efb435189231666  tac-qlib/tac_qlib/contrib/model/__pycache__/__init__.cpython-312.pyc
-  7478f6b0f6de419615c02d4d92b54529f689ef04  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_ensemble.cpython-312.pyc
-  9f9014ddd9bce37490061312d51e8e6fe540fec4  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_gbdt.cpython-312.pyc
-  ce77dea53f6a87c5379782709293bf8ff55b2c75  tac-qlib/tac_qlib/contrib/model/rank_ensemble.py
+  483221cf1d5bad779d3cf9505269b7fb0b3f165d  tac-qlib/tac_qlib/contrib/model/__pycache__/__init__.cpython-312.pyc
+  1286dec07a861f25691b24f71ecc22d8eb3537df  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_ensemble.cpython-312.pyc
+  5185764bd55dbc63d16582bfcb6adc11b7e6d342  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_gbdt.cpython-312.pyc
+  d3f051f3a8650c42fedc7b367b966f7c74fb5789  tac-qlib/tac_qlib/contrib/model/rank_ensemble.py
   ccfe7d554989aa7f3e5a2128ae663e51b2207149  tac-qlib/tac_qlib/contrib/model/rank_gbdt.py
   4afcf9058231111c412925f4c4b84e81d656db87  tac-qlib/tac_qlib/contrib/strategy/__init__.py
-  74e5ecbbbb20bb71fd5cd083383de4ce88476712  tac-qlib/tac_qlib/contrib/strategy/__pycache__/__init__.cpython-312.pyc
-  afaf562aeaa12cebc8529cd916153252e7e3c38a  tac-qlib/tac_qlib/contrib/strategy/__pycache__/optimal_stop.cpython-312.pyc
-  96a0a25201f0a1bb2fc2190e26228c5c0e711a79  tac-qlib/tac_qlib/contrib/strategy/hmm_risk.py
-  816de5d58ae23d996635d42331cf9fc8963d5dbe  tac-qlib/tac_qlib/contrib/strategy/momentum_gate.py
+  13a8e4a41ce9afde97a55756d666d3ff5cbbec0e  tac-qlib/tac_qlib/contrib/strategy/__pycache__/__init__.cpython-312.pyc
+  0bb5804a79611c66bc25988226ca0f1cdbe1a7eb  tac-qlib/tac_qlib/contrib/strategy/__pycache__/optimal_stop.cpython-312.pyc
   79aaad9e39fcc740a773f4f63c512ce1086cfde0  tac-qlib/tac_qlib/contrib/strategy/optimal_stop.py
   92e6e90eb0cd0a25142034560f27adb6b705b1a8  tac-qlib/tac_qlib/data/__init__.py
-  0ed1ead6c1314a3f25784d453e54a15a8a04baaa  tac-qlib/tac_qlib/data/__pycache__/__init__.cpython-312.pyc
-  9609782800944c45b78bb58eaa7b51ba1b7f8f43  tac-qlib/tac_qlib/data/__pycache__/config.cpython-312.pyc
-  a85628d71d12cfe5b18b1c884c5d829c89594579  tac-qlib/tac_qlib/data/__pycache__/providers.cpython-312.pyc
-  686d36f6d101c547491ca866aa143aa542e17518  tac-qlib/tac_qlib/data/config.py
-  d9f839be30026f337754a3f015425a8efdbe8e2a  tac-qlib/tac_qlib/data/providers.py
+  3cbc0686e6f863d306d93c589a607a5bdb7201f2  tac-qlib/tac_qlib/data/__pycache__/__init__.cpython-312.pyc
+  46bcdbcc173ff3a6281fed33d10c1bcac96876b0  tac-qlib/tac_qlib/data/__pycache__/config.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/data/handler.py

@@ -64,9 +64,13 @@ def check_transform_proc(proc_l, fit_start_time, fit_end_time):
 
 
 def get_common_feature_fields(lake_root=None, market="US", timeframe="1d") -> List[str]:
-    """Discover ta-lib columns present in *every* features parquet file of the lake.
+    """Discover feature columns present in *every* feature file of the lake.
 
