start experiment 62 (exp/62-scheduled-algo-retrain-on-2026-08-25-tac)

code/MANIFEST.txt

@@ -1,34 +1,34 @@
 # TradeAC custom-qlib-code snapshot (auto-generated)
-# parent repo HEAD : ee5aa8e73c5286860d3ec1dfa6001bf0f8b6690d
+# parent repo HEAD : 1142cc9eefde88739f33f34aa96af7b182320d96
 #   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
+  6c57851807631dfa1a525f87538a1b0a495fd7b2  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
+  1acd2cb845eac1bcee54450004a4af36484544ed  tac-qlib/tac_qlib/contrib/data/__pycache__/__init__.cpython-312.pyc
-  39f148bef96fcce8f548d74c6d338eccdc4145e3  tac-qlib/tac_qlib/contrib/data/__pycache__/handler.cpython-312.pyc
+  2ef18965f77e8955580334d2edc09bd381204355  tac-qlib/tac_qlib/contrib/data/__pycache__/handler.cpython-312.pyc
-  fc3d01d530d4e84b3386614b6ac94324e811920e  tac-qlib/tac_qlib/contrib/data/handler.py
+  3bba0f1696e4ab4b3deebec3f31f269b2e713899  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
+  c975d2b978f2cc08a388a5d921938704a3dd592d  tac-qlib/tac_qlib/contrib/model/__pycache__/__init__.cpython-312.pyc
-  858f5fcbe285642569c214d5803edbae1e5dfa1e  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_ensemble.cpython-312.pyc
+  009ebd83c5156ca3d7039a112e0d277dd416ca86  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
+  1716b680b5623394229f7600ad4c81ad07fa6a2b  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
+  9c9f7743970b1a3827bb72768bb6e8be03040759  tac-qlib/tac_qlib/contrib/strategy/__pycache__/__init__.cpython-312.pyc
-  423ec5cd15b273c119ba3b1d7dc7467fc6ba41c4  tac-qlib/tac_qlib/contrib/strategy/__pycache__/long_short.cpython-312.pyc
+  6e38a7fa8584b80410ccc88e5feff228a7ece38b  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
+  f983d5c2472cd16ef9f14a240674ec0a7f41e81c  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
   92e6e90eb0cd0a25142034560f27adb6b705b1a8  tac-qlib/tac_qlib/data/__init__.py
-  fa1090eb6f17b1b7835038e35fac86334294d165  tac-qlib/tac_qlib/data/__pycache__/__init__.cpython-312.pyc
+  a0e969bd6504bb8d9220f4641cc01e960c3120e4  tac-qlib/tac_qlib/data/__pycache__/__init__.cpython-312.pyc
-  48629a1f51bd4058036ce78d79ed49454982c051  tac-qlib/tac_qlib/data/__pycache__/config.cpython-312.pyc
+  2f8c537d11135155539276bee342d087aad8743e  tac-qlib/tac_qlib/data/__pycache__/config.cpython-312.pyc
-  ad7c9b726c9c52773fa82031fcd681337be97fa8  tac-qlib/tac_qlib/data/__pycache__/providers.cpython-312.pyc
+  53cf7828c425f6b5032b206b93a238607111a6ed  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