start experiment 75 (exp/75-scheduled-re-train-for-2026-09-16-round)

code/MANIFEST.txt

@@ -1,34 +1,25 @@
 # TradeAC custom-qlib-code snapshot (auto-generated)
-# parent repo HEAD : ee5aa8e73c5286860d3ec1dfa6001bf0f8b6690d
+# parent repo HEAD : fd5382caa4c4e96417a16d5a22006d9a7d625d00
 #   tac-qlib/tac_qlib/contrib
 #   tac-qlib/tac_qlib/data
 # per-file hashes (git hash-object):
   1b6298c4a5652f2e863cbdc385a1014a570fcd59  tac-qlib/tac_qlib/contrib/__init__.py
-  e21663470e4ab108691392c3f0bcff0a3e7fe459  tac-qlib/tac_qlib/contrib/__pycache__/__init__.cpython-312.pyc
   2224424d0ff193be4f55d1b791f8fce89439c5d2  tac-qlib/tac_qlib/contrib/backtest/__init__.py
   0bf40dee440ddbded357d7bbb4efc67c62c4b084  tac-qlib/tac_qlib/contrib/backtest/tradeac_exchange.py
   c76a9f17f680e74eea766eff27f7624359749ed6  tac-qlib/tac_qlib/contrib/data/__init__.py
-  a5c6952e9c8bab2c83fd8030416999726aea73d9  tac-qlib/tac_qlib/contrib/data/__pycache__/__init__.cpython-312.pyc
+  3bba0f1696e4ab4b3deebec3f31f269b2e713899  tac-qlib/tac_qlib/contrib/data/handler.py
-  39f148bef96fcce8f548d74c6d338eccdc4145e3  tac-qlib/tac_qlib/contrib/data/__pycache__/handler.cpython-312.pyc
-  fc3d01d530d4e84b3386614b6ac94324e811920e  tac-qlib/tac_qlib/contrib/data/handler.py
   b151d139a0dcde87d74b21e7c4b729176ba5c39b  tac-qlib/tac_qlib/contrib/model/__init__.py
-  f76257db439b030d84ecea2b8ae67079bae4dc6f  tac-qlib/tac_qlib/contrib/model/__pycache__/__init__.cpython-312.pyc
-  858f5fcbe285642569c214d5803edbae1e5dfa1e  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_ensemble.cpython-312.pyc
-  7de125f7f263c554b3337138c760d44394b4824a  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
   184f80da8edf944bad3c8fb4d4d3d189bf4f082b  tac-qlib/tac_qlib/contrib/strategy/__init__.py
-  6893c2097f0de110909f3f5076ac1c32ac5b742b  tac-qlib/tac_qlib/contrib/strategy/__pycache__/__init__.cpython-312.pyc
-  423ec5cd15b273c119ba3b1d7dc7467fc6ba41c4  tac-qlib/tac_qlib/contrib/strategy/__pycache__/long_short.cpython-312.pyc
-  b6b3238699337d559868cb5f8e0c3e900e5da0cf  tac-qlib/tac_qlib/contrib/strategy/__pycache__/optimal_stop.cpython-312.pyc
   896ef74ae47bcd1ed388e1e5d9c8d70c28097fe9  tac-qlib/tac_qlib/contrib/strategy/kelly_dropout.py
   9090fc6dfbd339f2f4df4b0c9b87f400ecb5c9d5  tac-qlib/tac_qlib/contrib/strategy/long_short.py
   79aaad9e39fcc740a773f4f63c512ce1086cfde0  tac-qlib/tac_qlib/contrib/strategy/optimal_stop.py
   5b9acfb4340111b204249add7760bd53c6ae03f1  tac-qlib/tac_qlib/contrib/strategy/regime_gate.py
-  fe60bacdfedd48617863be31f24b7c7daebfac5a  tac-qlib/tac_qlib/contrib/strategy/weekly_rebalance.py
+  839abb89ad40cd516eabcfd91fe1be626b9f091f  tac-qlib/tac_qlib/contrib/strategy/weekly_rebalance.py
   92e6e90eb0cd0a25142034560f27adb6b705b1a8  tac-qlib/tac_qlib/data/__init__.py
-  fa1090eb6f17b1b7835038e35fac86334294d165  tac-qlib/tac_qlib/data/__pycache__/__init__.cpython-312.pyc
+  6963ba16f49411450562d381fd6ba89e4a7b3e28  tac-qlib/tac_qlib/data/__pycache__/__init__.cpython-312.pyc
-  48629a1f51bd4058036ce78d79ed49454982c051  tac-qlib/tac_qlib/data/__pycache__/config.cpython-312.pyc
+  fb3c8faf2701e3e2e5abf9a8958f2684783fbd74  tac-qlib/tac_qlib/data/__pycache__/config.cpython-312.pyc
-  ad7c9b726c9c52773fa82031fcd681337be97fa8  tac-qlib/tac_qlib/data/__pycache__/providers.cpython-312.pyc
+  67cc6fa7b0fe0a87b1882dd736123ffead6a5163  tac-qlib/tac_qlib/data/__pycache__/providers.cpython-312.pyc
   1953fb2a6371525db7f7b0e1c9dfbf3492d82110  tac-qlib/tac_qlib/data/config.py
   8d0644f6f0d1efb94798ed444cc73e63b643459b  tac-qlib/tac_qlib/data/providers.py