-    Returns sorted field names (without the ``$`` prefix). Empty if no features are persisted.
+    Walks the `family=ta|sp` partition layout (plus any legacy flat files).
+    TA and SP columns are disjoint by construction, so the common set is
+    computed per family (columns shared by all symbol files of that family),
+    then the per-family results are unioned. Returns sorted field names
+    (without the ``$`` prefix). Empty if no features are persisted.
     """
     cfg = LakeConfig(lake_root, market)
     feat_dir = cfg.features_dir(timeframe)
@@ -74,16 +78,30 @@ def get_common_feature_fields(lake_root=None, market="US", timeframe="1d") -> Li
         return []
     import pyarrow.parquet as pq
 
-    common = None
-    for p in sorted(feat_dir.glob("symbol=*.parquet")):
-        try:
-            cols = set(pq.read_schema(p).names) - set(NON_FEATURE_COLUMNS)
-        except Exception:  # pragma: no cover - skip unreadable files
-            continue
-        common = cols if common is None else (common & cols)
-        if not common:
-            break
-    return sorted(common) if common else []
+    def _family_common(fam_dir: Path) -> set:
+        common = None
+        for p in sorted(fam_dir.glob("symbol=*.parquet")):
+            try:
+                cols = set(pq.read_schema(p).names) - set(NON_FEATURE_COLUMNS)
+            except Exception:  # pragma: no cover - skip unreadable files
+                continue
+            common = cols if common is None else (common & cols)
+            if not common:
+                break
+        return common or set()
+
+    common: set = set()
+    # family tier: features/market=*/timeframe=*/family=*/symbol=*.parquet
+    for fam in ("ta", "sp"):
+        fam_dir = feat_dir / f"family={fam}"
+        if fam_dir.is_dir():
+            common |= _family_common(fam_dir)
+    # legacy flat: features/market=*/timeframe=*/symbol=*.parquet
+    if (feat_dir / "family=ta").exists() or (feat_dir / "family=sp").exists():
+        pass  # family layout already covered
+    else:
+        common |= _family_common(feat_dir)
+    return sorted(common)
 
 
 class DropAllNaN(processor_module.Processor):

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

@@ -56,7 +56,6 @@ import os
 from concurrent.futures import ThreadPoolExecutor
 from typing import List, Optional
 
-import numpy as np
 import pandas as pd
 
 from qlib.data.dataset import DatasetH
@@ -80,15 +79,11 @@ class RankICEnsembleLGBModel(RankICLGBModel):
         forwarded.
     """
 
-    def __init__(self, seeds: str = "42", parallel: int = 0, weight_mode: str = "equal", **kwargs):
+    def __init__(self, seeds: str = "42", parallel: int = 0, **kwargs):
         self.seeds = [int(s.strip()) for s in str(seeds).split(",") if s.strip()]
         if not self.seeds:
             raise ValueError("seeds must contain at least one integer")
         self.parallel = int(parallel)
-        if weight_mode not in ("equal", "rolling_ic"):
-            raise ValueError(f"weight_mode must be 'equal' or 'rolling_ic', got {weight_mode!r}")
-        self.weight_mode = weight_mode
-        self.rolling_ic_window = int(kwargs.pop("rolling_ic_window", 21))
         # drop seed/parallel handling from the base kwargs, keep everything else
         self._model_kwargs = dict(kwargs)
         super().__init__(**self._model_kwargs)
@@ -184,44 +179,11 @@ class RankICEnsembleLGBModel(RankICLGBModel):
 
