finish experiment 31 (exp/31-isolation-run-m3-does-adding-garch11-vol)

code/MANIFEST.txt

@@ -1,34 +1,27 @@
 # TradeAC custom-qlib-code snapshot (auto-generated)
-# parent repo HEAD : 7b9819b163e5d297d6d8862aea48b66c376e2919
+# parent repo HEAD : e660b4f2dd7c521615c54a142eec9266837f2e64
 #   tac-qlib/tac_qlib/contrib
 #   tac-qlib/tac_qlib/data
 # per-file hashes (git hash-object):
   1b6298c4a5652f2e863cbdc385a1014a570fcd59  tac-qlib/tac_qlib/contrib/__init__.py
-  d1a8ec0c9e6c38839e966f687b08ec412f87ec20  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
+  b5e28b7c0a10ab553eaa6303013a880731742378  tac-qlib/tac_qlib/contrib/__pycache__/__init__.cpython-312.pyc
   c76a9f17f680e74eea766eff27f7624359749ed6  tac-qlib/tac_qlib/contrib/data/__init__.py
-  c1543fabfc22e07c7e9942015c4462f84acc1e91  tac-qlib/tac_qlib/contrib/data/__pycache__/__init__.cpython-312.pyc
-  89f5cfc15b946b6ea1fb7724f021024967cdb6c5  tac-qlib/tac_qlib/contrib/data/__pycache__/handler.cpython-312.pyc
-  3bba0f1696e4ab4b3deebec3f31f269b2e713899  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
-  f4e9bf0a78d22e256cade0d794a6958aaa7c6721  tac-qlib/tac_qlib/contrib/model/__pycache__/__init__.cpython-312.pyc
-  c35c166a8449c14fa3cd4972c363d3d9d58620ef  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_ensemble.cpython-312.pyc
-  98be60fe19fedb3d9cb21c3f91ef0e176bd93287  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_gbdt.cpython-312.pyc
+  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
-  d03e6611338918d4aac5eea4adf26f85a3763652  tac-qlib/tac_qlib/contrib/model/rank_gbdt.py
-  184f80da8edf944bad3c8fb4d4d3d189bf4f082b  tac-qlib/tac_qlib/contrib/strategy/__init__.py
-  69684c9c9624cb16c63f3a18a864c49a7db37fa9  tac-qlib/tac_qlib/contrib/strategy/__pycache__/__init__.cpython-312.pyc
-  4d3a5433e57e65e5dc96c6d2999f9d473b696dc4  tac-qlib/tac_qlib/contrib/strategy/__pycache__/long_short.cpython-312.pyc
-  53e72f512b47207a5292a918efef7fee162deef3  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
+  ccfe7d554989aa7f3e5a2128ae663e51b2207149  tac-qlib/tac_qlib/contrib/model/rank_gbdt.py
+  4afcf9058231111c412925f4c4b84e81d656db87  tac-qlib/tac_qlib/contrib/strategy/__init__.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
-  5b9acfb4340111b204249add7760bd53c6ae03f1  tac-qlib/tac_qlib/contrib/strategy/regime_gate.py
-  839abb89ad40cd516eabcfd91fe1be626b9f091f  tac-qlib/tac_qlib/contrib/strategy/weekly_rebalance.py
   92e6e90eb0cd0a25142034560f27adb6b705b1a8  tac-qlib/tac_qlib/data/__init__.py
-  0f1eb6f41d44bd9064b1f16f529dac6bb9d7c3fd  tac-qlib/tac_qlib/data/__pycache__/__init__.cpython-312.pyc
-  cf99dd8a481f6e2d1f323f8d8d754730eadb357a  tac-qlib/tac_qlib/data/__pycache__/config.cpython-312.pyc
-  ddac5bab6578399c0301390d71bae13511a56cb1  tac-qlib/tac_qlib/data/__pycache__/providers.cpython-312.pyc
-  1953fb2a6371525db7f7b0e1c9dfbf3492d82110  tac-qlib/tac_qlib/data/config.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/backtest/__init__.py

