From 891bd0743d81f4a49cd91fc4d5dc1d97873e750e Mon Sep 17 00:00:00 2001 From: zhaoli Date: Mon, 24 Aug 2026 12:01:27 +0000 Subject: [PATCH] start experiment 60 (exp/60-scheduled-algo-retrain-on-2026-08-21-tac) --- code/MANIFEST.txt | 22 +- .../tac_qlib/contrib/backtest/__init__.py | 1 + .../contrib/backtest/tradeac_exchange.py | 432 ++++++++++++++++++ .../tac-qlib/tac_qlib/contrib/data/handler.py | 3 +- .../tac_qlib/contrib/model/rank_gbdt.py | 54 ++- .../tac_qlib/contrib/strategy/__init__.py | 3 +- .../contrib/strategy/kelly_dropout.py | 201 ++++++++ .../tac_qlib/contrib/strategy/long_short.py | 361 +++++++++++++++ .../tac_qlib/contrib/strategy/regime_gate.py | 231 ++++++++++ .../contrib/strategy/weekly_rebalance.py | 202 ++++++++ .../data/__pycache__/__init__.cpython-312.pyc | Bin 522 -> 522 bytes .../data/__pycache__/config.cpython-312.pyc | Bin 11464 -> 11507 bytes .../__pycache__/providers.cpython-312.pyc | Bin 13340 -> 13340 bytes code/tac-qlib/tac_qlib/data/config.py | 11 +- 14 files changed, 1500 insertions(+), 21 deletions(-) create mode 100644 code/tac-qlib/tac_qlib/contrib/backtest/__init__.py create mode 100644 code/tac-qlib/tac_qlib/contrib/backtest/tradeac_exchange.py create mode 100644 code/tac-qlib/tac_qlib/contrib/strategy/kelly_dropout.py create mode 100644 code/tac-qlib/tac_qlib/contrib/strategy/long_short.py create mode 100644 code/tac-qlib/tac_qlib/contrib/strategy/regime_gate.py create mode 100644 code/tac-qlib/tac_qlib/contrib/strategy/weekly_rebalance.py diff --git a/code/MANIFEST.txt b/code/MANIFEST.txt index f94dac7..dbfd1c6 100644 --- a/code/MANIFEST.txt +++ b/code/MANIFEST.txt @@ -1,19 +1,25 @@ # TradeAC custom-qlib-code snapshot (auto-generated) -# parent repo HEAD : 337f99222df3629f58eca0404caae2b1ccb6a994 +# parent repo HEAD : 7460d5fe014ac209fd901b13a048a6c2912725eb # tac-qlib/tac_qlib/contrib # tac-qlib/tac_qlib/data # per-file hashes (git hash-object): 1b6298c4a5652f2e863cbdc385a1014a570fcd59 tac-qlib/tac_qlib/contrib/__init__.py + 2224424d0ff193be4f55d1b791f8fce89439c5d2 tac-qlib/tac_qlib/contrib/backtest/__init__.py + 0bf40dee440ddbded357d7bbb4efc67c62c4b084 tac-qlib/tac_qlib/contrib/backtest/tradeac_exchange.py c76a9f17f680e74eea766eff27f7624359749ed6 tac-qlib/tac_qlib/contrib/data/__init__.py - 0dd25ef161c6e0f15eafc84886e7e1381deb38c3 tac-qlib/tac_qlib/contrib/data/handler.py + fc3d01d530d4e84b3386614b6ac94324e811920e tac-qlib/tac_qlib/contrib/data/handler.py b151d139a0dcde87d74b21e7c4b729176ba5c39b tac-qlib/tac_qlib/contrib/model/__init__.py d3f051f3a8650c42fedc7b367b966f7c74fb5789 tac-qlib/tac_qlib/contrib/model/rank_ensemble.py - ccfe7d554989aa7f3e5a2128ae663e51b2207149 tac-qlib/tac_qlib/contrib/model/rank_gbdt.py - 4afcf9058231111c412925f4c4b84e81d656db87 tac-qlib/tac_qlib/contrib/strategy/__init__.py + d03e6611338918d4aac5eea4adf26f85a3763652 tac-qlib/tac_qlib/contrib/model/rank_gbdt.py + 184f80da8edf944bad3c8fb4d4d3d189bf4f082b tac-qlib/tac_qlib/contrib/strategy/__init__.py + 896ef74ae47bcd1ed388e1e5d9c8d70c28097fe9 tac-qlib/tac_qlib/contrib/strategy/kelly_dropout.py + 9090fc6dfbd339f2f4df4b0c9b87f400ecb5c9d5 tac-qlib/tac_qlib/contrib/strategy/long_short.py 79aaad9e39fcc740a773f4f63c512ce1086cfde0 