     # -------------------------------------------------------------- predict
     def predict(self, dataset: DatasetH, segment="test") -> pd.Series:
-        """Combine per-seed predictions.
-
-        ``weight_mode='equal'`` (default): simple average, as before.
-        ``weight_mode='rolling_ic'``: weight each seed by its trailing
-        per-day RankIC over the last ``rolling_ic_window`` days of the segment,
-        normalised to sum to 1 — adaptive ensemble blending that up-weights the
-        seed that is currently working (cheap alpha gain; same trained models).
-        """
+        """Average the per-seed predictions over the given segment."""
         if not self._models:
             raise ValueError("model is not fitted yet!")
         preds = [m.predict(dataset, segment=segment) for m in self._models]
         if len(preds) == 1:
             return preds[0]
         frame = pd.concat(preds, axis=1)
-        frame.columns = [f"seed{m.params.get('seed', i)}" for i, m in enumerate(self._models)]
-        if self.weight_mode == "equal":
-            return frame.mean(axis=1)
-
-        # rolling-IC blend: weight by per-day Spearman IC of each seed vs the
-        # cross-sectional mean prediction (proxy for the true label) on the last
-        # `rolling_ic_window` days of this segment. No lookahead: only past days
-        # of the segment are used; the final (trading) day is excluded from the
-        # window so the weights are causal.
-        mean_pred = frame.mean(axis=1)
-        dates = sorted(frame.index.get_level_values(0).unique())
-        win = [d for d in dates if d < dates[-1]][-self.rolling_ic_window :]
-        ics = {}
-        for col in frame.columns:
-            if not win:
-                ics[col] = 1.0
-                continue
-            sub = pd.DataFrame({"p": frame[col], "m": mean_pred})
-            vals = []
-            for d in win:
-                s = sub[sub.index.get_level_values(0) == d]
-                if len(s) >= 3 and s["p"].nunique() > 1 and s["m"].nunique() > 1:
-                    vals.append(s["p"].rank().corr(s["m"].rank()))
-            ics[col] = float(np.mean(vals)) if vals else 1.0
-        wsum = sum(ics.values()) or len(ics)
-        weights = {c: v / wsum for c, v in ics.items()}
-        return sum(frame[c] * weights[c] for c in frame.columns)
+        return frame.mean(axis=1)

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

@@ -1,138 +0,0 @@
-"""TopkDropout with HMM high-volatility + drawdown-pause risk gates.
-
-Gates NEW entries on two risk conditions (held names are never force-sold):
-
-1. **HMM high-vol pause**: when the cross-sectional mean of ``sp_hmm_p_regime1``
-   (HMM high-vol regime probability) on the signal date is >= ``hmm_pause_pct``,
-   new buys are paused. The time-series study showed HMM high-vol probability
-   pulses BEFORE sharp moves (regime-change cut) — pausing new exposure at the
-   boundary reduces drawdown from price over-reaction.
-2. **Drawdown pause**: when the account equity drawdown from its running peak
-   exceeds ``drawdown_pause_pct``, new buys are paused. This is the
-   ``drawdown_pause_pct`` risk-limit expressed inside the backtest (the pure
-   executor-side gate is documented as not expressible in a one-shot backtest).
-3. **Liquidity floor**: names whose 20-day average daily dollar volume is below
-   ``liquidity_floor_adv`` are dropped from BUY candidates (the proven mitigant
-   from exp-18: $5M floor cut drawdown 7.9%->5.4% at higher IR).
-
-Implementation: pre-filter the signal score before the base TopkDropout
-decision — non-held names get score 0 when any gate fires.
-
-Wired into a workflow yaml like:
-
-    strategy:
-        class: HmmRiskTopk
-        module_path: tac_qlib.contrib.strategy.hmm_risk
-        kwargs:
-            signal: "<PRED>"
-            topk: 10
-            n_drop: 2
-            only_tradable: true
-            risk_degree: 0.95
-            hmm_pause_pct: 0.70