@@ -1 +0,0 @@
-from .tradeac_exchange import TradeACExchange

code/tac-qlib/tac_qlib/contrib/backtest/tradeac_exchange.py

@@ -1,432 +0,0 @@
-# Copyright (c) Microsoft Corporation.
-# Licensed under the MIT License.
-"""
-TradeACExchange
-
-A short/borrow enabled Exchange implementation built on top of qlib.backtest.exchange.Exchange.
-This exchange adds simple, configurable margin logic (initial/maintenance), borrowing support for
-shorts, a borrow fee, and a lightweight SMA (Special Memorandum Account) concept to emulate
-behaviors similar to brokers such as IBKR and Alpaca for backtesting purposes.
-
-Notes / limitations
-- This implementation is intentionally lightweight and conservative: it implements the
-  key behaviors needed for strategy/backtest experiments (allowing short selling, computing
-  margin requirements, performing margin-call checks, and tracking SMA-like excess equity).
-- It makes some simplifying assumptions compared to real brokers (no per-product house margins,
-  simplified SMA bookkeeping, borrow availability modeled only by a per-symbol boolean/limit).
-- The Position class in qlib.backtest.position was not changed. To support shorts we update the
-  position.position dict directly when necessary. This keeps integration simple but bypasses some
-  internal Position helpers. Use with care.
-
-API additions
-- allow_short: enable short selling (bool)
-- initial_margin_long/short: fraction required to open a position
-- maintenance_margin_long/short: fraction required to keep a position
-- borrow_fee_rate: periodic borrow fee applied on short value (applied at trade time as additional cost)
-- borrowable: dict mapping stock_id -> bool or float (max borrowable shares). Symbols missing from
-  the dict follow `borrow_default` (default True = unlimited; set False for a strict whitelist)
-- get_sma(position): returns SMA-like excess equity available as "buying power credit"
-- check_margin_call(position): returns True if position is below maintenance requirement
-
-"""
-from __future__ import annotations
-
-from typing import Any, Dict, Optional, Tuple
-
-import numpy as np
-
-from qlib.backtest.decision import Order
-from qlib.backtest.exchange import Exchange
-from qlib.backtest.position import BasePosition
-
-
-class TradeACExchange(Exchange):
-    """An exchange that supports short selling / borrowing and basic margin rules.
-
-    The implementation aims to be compatible with the Exchange API used by Account and
-    Position classes in qlib.backtest. It overrides only the minimum methods required to
-    enable short/borrow behavior and margin calculations.
-    """
-
-    def __init__(
-        self,
-        *args: Any,
-        allow_short: bool = True,
-        initial_margin_long: float = 0.5,
-        initial_margin_short: float = 0.5,
-        maintenance_margin_long: float = 0.25,
-        maintenance_margin_short: float = 0.3,
-        borrow_fee_rate: float = 0.0,
-        borrowable: Optional[Dict[str, float]] = None,
-        borrow_default: bool = True,
-        sma_enabled: bool = True,
-        **kwargs: Any,
-    ) -> None:
-        """Create TradeACExchange.
-
-        Parameters mirror Exchange with additional tradeac-specific options.
-        """
-        super().__init__(*args, **kwargs)
-        self.allow_short = allow_short
-        self.initial_margin_long = initial_margin_long
-        self.initial_margin_short = initial_margin_short
-        self.maintenance_margin_long = maintenance_margin_long
-        self.maintenance_margin_short = maintenance_margin_short
-        self.borrow_fee_rate = borrow_fee_rate
-        # borrowable can be a dict with per-symbol max borrowable amount, or None (unlimited)
-        self.borrowable = borrowable or {}
-        # borrow_default: policy for symbols absent from `borrowable`.
-        #   True  -> unlisted symbols are unlimited-borrowable (legacy behavior)
-        #   False -> unlisted symbols are NOT borrowable; only listed ones can be shorted
-        self.borrow_default = bool(borrow_default)
-        # sma_enabled: whether to expose lightweight SMA calculation
-        self.sma_enabled = sma_enabled
-
-    # --------------------------- Helper calculations ---------------------------
-    def _initial_margin_requirement(self, position: BasePosition) -> float:
-        """Compute the initial margin requirement (money) for the given position.
-
-        We treat longs and shorts separately and sum their required initial margins.
-        """
-        im_req = 0.0
-        for sid in position.get_stock_list():
-            amt = position.get_stock_amount(sid)
-            price = position.get_stock_price(sid)
-            val = amt * price
-            if val > 0:
-                im_req += abs(val) * self.initial_margin_long
-            elif val < 0:
-                im_req += abs(val) * self.initial_margin_short
-        return im_req
-
-    def _maintenance_margin_requirement(self, position: BasePosition) -> float:
-        """Compute the maintenance margin requirement (money) for the given position."""
-        mm_req = 0.0
-        for sid in position.get_stock_list():
-            amt = position.get_stock_amount(sid)
-            price = position.get_stock_price(sid)
-            val = amt * price
-            if val > 0:
-                mm_req += abs(val) * self.maintenance_margin_long
-            elif val < 0:
-                mm_req += abs(val) * self.maintenance_margin_short
-        return mm_req
-
-    def get_equity(self, position: BasePosition) -> float:
-        """Return account equity (position value + cash)."""
-        return position.calculate_value()
-
-    def get_sma(self, position: BasePosition) -> float:
-        """Return a simplified SMA: excess equity above initial margin requirement.
-
-        Note: This is a synthetic/Simplified SMA used for strategy/backtest logic. Real-broker
-        SMA accounting (e.g. credits/debits across days) can be more complex.
-        """
-        if not self.sma_enabled:
-            return 0.0
-        equity = self.get_equity(position)
-        im_req = self._initial_margin_requirement(position)
-        return max(0.0, equity - im_req)
-
-    def check_margin_call(self, position: BasePosition) -> bool:
-        """Return True when the account is under maintenance margin (margin call).
-
-        Margin call condition here is simple: equity < maintenance requirement.
-        """
-        equity = self.get_equity(position)
-        mm_req = self._maintenance_margin_requirement(position)
-        return equity < mm_req
-
-    def get_buying_power(self, position: BasePosition) -> float:
-        """Estimate buying power for new long positions assuming opening margin requirement.
-
-        Simplified: the maximum notional long value = equity / initial_margin_long.
-        """
-        equity = self.get_equity(position)
-        if self.initial_margin_long <= 0:
-            return 0.0
-        return equity / self.initial_margin_long
-
-    # --------------------------- Order / execution overrides ---------------------------
-    def _borrow_headroom(self, stock_id: str, current_short: float) -> float:
-        """Remaining borrowable shares for `stock_id` given an already-open short of `current_short` shares.
-
-        borrowable values: bool (True=unlimited, False=not borrowable) or numeric max shares.
-        Missing symbols follow `borrow_default` (True = unlimited when allow_short is enabled).
-        """