code/tac-qlib/tac_qlib/contrib/data/handler.py

@@ -15,6 +15,9 @@ import os
 from inspect import getfullargspec
 from typing import List, Optional, Tuple, Union
 
+import numpy as np
+import pandas as pd
+
 from qlib.data.dataset import processor as processor_module
 from qlib.data.dataset.handler import DataHandlerLP
 from qlib.utils import get_callable_kwargs
@@ -144,6 +147,174 @@ class DropAllNaN(processor_module.Processor):
         return df
 
 
+class BenchResidual(processor_module.Processor):
+    """Subtract a benchmark instrument's forward return from the label, per datetime.
+
+    Turns the training target from an absolute-return rank into a *residual* rank:
+    ``r_i - r_bench`` is ranked cross-sectionally by the downstream ``CSRankNorm`` /
+    ``CSZScoreNorm`` processors instead of ``r_i`` alone. Must be inserted BEFORE any
+    per-date normalization so the ranking itself is computed on residual returns
+    (ordering flips exactly where the benchmark trends).
+
+    Stateless: ``fit`` is a no-op and the benchmark forward return is recomputed from
+    the lake parquet on first ``__call__``. Rows whose benchmark value is missing are
+    left untouched. Accepts ``fit_start_time``/``fit_end_time`` (ignored) so
+    ``check_transform_proc`` can inject the fit window uniformly.
+
+    NOTE: under any cross-sectional normalization downstream (``CSRankNorm`` /
+    ``CSZScoreNorm``) this processor is a mathematical no-op: subtracting the same
+    per-date constant preserves ranks, and z-scoring absorbs constant shifts. Use
+    ``BenchBetaResidual`` for a target that actually reorders.
+    """
+
+    def __init__(
+        self,
+        benchmark="SPY",
+        fields_group="label",
+        lake_root=None,
+        market="US",
+        timeframe=None,
+        freq="day",
+        fit_start_time=None,
+        fit_end_time=None,
+    ):
+        self.benchmark = benchmark
+        self.fields_group = fields_group
+        self.lake_root = lake_root
+        self.market = market
+        self.timeframe = timeframe or timeframe_for_freq(freq)
+        self.fit_start_time = fit_start_time
+        self.fit_end_time = fit_end_time
+        self._bench_label = None
+
+    def _load_bench_label(self):
+        if self._bench_label is not None:
+            return self._bench_label
+        cfg = LakeConfig(self.lake_root, self.market)
+        p = cfg.bar_path(self.timeframe, self.benchmark)
+        if not p.exists():
+            raise FileNotFoundError(f"BenchResidual: benchmark bar file not found: {p}")
+        df = pd.read_parquet(p)
+        s = pd.Series(df["c"].astype(float).values, index=pd.to_datetime(df["t"])).sort_index()
+        s.index = s.index.normalize()
+        # mirror Ref($close,-6)/Ref($close,-1)-1 on the benchmark's own calendar
+        bench_label = s.shift(-6) / s.shift(-1) - 1
+        self._bench_label = bench_label[~bench_label.index.duplicated(keep="last")]
+        return self._bench_label
+
+    def fit(self, df=None):
+        return self
+
+    def __call__(self, df):
+        bl = self._load_bench_label()
+        cols = processor_module.get_group_columns(df, self.fields_group)
+        dt = df.index.get_level_values("datetime")
+        aligned = bl.reindex(pd.DatetimeIndex(dt.unique())).reindex(dt)
+        mask = aligned.notna().values
+        out = df.copy()
+        for c in cols:
+            vals = df[c].values
+            res = vals.copy()
+            res[mask] = np.asarray(vals[mask], dtype=float) - aligned[mask].values
+            out[c] = res
+        return out
+
+
+class BenchBetaResidual(processor_module.Processor):
+    """Residualize the label against a beta-scaled benchmark move: ``r_i - b_i * r_bench``.
+
+    Unlike a plain constant subtraction (see ``BenchResidual``), the name-specific rolling
+    beta ``b_i`` makes this survive cross-sectional normalization: in up-weeks high-beta