-            drawdown_pause_pct: 8.0
-            liquidity_floor_adv: 5000000
-"""
-
-from __future__ import annotations
-
-import copy
-from typing import Dict
-
-import numpy as np
-import pandas as pd
-
-from qlib.backtest.decision import TradeDecisionWO
-from qlib.backtest.position import Position
-from qlib.contrib.strategy.signal_strategy import TopkDropoutStrategy
-
-__all__ = ["HmmRiskTopk"]
-
-
-class HmmRiskTopk(TopkDropoutStrategy):
-    """TopkDropoutStrategy with HMM high-vol pause + drawdown pause + liquidity floor."""
-
-    def __init__(
-        self,
-        *,
-        hmm_pause_pct: float = 0.70,
-        drawdown_pause_pct: float = 8.0,
-        liquidity_floor_adv: float = 0.0,
-        **kwargs,
-    ):
-        super().__init__(**kwargs)
-        self.hmm_pause_pct = float(hmm_pause_pct)
-        self.drawdown_pause_pct = float(drawdown_pause_pct)
-        self.liquidity_floor_adv = float(liquidity_floor_adv)
-        self._peak_equity = 0.0
-
-    # ------------------------------------------------------------- gates
-    def _hmm_high_vol(self, pred_date) -> bool:
-        """Cross-sectional mean HMM high-vol regime probability >= threshold."""
-        try:
-            from qlib.data import D
-
-            feat = D.features(D.instruments("all"), ["$sp_hmm_p_regime1"],
-                              start_time=pred_date, end_time=pred_date)
-            if feat is None or len(feat) == 0:
-                return False
-            p = feat["$sp_hmm_p_regime1"].dropna()
-            if len(p) == 0:
-                return False
-            return float(p.mean()) >= self.hmm_pause_pct
-        except Exception:
-            return False
-
-    def _drawdown_active(self, equity: float) -> bool:
-        if self.drawdown_pause_pct <= 0:
-            return False
-        self._peak_equity = max(self._peak_equity, equity)
-        if self._peak_equity <= 0:
-            return False
-        dd = (self._peak_equity - equity) / self._peak_equity * 100.0
-        return dd >= self.drawdown_pause_pct
-
-    def _illiquid(self, codes, asof) -> Dict[str, bool]:
-        if self.liquidity_floor_adv <= 0 or not codes:
-            return {}
-        from tac_qlib.risk_limits import dollar_adv
-
-        adv = dollar_adv(codes, market="US", asof=asof, lookback=20)
-        return {c: adv.get(str(c).upper(), 0.0) < self.liquidity_floor_adv for c in codes}
-
-    # ------------------------------------------------------------- decision
-    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 pred_score is None:
-            return TradeDecisionWO([], self)
-        if isinstance(pred_score, pd.DataFrame):
-            pred_score = pred_score.iloc[:, 0]
-
-        current_temp = copy.deepcopy(self.trade_position)
-        assert isinstance(current_temp, Position)
-        held = {c for c in current_temp.get_stock_list() if abs(current_temp.get_stock_amount(c)) > 1e-6}
-
-        equity = current_temp.get_cash()
-        for code in held:
-            mark = self.trade_exchange.get_deal_price(
-                stock_id=code, start_time=trade_start_time, end_time=trade_end_time, direction=1
-            )
-            if mark is not None and np.isfinite(mark):
-                equity += abs(current_temp.get_stock_amount(code)) * mark
-
-        hmm_pause = self._hmm_high_vol(str(pd.Timestamp(pred_start_time).date()))
-        dd_pause = self._drawdown_active(equity)
-        buys_paused = hmm_pause or dd_pause
-
-        pred_score = pred_score.copy()
-        if buys_paused or self.liquidity_floor_adv > 0:
-            new_codes = [c for c in pred_score.index if c not in held]
-            illiquid = self._illiquid(new_codes, str(pd.Timestamp(pred_start_time).date()))
-            for code in new_codes:
-                if buys_paused or illiquid.get(code, False):
-                    pred_score[code] = -1e9  # cannot enter today
-
-        return super().generate_trade_decision(execute_result)