-        if not self.allow_short:
-            return 0.0
-        v = self.borrowable.get(stock_id, self.borrow_default)
-        if isinstance(v, bool):
-            return float("inf") if v else 0.0
-        try:
-            limit = float(v)
-        except (TypeError, ValueError):
-            return float("inf")
-        return max(0.0, limit - max(current_short, 0.0))
-
-    def _calc_trade_info_by_order(
-        self,
-        order: Order,
-        position: Optional[BasePosition],
-        dealt_order_amount: Dict[str, float],
-    ) -> Tuple[float, float, float]:
-        """Override to allow (optionally) short selling and to apply borrow fees.
-
-        The original Exchange implementation forbids selling more than you own. Here we allow
-        sell orders to create/expand short positions when allow_short is True. We still rely on
-        most base logic (price discovery, impact, cost calculation) by calling super(), but we
-        adjust the sell-side clipping behavior before delegating to the base implementation.
-        """
-        # When selling and shorts are allowed, temporarily relax the clipping logic in the base
-        # implementation by monkey-patching current position check. Simpler: replicate minimal
-        # parts of logic from Exchange._calc_trade_info_by_order with the key change.
-
-        # Get basic trade price & volume info using Exchange helpers
-        trade_price = float(self.get_deal_price(order.stock_id, order.start_time, order.end_time, direction=order.direction))
-        total_trade_val = float(self.get_volume(order.stock_id, order.start_time, order.end_time) or 0.0) * trade_price
-
-        order.factor = self.get_factor(order.stock_id, order.start_time, order.end_time)
-        order.deal_amount = order.amount  # attempt full
-
-        # volume clipping (same as base)
-        self._clip_amount_by_volume(order, dealt_order_amount)
-
-        # approximate adjusted cost ratio based on liquidity
-        if not total_trade_val or np.isnan(total_trade_val) or total_trade_val <= 0:
-            adj_cost_ratio = self.impact_cost
-        else:
-            trade_val_tmp = order.deal_amount * trade_price
-            adj_cost_ratio = self.impact_cost * (trade_val_tmp / total_trade_val) ** 2
-
-        # Differentiate buy / sell
-        if order.direction == Order.SELL:
-            cost_ratio = self.close_cost + adj_cost_ratio
-            current_amount = (
-                position.get_stock_amount(order.stock_id) if (position is not None and position.check_stock(order.stock_id)) else 0.0
-            )
-            long_held = max(current_amount, 0.0)
-            short_open = max(-current_amount, 0.0)
-
-            if position is not None:
-                if not self.allow_short:
-                    # clip by current holdings only
-                    if not np.isclose(order.deal_amount, current_amount):
-                        order.deal_amount = self.round_amount_by_trade_unit(
-                            min(long_held, order.deal_amount), order.factor
-                        )
-                else:
-                    # allow selling beyond holdings up to the remaining borrow limit;
-                    # later when updating the position we create/expand a short if necessary.
-                    max_sell = long_held + self._borrow_headroom(order.stock_id, short_open)
-                    if order.deal_amount > max_sell and not np.isclose(order.deal_amount, max_sell):
-                        order.deal_amount = self.round_amount_by_trade_unit(max_sell, order.factor)
-
-        elif order.direction == Order.BUY:
-            cost_ratio = self.open_cost + adj_cost_ratio
-            if position is not None:
-                cash = position.get_cash()
-                trade_val = order.deal_amount * trade_price
-                if cash < max(trade_val * cost_ratio, self.min_cost):
-                    order.deal_amount = 0
-                    self.logger.debug(f"Order clipped due to cost higher than cash: {order}")
-                elif cash < trade_val + max(trade_val * cost_ratio, self.min_cost):
-                    max_buy_amount = self._get_buy_amount_by_cash_limit(trade_price, cash, cost_ratio)
-                    order.deal_amount = self.round_amount_by_trade_unit(min(max_buy_amount, order.deal_amount), order.factor)
-                    self.logger.debug(f"Order clipped due to cash limitation: {order}")
-                else:
-                    order.deal_amount = self.round_amount_by_trade_unit(order.deal_amount, order.factor)
-            else:
-                order.deal_amount = self.round_amount_by_trade_unit(order.deal_amount, order.factor)
-        else:
-            raise NotImplementedError("order direction {} error".format(order.direction))
-
-        # compute final trade_val & trade_cost
-        trade_val = order.deal_amount * trade_price
-        # base trade_cost
-        trade_cost = max(trade_val * cost_ratio, self.min_cost)
-        # apply borrow fee only on the net-new short portion of the sell
-        if order.direction == Order.SELL and self.allow_short:
-            new_short = max(0.0, order.deal_amount - long_held)
-            trade_cost += new_short * trade_price * self.borrow_fee_rate
-
-        if trade_val <= 1e-5:
-            trade_cost = 0
-
-        return trade_price, trade_val, trade_cost
-
-    def deal_order(
-        self,
-        order: Order,
-        trade_account: Optional[Any] = None,
-        position: Optional[BasePosition] = None,
-        dealt_order_amount: Dict[str, float] = None,
-    ) -> Tuple[float, float, float]:
-        """Deal order and handle short position bookkeeping.
-
-        This method mirrors Exchange.deal_order but when a position is provided and shorts are
-        allowed it will update the Position.position dict directly to support negative amounts.
-        """
-        if dealt_order_amount is None:
-            dealt_order_amount = {}
-
-        if not self.check_order(order):
-            order.deal_amount = 0.0
-            self.logger.debug(f"Order failed due to trading limitation: {order}")
-            return 0.0, 0.0, np.nan
-
-        if trade_account is not None and position is not None:
-            raise ValueError("trade_account and position can only choose one")
-
-        pos = position or (trade_account.current_position if trade_account is not None else None)
-        trade_price, trade_val, trade_cost = self._calc_trade_info_by_order(order, pos, dealt_order_amount)
-
-        if trade_val > 1e-5:
-            if trade_account is not None:
-                cp = trade_account.current_position
-                if not cp.skip_update():
-                    held = cp.check_stock(order.stock_id)
-                    # Account-level bookkeeping (turnover/cost/returns). Mirrors
-                    # Account._update_state_from_order except for fresh short sales,
-                    # where no prior price exists to compute order profit from.
-                    if order.direction == Order.SELL and not held:
-                        trade_account.accum_info.add_turnover(trade_val)
-                        trade_account.accum_info.add_cost(trade_cost)
-                        trade_account.accum_info.add_return_value(0.0)
-                    if order.direction == Order.SELL:
-                        # sell: update account state first (stock entry may be deleted)
-                        if held:
-                            trade_account._update_state_from_order(order, trade_val, trade_cost, trade_price)
-                        self._position_sell(cp, order, trade_val, trade_cost, trade_price)
-                    else:
-                        # buy: update position first (entry may be created), then account state
-                        # A buy that covers a short to exactly flat deletes the entry inside
-                        # _position_buy; re-seed a transient zero-amount stub so the
-                        # account's order-profit lookup still finds the trade price,
-                        # then drop it (_update_state_from_order never mutates entries).
-                        sid = order.stock_id
-                        had_entry = isinstance(cp.position.get(sid), dict)
-                        self._position_buy(cp, order, trade_val, trade_cost, trade_price)
-                        covered_to_flat = had_entry and not isinstance(cp.position.get(sid), dict)
-                        if covered_to_flat:
-                            cp.position[sid] = {"amount": 0.0, "price": trade_price, "weight": 0}
-                        trade_account._update_state_from_order(order, trade_val, trade_cost, trade_price)
-                        if covered_to_flat:
-                            cp.position.pop(sid, None)
-            elif position is not None:
-                if order.direction == Order.BUY:
-                    self._position_buy(position, order, trade_val, trade_cost, trade_price)
-                else:
-                    self._position_sell(position, order, trade_val, trade_cost, trade_price)
-        return trade_val, trade_cost, trade_price
-
-    # --------------------------- Position mutation helpers ---------------------------
-    def _position_buy(self, position: BasePosition, order: Order, trade_val: float, cost: float, trade_price: float) -> None:
-        """Handle buy order bookkeeping against a BasePosition while supporting shorts.
-
-        Rules implemented (simplified):
-        - If there is an existing short (amount < 0), the buy will first cover the short.
-        - If covering closes the short completely, the remaining buy becomes a long
-        - Cash updates mimic Position._buy_stock/_sell_stock (cash decreases by trade_val+cost for buys)
-        """
-        trade_amount = trade_val / trade_price
-        sid = order.stock_id
-        current_amount = position.get_stock_amount(sid) if position.check_stock(sid) else 0.0
-
-        # covering existing short
-        if current_amount < -1e-12:
-            # amount is negative -> we are short. Buying reduces the short.
-            new_amount = current_amount + trade_amount
-            if abs(new_amount) <= 1e-8:
-                # short fully covered exactly -> remove entry
-                if sid in position.position:
-                    del position.position[sid]
-            elif new_amount > 0:
-                # short fully covered with leftover buy amount -> leftover becomes a long position
-                position.position[sid] = {"amount": new_amount, "price": trade_price, "weight": 0}
-            else:
-                # partially cover
-                position.position[sid]["amount"] = new_amount
-                position.position[sid]["price"] = trade_price
-        else:
-            # normal or increasing long
-            if sid not in position.position or not isinstance(position.position[sid], dict):
-                # initialize stock
-                position.position[sid] = {"amount": trade_amount, "price": trade_price, "weight": 0}
-            else:
-                position.position[sid]["amount"] = position.position[sid].get("amount", 0.0) + trade_amount
-                position.position[sid]["price"] = trade_price
-
-        # cash effect same as Position._buy_stock
-        position.position["cash"] -= trade_val + cost
-
-    def _position_sell(self, position: BasePosition, order: Order, trade_val: float, cost: float, trade_price: float) -> None:
-        """Handle sell order bookkeeping against a BasePosition while supporting shorts.
-
-        Rules implemented (simplified):
-        - If holding enough long shares, sell will reduce/close the long position normally.
-        - If not holding enough long shares and shorts are allowed, the remaining sold amount will create/expand a short position.
-        - Cash update for sells follows Position._sell_stock logic (cash increases by trade_val - cost)
-        """
-        trade_amount = trade_val / trade_price
-        sid = order.stock_id
-        current_amount = position.get_stock_amount(sid) if position.check_stock(sid) else 0.0
-
-        if current_amount > 1e-12:
-            # we have long shares; sell from them first
-            if trade_amount >= current_amount - 1e-8:
-                # selling all or more than holdings
-                # remove long position
-                if sid in position.position:
-                    del position.position[sid]
-                # remaining sold amount becomes short if allowed
-                remain = trade_amount - current_amount
-                if remain > 1e-8:
-                    if not self.allow_short:
-                        # should not happen due to clipping earlier, but guard anyway
-                        raise ValueError(f"Attempt to short {sid} while shorting disabled")
-                    # create short entry
-                    position.position[sid] = {"amount": -remain, "price": trade_price, "weight": 0}
-            else:
-                # partial sell
-                position.position[sid]["amount"] = current_amount - trade_amount
-                position.position[sid]["price"] = trade_price
-        else:
-            # currently flat or already short
-            if not self.allow_short:
-                raise ValueError(f"Attempt to short {sid} while shorting disabled")
-            # expand short
-            new_amount = current_amount - trade_amount
-            if sid not in position.position or not isinstance(position.position[sid], dict):
-                position.position[sid] = {"amount": new_amount, "price": trade_price, "weight": 0}
-            else:
-                position.position[sid]["amount"] = new_amount
-                position.position[sid]["price"] = trade_price
-
-        # cash effect same as Position._sell_stock
-        new_cash = trade_val - cost
-        if getattr(position, "_settle_type", None) == position.ST_CASH:
-            position.position["cash_delay"] = position.position.get("cash_delay", 0.0) + new_cash
-        else:
-            position.position["cash"] = position.position.get("cash", 0.0) + new_cash
-
-    # --------------------------- Borrow availability helpers ---------------------------
-    def is_borrowable(self, stock_id: str, amount: float) -> bool:
-        """Check whether the requested amount is borrowable for the given stock.
-
-        If a borrowable dict is provided, it may contain either booleans or numeric limits (maximum borrowable shares).
-        Symbols absent from the dict follow `borrow_default`.
-        """
-        if not self.allow_short:
-            return False
-        if stock_id not in self.borrowable:
-            return self.borrow_default
-        v = self.borrowable[stock_id]
-        if isinstance(v, bool):
-            return v
-        try:
-            limit = float(v)
-            return amount <= limit
-        except Exception:
-            return True
-