+    names lose rank, in down-weeks they gain — exactly the relative structure an absolute-
+    return ranking hides.
+
+    Beta is estimated from *past* data only (rolling ``window`` trading days of daily close
+    returns of each instrument vs the benchmark, both read up to and including ``t``), so
+    no lookahead enters the target. The benchmark leg uses the same horizon as the label
+    expression (``Ref($close,-6)/Ref($close,-1)-1`` by default via ``horizon``/``base``,
+    matching the yaml's 6-day label). Rows with missing beta or benchmark values keep
+    their raw label.
+
+    Requires ``$close`` to be present in the feature group (it always is for TACHandler).
+    Stateless; accepts ``fit_start_time``/``fit_end_time`` (ignored) for uniform kwargs
+    injection. Must be inserted BEFORE any per-date normalization processor.
+    """
+
+    def __init__(
+        self,
+        benchmark="SPY",
+        fields_group="label",
+        lake_root=None,
+        market="US",
+        timeframe=None,
+        freq="day",
+        window=63,
+        horizon=6,
+        base=1,
+        feature_field="$close",
+        fit_start_time=None,
+        fit_end_time=None,
+    ):
+        self.benchmark = benchmark
+        self.fields_group = fields_group
+        self.lake_root = lake_root
+        self.market = market
+        self.timeframe = timeframe or timeframe_for_freq(freq)
+        self.window = int(window)
+        self.horizon = int(horizon)
+        self.base = int(base)
+        self.feature_field = feature_field
+        self.fit_start_time = fit_start_time
+        self.fit_end_time = fit_end_time
+        self._bench = None
+
+    def _load_bench_close(self):
+        if self._bench is not None:
+            return self._bench
+        cfg = LakeConfig(self.lake_root, self.market)
+        p = cfg.bar_path(self.timeframe, self.benchmark)
+        if not p.exists():
+            raise FileNotFoundError(f"BenchBetaResidual: benchmark bar file not found: {p}")
+        df = pd.read_parquet(p)
+        s = pd.Series(df["c"].astype(float).values, index=pd.to_datetime(df["t"])).sort_index()
+        s.index = s.index.normalize()
+        self._bench = s[~s.index.duplicated(keep="last")]
+        return self._bench
+
+    def fit(self, df=None):
+        return self
+
+    def __call__(self, df):
+        bench = self._load_bench_close()
+
+        # benchmark forward return over the same horizon as the label expression
+        fwd = bench.shift(-(self.base + self.horizon - 1)) / bench.shift(-self.base) - 1
+
+        px_col = ("feature", self.feature_field)
+        if px_col not in df.columns:
+            raise KeyError(f"BenchBetaResidual: {self.feature_field} not found in features")
+        px = df[px_col].unstack("instrument").sort_index()
+        rets = px / px.shift(1) - 1
+        bret = bench.reindex(px.index).pct_change()
+
+        # rolling beta per instrument using data <= t (no lookahead)
+        cov = rets.rolling(self.window, min_periods=max(10, self.window // 2)).cov(bret)
+        var = bret.rolling(self.window, min_periods=max(10, self.window // 2)).var()
+        beta = cov.div(var, axis=0)
+
+        contrib = beta.mul(fwd.reindex(px.index), axis=0)
+        cols = list(processor_module.get_group_columns(df, self.fields_group))
+        out = df.copy()
+        for c in cols:
+            lab = df[c].unstack("instrument").reindex(px.index)
+            resid = lab - contrib.where(contrib.notna() & lab.notna(), 0.0)
+            new_vals = resid.stack()
+            new_vals.index.names = df.index.names
+            # residual where available, raw label otherwise (e.g. beta warm-up rows)
+            out[c] = new_vals.reindex(out.index).fillna(df[c])
+        return out
+
+
 class TACHandler(DataHandlerLP):
     """DataHandlerLP backed by the TradeAC parquet lake.
 