tac-qlib/tac_qlib/contrib/strategy/optimal_stop.py + 5b9acfb4340111b204249add7760bd53c6ae03f1 tac-qlib/tac_qlib/contrib/strategy/regime_gate.py + fe60bacdfedd48617863be31f24b7c7daebfac5a tac-qlib/tac_qlib/contrib/strategy/weekly_rebalance.py 92e6e90eb0cd0a25142034560f27adb6b705b1a8 tac-qlib/tac_qlib/data/__init__.py - 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 + fa1090eb6f17b1b7835038e35fac86334294d165 tac-qlib/tac_qlib/data/__pycache__/__init__.cpython-312.pyc + 48629a1f51bd4058036ce78d79ed49454982c051 tac-qlib/tac_qlib/data/__pycache__/config.cpython-312.pyc + ad7c9b726c9c52773fa82031fcd681337be97fa8 tac-qlib/tac_qlib/data/__pycache__/providers.cpython-312.pyc + 1953fb2a6371525db7f7b0e1c9dfbf3492d82110 tac-qlib/tac_qlib/data/config.py 8d0644f6f0d1efb94798ed444cc73e63b643459b tac-qlib/tac_qlib/data/providers.py diff --git a/code/tac-qlib/tac_qlib/contrib/backtest/__init__.py b/code/tac-qlib/tac_qlib/contrib/backtest/__init__.py new file mode 100644 index 0000000..2224424 --- /dev/null +++ b/code/tac-qlib/tac_qlib/contrib/backtest/__init__.py @@ -0,0 +1 @@ +from .tradeac_exchange import TradeACExchange diff --git a/code/tac-qlib/tac_qlib/contrib/backtest/tradeac_exchange.py b/code/tac-qlib/tac_qlib/contrib/backtest/tradeac_exchange.py new file mode 100644 index 0000000..0bf40de --- /dev/null +++ b/code/tac-qlib/tac_qlib/contrib/backtest/tradeac_exchange.py @@ -0,0 +1,432 @@ +# 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 + diff --git a/code/tac-qlib/tac_qlib/contrib/data/handler.py b/code/tac-qlib/tac_qlib/contrib/data/handler.py index 0dd25ef..fc3d01d 100644 --- a/code/tac-qlib/tac_qlib/contrib/data/handler.py +++ b/code/tac-qlib/tac_qlib/contrib/data/handler.py @@ -22,6 +22,7 @@ from qlib.utils import get_callable_kwargs from ...data.config import ( LakeConfig, timeframe_for_freq, + FEATURE_FAMILIES, NON_FEATURE_COLUMNS, ) @@ -92,7 +93,7 @@ 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 ("ta", "sp"): + for fam in FEATURE_FAMILIES: fam_dir = feat_dir / f"family={fam}" if fam_dir.is_dir(): common |= _family_common(fam_dir) diff --git a/code/tac-qlib/tac_qlib/contrib/model/rank_gbdt.py b/code/tac-qlib/tac_qlib/contrib/model/rank_gbdt.py index ccfe7d5..d03e661 100644 --- a/code/tac-qlib/tac_qlib/contrib/model/rank_gbdt.py +++ b/code/tac-qlib/tac_qlib/contrib/model/rank_gbdt.py @@ -53,23 +53,61 @@ 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))]) - 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 + 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 def rankic_feval(preds, dataset): diff --git a/code/tac-qlib/tac_qlib/contrib/strategy/__init__.py b/code/tac-qlib/tac_qlib/contrib/strategy/__init__.py index 4afcf90..184f80d 100644 --- a/code/tac-qlib/tac_qlib/contrib/strategy/__init__.py +++ b/code/tac-qlib/tac_qlib/contrib/strategy/__init__.py @@ -1,3 +1,4 @@ from .optimal_stop import OptimalStopControl # noqa: F401 +from .long_short import LongShortTopkStrategy # noqa: F401 -__all__ = ["OptimalStopControl"] +__all__ = ["OptimalStopControl", "LongShortTopkStrategy"] diff --git a/code/tac-qlib/tac_qlib/contrib/strategy/kelly_dropout.py