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

@@ -15,9 +15,6 @@ 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
@@ -25,7 +22,6 @@ from qlib.utils import get_callable_kwargs
 from ...data.config import (
     LakeConfig,
     timeframe_for_freq,
-    FEATURE_FAMILIES,
     NON_FEATURE_COLUMNS,
 )
 
@@ -96,7 +92,7 @@ def get_common_feature_fields(lake_root=None, market="US", timeframe="1d") -> Li
 
     common: set = set()
     # family tier: features/market=*/timeframe=*/family=*/symbol=*.parquet
-    for fam in FEATURE_FAMILIES:
+    for fam in ("ta", "sp"):
         fam_dir = feat_dir / f"family={fam}"
         if fam_dir.is_dir():
             common |= _family_common(fam_dir)
@@ -147,174 +143,6 @@ 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.
 
@@ -417,12 +245,10 @@ class TACHandler(DataHandlerLP):
         return get_common_feature_fields(lake_root, market, timeframe_for_freq(freq))
 
 
-__all__ = ["TACHandler", "DropAllNaN", "BenchResidual", "BenchBetaResidual", "get_common_feature_fields"]
+__all__ = ["TACHandler", "DropAllNaN", "get_common_feature_fields"]
 
 
-# Make `DropAllNaN`/`BenchResidual`/`BenchBetaResidual` resolvable by bare name from processor
-# configs (e.g. the default ``infer_processors`` and workflow yamls that reference them without a
-# ``module_path``), mirroring how qlib registers its own processors in ``qlib.data.dataset.processor``.
+# Make `DropAllNaN` resolvable by bare name from processor configs (e.g. the default
+# ``infer_processors`` and workflow yamls that reference it without a ``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/model/rank_gbdt.py

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

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

@@ -1,4 +1,3 @@
 from .optimal_stop import OptimalStopControl  # noqa: F401
-from .long_short import LongShortTopkStrategy  # noqa: F401
 
-__all__ = ["OptimalStopControl", "LongShortTopkStrategy"]
+__all__ = ["OptimalStopControl"]