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

@@ -1,91 +0,0 @@
-"""TopkDropout with a 1-day momentum entry-confirmation gate.
-
-Gates NEW entries on short-term momentum: a name that is not currently held
-may only be bought when its trailing 1-day return is above ``min_momentum``
-(Lag-1 autocorr ~ +0.45 in the time-series study => short-term momentum
-continuation). Held names are never force-sold by this gate — exits stay the
-pure TopkDropout rule.
-
-Implementation: override ``generate_trade_decision`` and zero out the signal
-score of any non-held name that fails the momentum check BEFORE calling the
-base TopkDropout decision, so it can never be selected as a buy candidate.
-This is a clean pre-filter: the rest of the strategy (top-k, n_drop, sizing,
-costs) is untouched.
-
-Wired into a workflow yaml like:
-
-    strategy:
-        class: MomentumGateTopk
-        module_path: tac_qlib.contrib.strategy.momentum_gate
-        kwargs:
-            signal: "<PRED>"
-            topk: 10
-            n_drop: 2
-            only_tradable: true
-            risk_degree: 0.95
-            min_momentum: 0.0
-"""
-
-from __future__ import annotations
-
-import copy
-
-import pandas as pd
-
-from qlib.backtest.decision import TradeDecisionWO
-from qlib.backtest.position import Position
-from qlib.contrib.strategy.signal_strategy import TopkDropoutStrategy
-
-__all__ = ["MomentumGateTopk"]
-
-
-class MomentumGateTopk(TopkDropoutStrategy):
-    """TopkDropoutStrategy gated on 1-day momentum for new entries."""
-
-    def __init__(self, *, min_momentum: float = 0.0, **kwargs):
-        super().__init__(**kwargs)
-        self.min_momentum = float(min_momentum)
-
-    def _momentum_ok(self, code, trade_start, trade_end) -> bool:
-        """True when the trailing 1-day return is above the momentum floor."""
-        try:
-            cur = self.trade_exchange.get_deal_price(
-                stock_id=code, start_time=trade_start, end_time=trade_end, direction=1
-            )
-        except Exception:
-            return False
-        if cur is None or cur != cur or cur <= 0:
-            return False
-        prev_start = trade_start - pd.Timedelta(days=5)
-        prev_end = trade_start - pd.Timedelta(seconds=1)
-        prev = self.trade_exchange.get_deal_price(
-            stock_id=code, start_time=prev_start, end_time=prev_end, direction=0
-        )
-        if prev is None or prev != prev or prev <= 0:
-            return False
-        return (cur / prev - 1.0) >= self.min_momentum
-
-    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 pred_score is None:
-            return TradeDecisionWO([], self)
-        if isinstance(pred_score, pd.DataFrame):
-            pred_score = pred_score.iloc[:, 0]
-
-        current_temp = copy.deepcopy(self.trade_position)
-        assert isinstance(current_temp, Position)
-        held = set(current_temp.get_stock_list())
-        held = {c for c in held if abs(current_temp.get_stock_amount(c)) > 1e-6}
-
-        # pre-filter: zero the score of non-held names that fail momentum
-        pred_score = pred_score.copy()
-        for code in pred_score.index:
-            if code in held:
-                continue  # never gate exits / re-balancing of held names
-            if not self._momentum_ok(code, trade_start_time, trade_end_time):
-                pred_score[code] = -1e9  # cannot enter today
-
-        return super().generate_trade_decision(execute_result)

code/tac-qlib/tac_qlib/data/config.py

@@ -6,10 +6,11 @@ The lake is a hive-partitioned parquet store (see ``tac-engine/skills/tradeac-la
     ├── market=US/
     │   └── timeframe=1d/
     │       └── symbol=AAPL.parquet        # OHLCV bars: t, date, o, h, l, c, v, n, vw
-    ├── features/                          # ta-lib indicators, wide format
+    ├── features/                          # indicators, wide format, family tier
     │   └── market=US/
     │       └── timeframe=1d/
-    │           └── symbol=AAPL.parquet    # t, sma_5, sma_20, rsi_14, ...
+    │           ├── family=ta/symbol=AAPL.parquet  # t, sma_5, sma_20, rsi_14, ...
+    │           └── family=sp/symbol=AAPL.parquet  # t, sp_ou_*, sp_hmm_*, ...
     ├── calendar.parquet                   # trading days per market
     ├── coverage.parquet                   # per (market,timeframe,symbol) loaded windows
     └── symbols.parquet                    # asset master
@@ -107,8 +108,34 @@ class LakeConfig:
         return self.lake_root / "features" / f"market={self.market}" / f"timeframe={timeframe}"
 
     def features_path(self, timeframe: str, symbol: str) -> Path:
+        # Legacy flat path (no family tier). Prefer `load_features` which
+        # resolves the family=ta|sp partition layout.
         return self.features_dir(timeframe) / f"symbol={str(symbol).upper()}.parquet"
 
+    def load_features(self, timeframe: str, symbol: str) -> pd.DataFrame:
+        """All feature columns for a symbol, merging the `family=ta` and
+        `family=sp` partitions by timestamp. Returns an empty frame when no
+        feature files exist (legacy flat layout falls back transparently)."""
+        sym = str(symbol).upper()
+        frames = []
+        for family in ("ta", "sp"):
+            p = self.features_dir(timeframe) / f"family={family}" / f"symbol={sym}.parquet"
+            if p.exists():
+                frames.append(pd.read_parquet(p))
+        if not frames:
+            flat = self.features_dir(timeframe) / f"symbol={sym}.parquet"
+            if flat.exists():
+                return pd.read_parquet(flat)
+            return pd.DataFrame()
+        if len(frames) == 1:
+            return frames[0]
+        merged = frames[0]
+        for extra in frames[1:]:
+            merged = merged.merge(extra, on="t", how="outer", suffixes=("", "_dup"))
+            for c in [c for c in merged.columns if c.endswith("_dup")]:
+                merged = merged.drop(columns=c)
+        return merged
+
     def calendar_path(self) -> Path:
         return self.lake_root / "calendar.parquet"
 