b/code/tac-qlib/tac_qlib/contrib/strategy/kelly_dropout.py new file mode 100644 index 0000000..896ef74 --- /dev/null +++ b/code/tac-qlib/tac_qlib/contrib/strategy/kelly_dropout.py @@ -0,0 +1,201 @@ +"""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) \ No newline at end of file diff --git a/code/tac-qlib/tac_qlib/contrib/strategy/long_short.py b/code/tac-qlib/tac_qlib/contrib/strategy/long_short.py new file mode 100644 index 0000000..9090fc6 --- /dev/null +++ b/code/tac-qlib/tac_qlib/contrib/strategy/long_short.py @@ -0,0 +1,361 @@ +"""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) diff --git a/code/tac-qlib/tac_qlib/contrib/strategy/regime_gate.py b/code/tac-qlib/tac_qlib/contrib/strategy/regime_gate.py new file mode 100644 index 0000000..5b9acfb --- /dev/null +++ b/code/tac-qlib/tac_qlib/contrib/strategy/regime_gate.py @@ -0,0 +1,231 @@ +"""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=`` 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) \ No newline at end of file diff --git a/code/tac-qlib/tac_qlib/contrib/strategy/weekly_rebalance.py b/code/tac-qlib/tac_qlib/contrib/strategy/weekly_rebalance.py new file mode 100644 index 0000000..fe60bac --- /dev/null +++ b/code/tac-qlib/tac_qlib/contrib/strategy/weekly_rebalance.py @@ -0,0 +1,202 @@ +"""Weekly-rebalance TopkDropout strategy. + +Turnover-reduction variant of ``qlib.contrib.strategy.signal_strategy.TopkDropoutStrategy``: +the topk/n_drop selection and sizing are identical to the reference, but the +target book is recomputed only on the first trading day of each ISO week; on the +other days the strategy issues NO orders (holds the book untouched). + +The weekly cadence is derived from the qlib trade calendar: a rebalance happens +when the current trade step's date belongs to a different ISO ``(year, week)`` +than the previous trade step. ``hold_band_pct`` (default 0) optionally skips +tiny rebalances: when a name's existing position differs from the new target by +less than this fraction, no order is generated for it. +""" + +from __future__ import annotations + +from typing import List + +import numpy as np +import pandas as pd + +from qlib.backtest import Order +from qlib.backtest.decision import OrderDir, TradeDecisionWO +from qlib.contrib.strategy.signal_strategy import TopkDropoutStrategy + +__all__ = ["WeeklyRebalanceDropoutStrategy"] + +DEFAULT_HOLD_BAND_PCT = 0.0 + + +class WeeklyRebalanceDropoutStrategy(TopkDropoutStrategy): + """TopkDropout rebalanced once per ISO week; holds otherwise. + + Parameters + ---------- + topk, n_drop, method_sell, method_buy, hold_thresh, only_tradable, + forbid_all_trade_at_limit : same as ``TopkDropoutStrategy``. + hold_band_pct : skip order for a name whose deviation from target weight is + below this fraction of the target (no-trade buffer band). + """ + + def __init__(self, *, topk, n_drop, hold_band_pct: float = DEFAULT_HOLD_BAND_PCT, **kwargs): + super().