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

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

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

@@ -1,361 +0,0 @@
-"""Long-short Top-K strategy for cross-sectional signals.
-
-Each day the strategy ranks the cross-section by prediction score and rebalances
-to an equal-weight two-sided book: the ``topk`` highest-ranked names go long and
-the ``k_short`` lowest-ranked names go short. Net-new shorts are opened by
-selling beyond current holdings, which requires a short-aware exchange such as
-``tac_qlib.contrib.backtest.tradeac_exchange.TradeACExchange`` with
-``allow_short=True`` (borrow limits, margin requirements and borrow fees are
-enforced there, not here).
-
-Sizing deploys ``equity * risk_degree`` as gross notional split evenly across
-all long and short legs, so the book is approximately market neutral.
-``allow_short=False`` disables the short side entirely (long-only ``topk``).
-
-Short eligibility can be restricted further, with static or dynamic gates:
-``short_whitelist`` limits shorts to an explicit symbol set; ``short_vol_top_pct``
-requires a candidate's trailing realized volatility to rank in the top fraction
-of that day's cross-section; ``short_max_mom`` (falling-knife filter) only
-allows shorting names whose own trailing momentum is at/below a threshold;
-``short_regime_sma`` disables shorts entirely while the benchmark trades above
-its moving average (risk-on). Borrow availability itself is enforced by the
-exchange (``borrowable`` whitelist / per-symbol caps via ``TradeACExchange``).
-
-Wired into qrun workflows like any ``BaseStrategy`` (see ``PortAnaRecord``
-config). Mirrors the API usage of qlib's ``TopkDropoutStrategy``: ``Order`` /
-``OrderDir`` from ``qlib.backtest.decision``, ``trade_calendar`` /
-``trade_exchange`` / ``trade_position`` injected by the backtest executor.
-"""
-
-from __future__ import annotations
-
-import copy
-from typing import Dict, List, Optional
-
-import pandas as pd
-
-from qlib.backtest import Order
-from qlib.backtest.decision import OrderDir, TradeDecisionWO
-from qlib.contrib.strategy.signal_strategy import BaseSignalStrategy
-from qlib.log import get_module_logger
-
-__all__ = ["LongShortTopkStrategy"]
-
-
-class LongShortTopkStrategy(BaseSignalStrategy):
-    """Equal-weight long-short Top-K strategy over a cross-sectional signal.
-
-    Parameters
-    ----------
-    topk : number of long legs (highest-ranked names).
-    k_short : number of short legs (lowest-ranked names).
-    hold_thresh : minimum holding days before a leg may be closed/reduced.
-    only_tradable : only select candidates tradable on the trade date.
-    rebalance_tol : skip rebalances smaller than this fraction of a leg's
-        target notional (turnover control).
-    allow_short : enable/disable the short side. With ``False`` the bottom-ranked
-        legs are dropped and the book is long-only ``topk``; pair with
-        ``allow_short=False`` on the exchange for a fully borrow-free run.
-        Legacy alias ``enable_short`` is accepted.
-    short_whitelist : optional list of symbols eligible for shorting; candidates
-        outside the list are skipped (``None`` = all names eligible).
-    short_vol_window : trailing window (trading days) for realized-vol estimation.
-    short_vol_top_pct : if set, a short candidate's trailing realized volatility
-        must rank at or above this percentile of that day's cross-section
-        (e.g. ``0.5`` = only the more volatile half may be shorted). Candidates
-        without measurable vol are never shorted.
-    short_mom_window : trailing window (trading days) for the candidate momentum
-        used by the falling-knife gate.
-    short_max_mom : if set, a candidate's trailing ``short_mom_window``-day return
-        must be <= this value to be shortable (e.g. ``0.0`` = only short names
-        that are actually falling). Candidates without measurable momentum are
-        never shorted.
-    short_regime_symbol : benchmark symbol for the regime gate (default SPY).
-    short_regime_sma : if set, shorts are only allowed on days where the regime
-        symbol's last close (strictly before the execution bar) is BELOW its
-        ``short_regime_sma``-day moving average — i.e. shorts are disabled in
-        risk-on regimes and enabled in drawdowns.
-    """
-
-    def __init__(
-        self,
-        *,
-        signal=None,
-        topk: int = 4,
-        k_short: int = 2,
-        hold_thresh: int = 1,
-        only_tradable: bool = True,
-        rebalance_tol: float = 0.05,
-        allow_short: Optional[bool] = None,
-        enable_short: Optional[bool] = None,
-        short_whitelist: Optional[List[str]] = None,
-        short_vol_window: int = 20,
-        short_vol_top_pct: Optional[float] = None,
-        short_mom_window: int = 20,
-        short_max_mom: Optional[float] = None,
-        short_regime_symbol: str = "SPY",
-        short_regime_sma: Optional[int] = None,
-        risk_degree: float = 0.95,
-        trade_exchange=None,
-        level_infra=None,
-        common_infra=None,
-        **kwargs,
-    ):
-        super().__init__(
-            signal=signal,
-            risk_degree=risk_degree,
-            trade_exchange=trade_exchange,
-            level_infra=level_infra,
-            common_infra=common_infra,
-            **kwargs,
-        )
-        if allow_short is None:
-            allow_short = True if enable_short is None else bool(enable_short)
-        self.allow_short = bool(allow_short)
-        self.topk = topk
-        self.k_short = k_short
-        self.hold_thresh = hold_thresh
-        self.only_tradable = only_tradable
-        self.rebalance_tol = rebalance_tol
-        self.short_whitelist = set(short_whitelist) if short_whitelist is not None else None
-        if not 0 < float(short_vol_window) <= 1000:
-            raise ValueError(f"short_vol_window must be in (0, 1000], got {short_vol_window}")
-        self.short_vol_window = int(short_vol_window)
-        if short_vol_top_pct is not None and not 0.0 < float(short_vol_top_pct) <= 1.0:
-            raise ValueError(f"short_vol_top_pct must be in (0, 1], got {short_vol_top_pct}")
-        self.short_vol_top_pct = None if short_vol_top_pct is None else float(short_vol_top_pct)
-        if not 0 < float(short_mom_window) <= 1000:
-            raise ValueError(f"short_mom_window must be in (0, 1000], got {short_mom_window}")
-        self.short_mom_window = int(short_mom_window)
-        self.short_max_mom = None if short_max_mom is None else float(short_max_mom)
-        self.short_regime_symbol = str(short_regime_symbol)
-        if short_regime_sma is not None and not 1 < int(short_regime_sma) <= 1000:
-            raise ValueError(f"short_regime_sma must be in (1, 1000], got {short_regime_sma}")
-        self.short_regime_sma = None if short_regime_sma is None else int(short_regime_sma)
-        # per-day caches (keyed by trade date)
-        self._vol_cache_key: Optional[str] = None
-        self._vol_cache_val: Dict[str, Dict[str, float]] = {}
-        self._regime_cache: Dict[str, bool] = {}
-
-    # ------------------------------------------------------------------ utils
-    def _is_tradable(self, code, start, end) -> bool:
-        if not self.only_tradable:
-            return True
-        try:
-            return self.trade_exchange.is_stock_tradable(stock_id=code, start_time=start, end_time=end)
-        except TypeError:
-            return True
-
-    def _mark_price(self, code, start, end) -> Optional[float]:
-        try:
-            px = self.trade_exchange.get_deal_price(
-                stock_id=code, start_time=start, end_time=end, direction=OrderDir.BUY
-            )
-        except (KeyError, ValueError):
-            return None
-        if px is None or px != px or px <= 0:
-            return None
-        return float(px)
-
-    def _day_stats(self, codes: List[str], trade_start) -> Dict[str, Dict[str, float]]:
-        """Per-day cross-sectional stats used by the dynamic short gates.
-
-        For each code, returns ``{"vol_rank": r}`` (percentile of trailing
-        realized vol over ``short_vol_window`` bars across that day's
-        cross-section) when the vol gate is on, and ``{"mom": m}`` (trailing
-        ``short_mom_window``-bar return) when the falling-knife gate is on.
-        All series end on the last bar strictly BEFORE the execution bar (no
-        lookahead). Codes without measurable data are simply absent — such
-        candidates are never shorted (fail-closed).
-        """
-        if self.short_vol_top_pct is None and self.short_max_mom is None:
-            return {}