@@ -246,10 +417,12 @@ class TACHandler(DataHandlerLP):
         return get_common_feature_fields(lake_root, market, timeframe_for_freq(freq))
 
 
-__all__ = ["TACHandler", "DropAllNaN", "get_common_feature_fields"]
+__all__ = ["TACHandler", "DropAllNaN", "BenchResidual", "BenchBetaResidual", "get_common_feature_fields"]
 
 
-# Make `DropAllNaN` resolvable by bare name from processor configs (e.g. the default
+# Make `DropAllNaN`/`BenchResidual`/`BenchBetaResidual` resolvable by bare name from processor
-# ``infer_processors`` and workflow yamls that reference it without a ``module_path``),
+# configs (e.g. the default ``infer_processors`` and workflow yamls that reference them without a
-# mirroring how qlib registers its own processors in ``qlib.data.dataset.processor``.
+# ``module_path``), mirroring how qlib registers its own processors in ``qlib.data.dataset.processor``.
 processor_module.DropAllNaN = DropAllNaN
+processor_module.BenchResidual = BenchResidual
+processor_module.BenchBetaResidual = BenchBetaResidual

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

@@ -37,11 +37,20 @@ class WeeklyRebalanceDropoutStrategy(TopkDropoutStrategy):
     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).
+    rebalance_every_n_weeks : rebalance every N ISO weeks instead of every week
+        (default 1 = weekly; 2 = biweekly).  Ignored when
+        ``rebalance_every_n_days`` is set.
+    rebalance_every_n_days : rebalance every N trading days (daily when N=1).
+        When set, overrides the weekly gating logic entirely.
     """
 
-    def __init__(self, *, topk, n_drop, hold_band_pct: float = DEFAULT_HOLD_BAND_PCT, **kwargs):
+    def __init__(self, *, topk, n_drop, hold_band_pct: float = DEFAULT_HOLD_BAND_PCT,
+                 rebalance_every_n_weeks: int = 1,
+                 rebalance_every_n_days: int = 0, **kwargs):
         super().__init__(topk=topk, n_drop=n_drop, **kwargs)
         self.hold_band_pct = hold_band_pct
+        self.rebalance_every_n_weeks = rebalance_every_n_weeks
+        self.rebalance_every_n_days = rebalance_every_n_days
 
     @staticmethod
     def _iso_week(ts) -> tuple:
@@ -53,13 +62,25 @@ class WeeklyRebalanceDropoutStrategy(TopkDropoutStrategy):
         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)
+        if self.rebalance_every_n_days > 0:
-        prev_week = getattr(self, "_last_week", None)
+            # daily gating: count trading steps since last rebalance
-        self._last_week = cur_week
+            step_num = trade_step
+            if hasattr(self, "_last_rebal_step"):
+                if (step_num - self._last_rebal_step) < self.rebalance_every_n_days:
+                    return TradeDecisionWO([], self)
+            self._last_rebal_step = step_num
+        else:
+            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:
+            if prev_week is not None and prev_week == cur_week:
-            # not the first trading day of this ISO week -> hold
+                return TradeDecisionWO([], self)
-            return TradeDecisionWO([], self)
+
+            if self.rebalance_every_n_weeks > 1:
+                week_num = cur_week[1]
+                if prev_week is not None and (week_num % self.rebalance_every_n_weeks) != 1:
+                    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)

workflows/ablate_baseline_all_sp_fields.yaml

@@ -1,133 +0,0 @@
-# -----------------------------------------------------------------------------
-# 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

@@ -1,134 +0,0 @@
-# -----------------------------------------------------------------------------
-# 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

@@ -1,141 +0,0 @@
-# -----------------------------------------------------------------------------
-# 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

@@ -1,97 +0,0 @@
-# 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

@@ -1,97 +0,0 @@
-# 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

@@ -1,97 +0,0 @@
-# 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/exp26/workflow.yaml

@@ -1,98 +0,0 @@
-# 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