__init__(topk=topk, n_drop=n_drop, **kwargs) + self.hold_band_pct = hold_band_pct + + @staticmethod + def _iso_week(ts) -> tuple: + return (ts.year, ts.week) + + def generate_trade_decision(self, execute_result=None): + import copy + + trade_step = self.trade_calendar.get_trade_step() + trade_start_time, trade_end_time = self.trade_calendar.get_step_time(trade_step) + + cur_week = self._iso_week(trade_start_time) + prev_week = getattr(self, "_last_week", None) + self._last_week = cur_week + + if prev_week is not None and prev_week == cur_week: + # not the first trading day of this ISO week -> hold + return TradeDecisionWO([], self) + + pred_start_time, pred_end_time = self.trade_calendar.get_step_time(trade_step, shift=1) + pred_score = self.signal.get_signal(start_time=pred_start_time, end_time=pred_end_time) + if isinstance(pred_score, pd.DataFrame): + pred_score = pred_score.iloc[:, 0] + if pred_score is None: + return TradeDecisionWO([], self) + + if self.only_tradable: + + def get_first_n(li, n, reverse=False): + cur_n = 0 + res = [] + for si in reversed(li) if reverse else li: + if self.trade_exchange.is_stock_tradable( + stock_id=si, start_time=trade_start_time, end_time=trade_end_time + ): + res.append(si) + cur_n += 1 + if cur_n >= n: + break + return res[::-1] if reverse else res + + def get_last_n(li, n): + return get_first_n(li, n, reverse=True) + + def filter_stock(li): + return [ + si + for si in li + if self.trade_exchange.is_stock_tradable( + stock_id=si, start_time=trade_start_time, end_time=trade_end_time + ) + ] + + else: + + def get_first_n(li, n): + return list(li)[:n] + + def get_last_n(li, n): + return list(li)[-n:] + + def filter_stock(li): + return li + + current_temp: "object" = copy.deepcopy(self.trade_position) + sell_order_list: List[Order] = [] + buy_order_list: List[Order] = [] + cash = current_temp.get_cash() + current_stock_list = current_temp.get_stock_list() + last = pred_score.reindex(current_stock_list).sort_values(ascending=False).index + + if self.method_buy == "top": + today = get_first_n( + pred_score[~pred_score.index.isin(last)].sort_values(ascending=False).index, + self.n_drop + self.topk - len(last), + ) + elif self.method_buy == "random": + topk_candi = get_first_n(pred_score.sort_values(ascending=False).index, self.topk) + candi = list(filter(lambda x: x not in last, topk_candi)) + n = self.n_drop + self.topk - len(last) + try: + today = np.random.choice(candi, n, replace=False) + except ValueError: + today = candi + else: + raise NotImplementedError(f"This type of input is not supported") + + comb = pred_score.reindex(last.union(pd.Index(today))).sort_values(ascending=False).index + + if self.method_sell == "bottom": + sell = last[last.isin(get_last_n(comb, self.n_drop))] + elif self.method_sell == "random": + candi = filter_stock(last) + try: + sell = pd.Index(np.random.choice(candi, self.n_drop, replace=False) if len(last) else []) + except ValueError: + sell = candi + else: + raise NotImplementedError(f"This type of input is not supported") + + buy = today[: len(sell) + self.topk - len(last)] + for code in current_stock_list: + if not self.trade_exchange.is_stock_tradable( + stock_id=code, + start_time=trade_start_time, + end_time=trade_end_time, + direction=None if self.forbid_all_trade_at_limit else OrderDir.SELL, + ): + continue + if code in sell: + time_per_step = self.trade_calendar.get_freq() + if