-        key = str(pd.Timestamp(trade_start))
-        if self._vol_cache_key == key:
-            return self._vol_cache_val
-        out: Dict[str, Dict[str, float]] = {}
-        try:
-            from qlib.data import D
-
-            end = pd.Timestamp(trade_start)
-            buf = max(self.short_vol_window, self.short_mom_window) * 3 + 30
-            df = D.features(
-                sorted(codes),
-                ["$close"],
-                start_time=end - pd.Timedelta(days=buf),
-                end_time=end - pd.Timedelta(days=1),
-            )
-            close = df["$close"].unstack(level="instrument") if isinstance(df.index, pd.MultiIndex) else df["$close"]
-            if self.short_vol_top_pct is not None:
-                vol = close.pct_change().rolling(self.short_vol_window).std().iloc[-1]
-                for code, rank in vol.rank(pct=True).dropna().items():
-                    out.setdefault(str(code), {})["vol_rank"] = float(rank)
-            if self.short_max_mom is not None:
-                w = min(self.short_mom_window, len(close) - 1)
-                mom = close.iloc[-1] / close.iloc[-(w + 1)] - 1
-                for code, m in mom.items():
-                    if m == m:
-                        out.setdefault(str(code), {})["mom"] = float(m)
-        except Exception as e:  # noqa: BLE001 - degrade to fail-closed (no shorts)
-            get_module_logger(self.__class__.__name__).warning(
-                f"short gates unavailable ({type(e).__name__}: {e}); no shorts this step"
-            )
-        self._vol_cache_key, self._vol_cache_val = key, out
-        return out
-
-    def _regime_ok(self, trade_start) -> bool:
-        """True when shorting is allowed by the benchmark-regime gate.
-
-        With ``short_regime_sma`` set, shorts are permitted only while the
-        regime symbol's last close strictly before the execution bar sits below
-        its moving average (risk-off). Data failure fails closed (no shorts).
-        """
-        if self.short_regime_sma is None:
-            return True
-        key = str(pd.Timestamp(trade_start))
-        cached = self._regime_cache.get(key)
-        if cached is not None:
-            return cached
-        ok = False
-        try:
-            from qlib.data import D
-
-            end = pd.Timestamp(trade_start)
-            df = D.features(
-                [self.short_regime_symbol],
-                ["$close"],
-                start_time=end - pd.Timedelta(days=int(self.short_regime_sma * 3 + 30)),
-                end_time=end - pd.Timedelta(days=1),
-            )
-            s = df["$close"]
-            if isinstance(s.index, pd.MultiIndex):
-                s = s.droplevel("instrument")
-            sma = s.rolling(self.short_regime_sma).mean().iloc[-1]
-            px = s.iloc[-1]
-            ok = bool(px < sma)
-        except Exception as e:  # noqa: BLE001 - degrade to fail-closed (no shorts)
-            get_module_logger(self.__class__.__name__).warning(
-                f"regime gate unavailable ({type(e).__name__}: {e}); no shorts this step"
-            )
-        self._regime_cache[key] = ok
-        return ok
-
-    # ------------------------------------------------------------- decision
-    def generate_trade_decision(self, execute_result=None):
-        trade_step = self.trade_calendar.get_trade_step()
-        trade_start, trade_end = self.trade_calendar.get_step_time(trade_step)
-        pred_start, pred_end = self.trade_calendar.get_step_time(trade_step, shift=1)
-        pred_score = self.signal.get_signal(start_time=pred_start, end_time=pred_end)
-        if isinstance(pred_score, pd.DataFrame):
-            pred_score = pred_score.iloc[:, 0]
-        if pred_score is None or len(pred_score) == 0:
-            return TradeDecisionWO([], self)
-        pred_score = pred_score.dropna()
-        if pred_score.empty:
-            return TradeDecisionWO([], self)
-
-        time_per_step = self.trade_calendar.get_freq()
-        current_temp = copy.deepcopy(self.trade_position)
-
-        # ---- signed current holdings ---------------------------------------
-        cur_amount: Dict[str, float] = {}
-        for code in current_temp.get_stock_list():
-            amt = float(current_temp.get_stock_amount(code))
-            if abs(amt) > 1e-6:
-                cur_amount[code] = amt
-
-        # ---- targets: top-k long, bottom-k_short short ----------------------
-        ranked = list(pred_score.sort_values(ascending=False).index)
-        longs: List[str] = []
-        for code in ranked:
-            if len(longs) >= self.topk:
-                break
-            if self._is_tradable(code, trade_start, trade_end):
-                longs.append(code)
-        shorts: List[str] = []
-        if self.allow_short and self._regime_ok(trade_start):
-            stats = self._day_stats(list(ranked), trade_start)
-            for code in reversed(ranked):
-                if len(shorts) >= self.k_short:
-                    break
-                if code in longs:
-                    continue
-                if not self._is_tradable(code, trade_start, trade_end):
-                    continue
-                if self.short_whitelist is not None and code not in self.short_whitelist:
-                    continue
-                st = stats.get(code)
-                if self.short_vol_top_pct is not None:
-                    rank = None if st is None else st.get("vol_rank")
-                    if rank is None or rank < self.short_vol_top_pct:
-                        continue
-                if self.short_max_mom is not None:
-                    mom = None if st is None else st.get("mom")
-                    if mom is None or mom > self.short_max_mom:
-                        continue
-                shorts.append(code)
-
-        # ---- marks & equity --------------------------------------------------
-        marks: Dict[str, float] = {}
-        for code in set(cur_amount) | set(longs) | set(shorts):
-            px = self._mark_price(code, trade_start, trade_end)
-            if px is not None:
-                marks[code] = px
-
-        equity = current_temp.get_cash()
-        for code, amt in cur_amount.items():
-            if code in marks:
-                equity += amt * marks[code]
-        if equity <= 0:
-            return TradeDecisionWO([], self)
-
-        n_legs = len([c for c in longs if c in marks]) + len([c for c in shorts if c in marks])
-        if n_legs == 0:
-            return TradeDecisionWO([], self)
-        per_leg = equity * self.risk_degree / n_legs
-
-        target_signed: Dict[str, float] = {}
-        for code in longs:
-            if code in marks:
-                target_signed[code] = per_leg / marks[code]
-        for code in shorts:
-            if code in marks:
-                target_signed[code] = -(per_leg / marks[code])
-
-        # ---- order generation -------------------------------------------------
-        sell_orders: List[Order] = []
-        buy_orders: List[Order] = []
-
-        def submit(code: str, amount: float, direction: int) -> None:
-            factor = self.trade_exchange.get_factor(stock_id=code, start_time=trade_start, end_time=trade_end)
-            amount = self.trade_exchange.round_amount_by_trade_unit(amount, factor)
-            if amount <= 1e-6:
-                return
-            o = Order(stock_id=code, amount=amount, start_time=trade_start, end_time=trade_end, direction=direction)
-            if self.trade_exchange.check_order(o):
-                (buy_orders if direction == Order.BUY else sell_orders).append(o)
-
-        # close holdings that are no longer targeted (frees cash / unwinds shorts)
-        for code, amt in cur_amount.items():
-            if code in target_signed:
-                continue
-            if marks.get(code) is None:
-                continue
-            if current_temp.get_stock_count(code, bar=time_per_step) < self.hold_thresh:
-                continue
-            submit(code, abs(amt), Order.SELL if amt > 0 else Order.BUY)
-
-        # rebalance targeted legs toward their signed target quantity
-        for code, tgt in target_signed.items():
-            cur = cur_amount.get(code, 0.0)
-            delta = tgt - cur
-            if abs(delta * marks[code]) < max(self.rebalance_tol * per_leg, 1.0):
-                continue
-            if delta > 0:
-                submit(code, delta, Order.BUY)
-            else:
-                if cur > 0 and current_temp.get_stock_count(code, bar=time_per_step) < self.hold_thresh:
-                    continue
-                submit(code, -delta, Order.SELL)
-
-        return TradeDecisionWO(sell_orders + buy_orders, self)