code/tac-qlib/tac_qlib/data/providers.py

@@ -173,8 +173,7 @@ class LakeFeatureProvider(FeatureProvider):
     def _load_feature_df(self, instrument: str, timeframe: str) -> pd.DataFrame:
         key = (instrument, timeframe)
         if key not in self._feature_cache:
-            p = self.cfg.features_path(timeframe, instrument)
-            self._feature_cache[key] = pd.read_parquet(p) if p.exists() else pd.DataFrame()
+            self._feature_cache[key] = self.cfg.load_features(timeframe, instrument)
         return self._feature_cache[key]
 
     @staticmethod

workflows/exp18-risk-limit/a_baseline.yaml

@@ -1,141 +0,0 @@
-# -----------------------------------------------------------------------------
-# EXP 18 - Risk-limit control: reference model + TopkDropout baseline (A).
-#
-# Signal/model identical to the reference (tac-rd-rank-ensemble-isolated,
-# run 0cea66d9...): RankICEnsembleLGBModel (parallel, 5 seeds) on the 50-ETF
-# SP-5d panel, test 2026-01-04..2026-08-10. This workflow reproduces the
-# unconstrained TopkDropout baseline net-of-cost so the risk-limited variant
-# (same pred, liquidity/size/concentration caps) can be compared 1:1.
-#
-# The risk_limits spec itself is applied via rd_backtest / rd_strategy_targets
-# (tool-level param, not a YAML key); this run records the unconstrained
-# baseline that the limit A/B is measured against.
-#
-# Run:
-#   rd_run_workflow config_path=experiments/workflows/exp18-risk-limit/a_baseline.yaml \
-#       experiment_name=tac-rd-risk-limit
-# -----------------------------------------------------------------------------
-{%- 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-risk-limit"
-
-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"
-            parallel: 5
-
-    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/exp20-risk-limit-improve/r2_momentum.yaml

@@ -1,136 +0,0 @@
-# -----------------------------------------------------------------------------
-# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
-#
-# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
-# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
-# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
-#
-# Run:
-#   rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
-#       experiment_name=tac-rd-risk-limit
-# -----------------------------------------------------------------------------
-{%- 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-risk-limit"
-
-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"
-            parallel: 5
-
-    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: MomentumGateTopk
-                      module_path: tac_qlib.contrib.strategy.momentum_gate
-                      kwargs:
-                          signal: "<PRED>"
-                          topk: 10
-                          n_drop: 2
-                          min_momentum: 0.0
-                          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/exp20-risk-limit-improve/r3_hmm_risk.yaml

@@ -1,138 +0,0 @@
-# -----------------------------------------------------------------------------
-# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
-#
-# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
-# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
-# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
-#
-# Run:
-#   rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
-#       experiment_name=tac-rd-risk-limit
-# -----------------------------------------------------------------------------
-{%- 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-risk-limit"
-
-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"
-            parallel: 5
-
-    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: HmmRiskTopk
-                      module_path: tac_qlib.contrib.strategy.hmm_risk
-                      kwargs:
-                          signal: "<PRED>"
-                          topk: 10
-                          n_drop: 2
-                          hmm_pause_pct: 0.70
-                          drawdown_pause_pct: 8.0
-                          liquidity_floor_adv: 5000000
-                          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/exp20-risk-limit-improve/r4_rolling_ic.yaml

@@ -1,137 +0,0 @@
-# -----------------------------------------------------------------------------
-# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
-#
-# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
-# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
-# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
-#
-# Run:
-#   rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
-#       experiment_name=tac-rd-risk-limit
-# -----------------------------------------------------------------------------
-{%- 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-risk-limit"
-
-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"
-            weight_mode: rolling_ic
-            rolling_ic_window: 21
-            parallel: 5
-
-    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