current_temp.get_stock_count(code, bar=time_per_step) < self.hold_thresh: + continue + sell_amount = current_temp.get_stock_amount(code=code) + sell_order = Order( + stock_id=code, + amount=sell_amount, + start_time=trade_start_time, + end_time=trade_end_time, + direction=Order.SELL, + ) + if self.trade_exchange.check_order(sell_order): + sell_order_list.append(sell_order) + trade_val, trade_cost, trade_price = self.trade_exchange.deal_order( + sell_order, position=current_temp + ) + cash += trade_val - trade_cost + + if len(buy) == 0: + return TradeDecisionWO(sell_order_list, self) + + value = cash * self.risk_degree / len(buy) + for code in buy: + if not self.trade_exchange.is_stock_tradable( + stock_id=code, + start_time=trade_start_time, + end_time=trade_end_time, + direction=None if self.forbid_all_trade_at_limit else OrderDir.BUY, + ): + continue + buy_price = self.trade_exchange.get_deal_price( + stock_id=code, start_time=trade_start_time, end_time=trade_end_time, direction=OrderDir.BUY + ) + buy_amount = value / buy_price + factor = self.trade_exchange.get_factor( + stock_id=code, start_time=trade_start_time, end_time=trade_end_time + ) + buy_amount = self.trade_exchange.round_amount_by_trade_unit(buy_amount, factor) + buy_order = Order( + stock_id=code, + amount=buy_amount, + start_time=trade_start_time, + end_time=trade_end_time, + direction=Order.BUY, + ) + buy_order_list.append(buy_order) + + return TradeDecisionWO(sell_order_list + buy_order_list, self) \ No newline at end of file diff --git a/code/tac-qlib/tac_qlib/data/__pycache__/__init__.cpython-312.pyc b/code/tac-qlib/tac_qlib/data/__pycache__/__init__.cpython-312.pyc index 3cbc0686e6f863d306d93c589a607a5bdb7201f2..fa1090eb6f17b1b7835038e35fac86334294d165 100644 GIT binary patch delta 20 acmeBT>0;qN&CAQh00bgyyEbzFX9NH*yagTr delta 20 acmeBT>0;qN&CAQh00hU~TQ+k4X9NH;9|dIq diff --git a/code/tac-qlib/tac_qlib/data/__pycache__/config.cpython-312.pyc b/code/tac-qlib/tac_qlib/data/__pycache__/config.cpython-312.pyc index 46bcdbcc173ff3a6281fed33d10c1bcac96876b0..48629a1f51bd4058036ce78d79ed49454982c051 100644 GIT binary patch delta 1815 zcmah~Uu;ul6u)14`)BRC{<&>w$0plgf9_TW43q&fnb0kmAsb`LhO?C2TWsmp`rTXD zYQaAcm5Bjz3=blS1QQ*95>531pOk1~Vl)t6$W_COiLXQwV|enM%V=3*;`i|D`OZ1N z?|kRnbH4sCet*2~M~}xP;0j)!&jg#!)kTw^cbSYsR&hM%iiE_*~xWRr*01kdGkz6bTgu-!e$2FsV+DP|`H9|4aiB8`x^5ka#e zG&MExIP`j2mk{bc|u9^Vqgd(Z_mx7 z(ucYibs5-Ew+>G`Qg=RZ0G)Xs!9IiqD<6j^ykQoHC%r9f8uodgGQ%Eic!_)_30@{h zAXEZEi?5UAVVAELo!|ByUv&_zvX!UFvvN3BiBnCi!yjWBjQKYs>8wA>K7uR$En!_m zFLUh>CdUNfn5`sa9B?VnxPp~z7lezJqFWFYOUZgcP^=fNv^!=m*)uh8J5cY`*y)~< zm~q2MK(cxS0s33(;myDbW*#9er8!Ctlh#=AbW0vLvL3FCkB$^a1zm!ENm?Tw?!bI( zB~h_O(PLD2Bpq|2Br5iL0q;D4_o*p4Ga%A)Ya z3W>SlPiZCeJRylC*R@(`4mMjo#h)M^>Fg>Hmb=ATfzJYlE-myLL#6bV9okKh0qdX1sp{3 zHu!s)PZ~DEo6V>(l&N#0kyztdlak9pUEaw)gv-lkabz1B95$xIs^->BXXwzS zfsC5??39|<)43V`8ktK3Lj*L|i&5dN=2n)1&ziS{%#fSNL?g^8I0yKrxf|=>-qPv# z1Qpu13>w;_HxFWBA5eHP@2MAIG<|B2Oq<09+`kF0de%=pA_bI{W1Z9K; z>^73=o#lHU!9m#2Ikv|%kPZv7olMniNs`&~iDsyR2r1})#{3U?82W44R<2_>pPtSsg{<1gZ=!()QQKC2w`(PH-g5~- O`Ig{=tFfp^gnt1+2Bw4n delta 1872 zcmah~Z%kWN6o0qx^$(P`l>S)@>nvq#JYaJ$BW$?2F}7vun1I`aiKXyf9njL|zE^=- zaAugfOsDMV5;K?S2NMxuqD}nsVR0r#r+&f256jc2i{DKY6Els8_uNuC5)