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

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

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

@@ -1,223 +0,0 @@
-"""Weekly-rebalance TopkDropout strategy.
-
-Turnover-reduction variant of ``qlib.contrib.strategy.signal_strategy.TopkDropoutStrategy``:
-the topk/n_drop selection and sizing are identical to the reference, but the
-target book is recomputed only on the first trading day of each ISO week; on the
-other days the strategy issues NO orders (holds the book untouched).
-
-The weekly cadence is derived from the qlib trade calendar: a rebalance happens
-when the current trade step's date belongs to a different ISO ``(year, week)``
-than the previous trade step. ``hold_band_pct`` (default 0) optionally skips
-tiny rebalances: when a name's existing position differs from the new target by
-less than this fraction, no order is generated for it.
-"""
-
-from __future__ import annotations
-
-from typing import List
-
-import numpy as np
-import pandas as pd
-
-from qlib.backtest import Order
-from qlib.backtest.decision import OrderDir, TradeDecisionWO
-from qlib.contrib.strategy.signal_strategy import TopkDropoutStrategy
-
-__all__ = ["WeeklyRebalanceDropoutStrategy"]
-
-DEFAULT_HOLD_BAND_PCT = 0.0
-
-
-class WeeklyRebalanceDropoutStrategy(TopkDropoutStrategy):
-    """TopkDropout rebalanced once per ISO week; holds otherwise.
-
-    Parameters
-    ----------
-    topk, n_drop, method_sell, method_buy, hold_thresh, only_tradable,
-    forbid_all_trade_at_limit : same as ``TopkDropoutStrategy``.
-    hold_band_pct : skip order for a name whose deviation from target weight is
-        below this fraction of the target (no-trade buffer band).
-    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,
-                 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:
-        return (ts.year, ts.week)
-
-    def generate_trade_decision(self, execute_result=None):
-        import copy
-
-        trade_step = self.trade_calendar.get_trade_step()
-        trade_start_time, trade_end_time = self.trade_calendar.get_step_time(trade_step)
-
-        if self.rebalance_every_n_days > 0:
-            # daily gating: count trading steps since last rebalance
-            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:
-                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)
-        if isinstance(pred_score, pd.DataFrame):
-            pred_score = pred_score.iloc[:, 0]
-        if pred_score is None:
-            return TradeDecisionWO([], self)
-
-        if self.only_tradable:
-
-            def get_first_n(li, n, reverse=False):
-                cur_n = 0
-                res = []
-                for si in reversed(li) if reverse else li:
-                    if self.trade_exchange.is_stock_tradable(
-                        stock_id=si, start_time=trade_start_time, end_time=trade_end_time
-                    ):
-                        res.append(si)
-                        cur_n += 1
-                        if cur_n >= n:
-                            break
-                return res[::-1] if reverse else res
-
-            def get_last_n(li, n):
-                return get_first_n(li, n, reverse=True)
-
-            def filter_stock(li):
-                return [
-                    si
-                    for si in li
-                    if self.trade_exchange.is_stock_tradable(
-                        stock_id=si, start_time=trade_start_time, end_time=trade_end_time
-                    )
-                ]
-
-        else:
-
-            def get_first_n(li, n):
-                return list(li)[:n]
-
-            def get_last_n(li, n):
-                return list(li)[-n:]
-
-            def filter_stock(li):
-                return li
-
-        current_temp: "object" = copy.deepcopy(self.trade_position)
-        sell_order_list: List[Order] = []
-        buy_order_list: List[Order] = []
-        cash = current_temp.get_cash()
-        current_stock_list = current_temp.get_stock_list()
-        last = pred_score.reindex(current_stock_list).sort_values(ascending=False).index
-
-        if self.method_buy == "top":
-            today = get_first_n(
-                pred_score[~pred_score.index.isin(last)].sort_values(ascending=False).index,
-                self.n_drop + self.topk - len(last),
-            )
-        elif self.method_buy == "random":
-            topk_candi = get_first_n(pred_score.sort_values(ascending=False).index, self.topk)
-            candi = list(filter(lambda x: x not in last, topk_candi))
-            n = self.n_drop + self.topk - len(last)
-            try:
-                today = np.random.choice(candi, n, replace=False)
-            except ValueError:
-                today = candi
-        else:
-            raise NotImplementedError(f"This type of input is not supported")
-
-        comb = pred_score.reindex(last.union(pd.Index(today))).sort_values(ascending=False).index
-
-        if self.method_sell == "bottom":
-            sell = last[last.isin(get_last_n(comb, self.n_drop))]
-        elif self.method_sell == "random":
-            candi = filter_stock(last)
-            try:
-                sell = pd.Index(np.random.choice(candi, self.n_drop, replace=False) if len(last) else [])
-            except ValueError:
-                sell = candi
-        else:
-            raise NotImplementedError(f"This type of input is not supported")
-
-        buy = today[: len(sell) + self.topk - len(last)]
-        for code in current_stock_list:
-            if not self.trade_exchange.is_stock_tradable(
-                stock_id=code,
-                start_time=trade_start_time,
-                end_time=trade_end_time,
-                direction=None if self.forbid_all_trade_at_limit else OrderDir.SELL,
-            ):
-                continue
-            if code in sell:
-                time_per_step = self.trade_calendar.get_freq()
-                if current_temp.get_stock_count(code, bar=time_per_step) < self.hold_thresh:
-                    continue
-                sell_amount = current_temp.get_stock_amount(code=code)
-                sell_order = Order(
-                    stock_id=code,
-                    amount=sell_amount,
-                    start_time=trade_start_time,
-                    end_time=trade_end_time,
-                    direction=Order.SELL,
-                )
-                if self.trade_exchange.check_order(sell_order):
-                    sell_order_list.append(sell_order)
-                    trade_val, trade_cost, trade_price = self.trade_exchange.deal_order(
-                        sell_order, position=current_temp
-                    )
-                    cash += trade_val - trade_cost
-
-        if len(buy) == 0:
-            return TradeDecisionWO(sell_order_list, self)
-
-        value = cash * self.risk_degree / len(buy)
-        for code in buy:
-            if not self.trade_exchange.is_stock_tradable(
-                stock_id=code,
-                start_time=trade_start_time,
-                end_time=trade_end_time,
-                direction=None if self.forbid_all_trade_at_limit else OrderDir.BUY,
-            ):
-                continue
-            buy_price = self.trade_exchange.get_deal_price(
-                stock_id=code, start_time=trade_start_time, end_time=trade_end_time, direction=OrderDir.BUY
-            )
-            buy_amount = value / buy_price
-            factor = self.trade_exchange.get_factor(
-                stock_id=code, start_time=trade_start_time, end_time=trade_end_time
-            )
-            buy_amount = self.trade_exchange.round_amount_by_trade_unit(buy_amount, factor)
-            buy_order = Order(
-                stock_id=code,
-                amount=buy_amount,
-                start_time=trade_start_time,
-                end_time=trade_end_time,
-                direction=Order.BUY,
-            )
-            buy_order_list.append(buy_order)
-
-        return TradeDecisionWO(sell_order_list + buy_order_list, self)

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

@@ -61,11 +61,6 @@ UNKNOWN_FIELD_NAMES = ("factor", "change", "trade_unit", "suspend_flag")
 #: columns in the parquet files that are not features
 NON_FEATURE_COLUMNS = ("t", "date", "market", "timeframe", "symbol")
 
-#: Feature-family partitions merged by ``LakeConfig.load_features`` and scanned
-#: by the handler's field discovery. ``macro`` holds broadcast market-state
-#: columns (see skills/tac-qlib-custom/examples/persist_macro_broadcast.py).
-FEATURE_FAMILIES = ("ta", "sp", "macro")
-
 
 def timeframe_for_freq(freq: str) -> str:
     """Map a qlib frequency (e.g. ``day``, ``1min``) to a lake timeframe (e.g. ``1d``)."""
@@ -118,12 +113,12 @@ class LakeConfig:
         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|sp|macro`
-        partitions by timestamp. Returns an empty frame when no
+        """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 FEATURE_FAMILIES:
+        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))

workflows/ablate_baseline_all_sp_fields.yaml

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

workflows/ablate_generic_only_sp_fields.yaml

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

workflows/exp12_isolation_ensemble.yaml

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

workflows/exp22/workflow.yaml

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

workflows/exp23/workflow.yaml

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

workflows/exp24/workflow.yaml

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

workflows/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/exp30/workflow.yaml

@@ -0,0 +1,99 @@
+# M2 isolation run: base compact set + risk-adjusted drift sp_sharpe_22.
+# Exact copy of exp26 (reference: expId=25 run=21afc6afdb674a399b59dd76c97628ce)
+# except feature_fields. 5-seed ensemble.
+{%- set LAKE = TAC_LAKE_DIR %}
+{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
+{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead,sp_sharpe_22" %}
+
+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-exp30-m2-sharpe" }
+
+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/exp31/workflow.yaml

@@ -0,0 +1,99 @@
+# M3 isolation run: base compact set + GARCH(1,1) vol-regime trio.
+# Exact copy of exp26 (reference: expId=25 run=21afc6afdb674a399b59dd76c97628ce)
+# except feature_fields. 5-seed ensemble.
+{%- set LAKE = TAC_LAKE_DIR %}
+{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
+{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead,sp_garch_cond_var,sp_garch_persistence,sp_garch_std_resid" %}
+
+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-exp31-m3-garch" }
+
+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