@@ -1,47 +1,26 @@
-# -----------------------------------------------------------------------------
-# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
-#
-# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
-# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
-# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
-#
-# Run:
-#   rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
-#       experiment_name=tac-rd-risk-limit
-# -----------------------------------------------------------------------------
+# 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 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" %}
+{%- 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
+        kwargs: { lake_root: "{{ LAKE }}", market: US }
     instrument_provider:
         class: tac_qlib.data.providers.LakeInstrumentProvider
-        kwargs:
-            lake_root: "{{ LAKE }}"
-            market: US
-            markets: {}
+        kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
     feature_provider:
         class: tac_qlib.data.providers.LakeFeatureProvider
-        kwargs:
-            lake_root: "{{ LAKE }}"
-            market: US
-
+        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-risk-limit"
+        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-exp16-db-ta-sp" }
 
 task:
     model:
@@ -62,7 +41,6 @@ task:
             reg_alpha: 0.1
             reg_lambda: 1.0
             seeds: "42,7,2026,99,123"
-            parallel: 1
 
     dataset:
         class: DatasetH
@@ -74,39 +52,28 @@ task:
                 kwargs:
                     instruments: "{{ UNIVERSE }}"
                     start_time: 2015-01-03
-                    end_time: 2026-08-14
+                    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: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
+                    feature_fields: "{{ FEATURES }}"
                     infer_processors:
-                        - class: DropAllNaN
-                          kwargs: {}
-                        - class: ProcessInf
-                          kwargs: {}
-                        - class: CSRankNorm
-                          kwargs: {}
-                        - class: ZScoreNorm
-                          kwargs: {}
-                        - class: Fillna
-                          kwargs: {}
+                        - { 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: 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:
@@ -114,12 +81,7 @@ task:
                   strategy:
                       class: TopkDropoutStrategy
                       module_path: qlib.contrib.strategy
-                      kwargs:
-                          signal: "<PRED>"
-                          topk: 10
-                          n_drop: 2
-                          only_tradable: true
-                          risk_degree: 0.95
+                      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

workflows/exp23/workflow.yaml

@@ -1,47 +1,26 @@
-# -----------------------------------------------------------------------------
-# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
-#
-# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
-# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
-# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
-#
-# Run:
-#   rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
-#       experiment_name=tac-rd-risk-limit
-# -----------------------------------------------------------------------------
+# 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 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" %}
+{%- 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
+        kwargs: { lake_root: "{{ LAKE }}", market: US }
     instrument_provider:
         class: tac_qlib.data.providers.LakeInstrumentProvider
-        kwargs:
-            lake_root: "{{ LAKE }}"
-            market: US
-            markets: {}
+        kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
     feature_provider:
         class: tac_qlib.data.providers.LakeFeatureProvider
-        kwargs:
-            lake_root: "{{ LAKE }}"
-            market: US
-
+        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-risk-limit"
+        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-exp22-stochastic-general" }
 
 task:
     model:
@@ -62,7 +41,6 @@ task:
             reg_alpha: 0.1
             reg_lambda: 1.0
             seeds: "42,7,2026,99,123"
-            parallel: 5
 
     dataset:
         class: DatasetH
@@ -74,39 +52,28 @@ task:
                 kwargs:
                     instruments: "{{ UNIVERSE }}"
                     start_time: 2015-01-03
-                    end_time: 2026-08-14
+                    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: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
+                    feature_fields: "{{ FEATURES }}"
                     infer_processors:
-                        - class: DropAllNaN
-                          kwargs: {}
-                        - class: ProcessInf
-                          kwargs: {}
-                        - class: CSRankNorm
-                          kwargs: {}
-                        - class: ZScoreNorm
-                          kwargs: {}
-                        - class: Fillna
-                          kwargs: {}
+                        - { 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: 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:
@@ -114,12 +81,7 @@ task:
                   strategy:
                       class: TopkDropoutStrategy
                       module_path: qlib.contrib.strategy
-                      kwargs:
-                          signal: "<PRED>"
-                          topk: 10
-                          n_drop: 2
-                          only_tradable: true
-                          risk_degree: 0.95
+                      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

workflows/exp24/workflow.yaml

@@ -1,47 +1,26 @@
-# -----------------------------------------------------------------------------
-# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
-#
-# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
-# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
-# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
-#
-# Run:
-#   rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
-#       experiment_name=tac-rd-risk-limit
-# -----------------------------------------------------------------------------
+# 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 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,sma_3,ema_3" %}
+{%- 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
+        kwargs: { lake_root: "{{ LAKE }}", market: US }
     instrument_provider:
         class: tac_qlib.data.providers.LakeInstrumentProvider
-        kwargs:
-            lake_root: "{{ LAKE }}"
-            market: US
-            markets: {}
+        kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
     feature_provider:
         class: tac_qlib.data.providers.LakeFeatureProvider
-        kwargs:
-            lake_root: "{{ LAKE }}"
-            market: US
-
+        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-risk-limit"
+        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-exp22-stochastic-general" }
 
 task:
     model:
@@ -62,7 +41,6 @@ task:
             reg_alpha: 0.1
             reg_lambda: 1.0
             seeds: "42,7,2026,99,123"
-            parallel: 5
 
     dataset:
         class: DatasetH
@@ -74,39 +52,28 @@ task:
                 kwargs:
                     instruments: "{{ UNIVERSE }}"
                     start_time: 2015-01-03
-                    end_time: 2026-08-14
+                    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: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
+                    feature_fields: "{{ FEATURES }}"
                     infer_processors:
-                        - class: DropAllNaN
-                          kwargs: {}
-                        - class: ProcessInf
-                          kwargs: {}
-                        - class: CSRankNorm
-                          kwargs: {}
-                        - class: ZScoreNorm
-                          kwargs: {}
-                        - class: Fillna
-                          kwargs: {}
+                        - { 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: 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:
@@ -114,12 +81,7 @@ task:
                   strategy:
                       class: TopkDropoutStrategy
                       module_path: qlib.contrib.strategy
-                      kwargs:
-                          signal: "<PRED>"
-                          topk: 10
-                          n_drop: 2
-                          only_tradable: true
-                          risk_degree: 0.95
+                      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

workflows/exp26/workflow.yaml

@@ -0,0 +1,98 @@
+# Compact stochastic feature set with reduced turnover: n_drop=1 instead of 2.
+# Same setup as exp24 (compact baseline) but replacing the TopkDropout n_drop 2 with 1.
+{%- 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: 1, 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/exp28/workflow.yaml

@@ -1,47 +1,28 @@
-# -----------------------------------------------------------------------------
-# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
-#
-# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
-# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
-# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
-#
-# Run:
-#   rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
-#       experiment_name=tac-rd-risk-limit
-# -----------------------------------------------------------------------------
+# 2-seed RankICEnsemble comparison on the compact stochastic set, n_drop=1.
+# Exact copy of exp26 (reference: expId=25 run=21afc6afdb674a399b59dd76c97628ce)
+# except seeds=42,7 and parallel=2. Test whether 5 seeds are needed vs 2.
 {%- 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" %}
+{%- 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
+        kwargs: { lake_root: "{{ LAKE }}", market: US }
     instrument_provider:
         class: tac_qlib.data.providers.LakeInstrumentProvider
-        kwargs:
-            lake_root: "{{ LAKE }}"
-            market: US
-            markets: {}
+        kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
     feature_provider:
         class: tac_qlib.data.providers.LakeFeatureProvider
-        kwargs:
-            lake_root: "{{ LAKE }}"
-            market: US
-
+        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-risk-limit"
+        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-exp28-2seed" }
 
 task:
     model:
@@ -74,39 +55,28 @@ task:
                 kwargs:
                     instruments: "{{ UNIVERSE }}"
                     start_time: 2015-01-03
-                    end_time: 2026-08-14
+                    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: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
+                    feature_fields: "{{ FEATURES }}"
                     infer_processors:
-                        - class: DropAllNaN
-                          kwargs: {}
-                        - class: ProcessInf
-                          kwargs: {}
-                        - class: CSRankNorm
-                          kwargs: {}
-                        - class: ZScoreNorm
-                          kwargs: {}
-                        - class: Fillna
-                          kwargs: {}
+                        - { 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: 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:
@@ -114,12 +84,7 @@ task:
                   strategy:
                       class: TopkDropoutStrategy
                       module_path: qlib.contrib.strategy
-                      kwargs:
-                          signal: "<PRED>"
-                          topk: 10
-                          n_drop: 2
-                          only_tradable: true
-                          risk_degree: 0.95
+                      kwargs: { signal: "<PRED>", topk: 10, n_drop: 1, only_tradable: true, risk_degree: 0.95 }
                   backtest:
                       start_time: 2026-01-04
                       end_time: 2026-08-10
@@ -132,4 +97,4 @@ task:
                           open_cost: 0.0005
                           close_cost: 0.0015
                           min_cost: 5.0
-              risk_analysis_freq: 1d
+              risk_analysis_freq: 1d