542 lines
20 KiB
Python
542 lines
20 KiB
Python
"""Offline event study for stateful post-stop re-entry policies.
|
|
|
|
Initial entries keep the validated weekly production cadence. After an initial
|
|
stop, the affected ticker is evaluated on every subsequent daily close. This
|
|
isolates the exact churn problem without changing the rest of the portfolio.
|
|
All arms retain the hard stop, production position sizing, 3x ATR trail, and
|
|
round-trip transaction costs.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import argparse
|
|
import asyncio
|
|
import bisect
|
|
import json
|
|
import multiprocessing
|
|
import os
|
|
import pickle
|
|
import sys
|
|
from collections import Counter
|
|
from concurrent.futures import ProcessPoolExecutor, as_completed
|
|
from datetime import date, datetime
|
|
from pathlib import Path
|
|
from types import SimpleNamespace
|
|
from typing import Any
|
|
|
|
from sqlalchemy import select
|
|
from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker, create_async_engine
|
|
|
|
ROOT = Path(__file__).resolve().parents[1]
|
|
if str(ROOT) not in sys.path:
|
|
sys.path.insert(0, str(ROOT))
|
|
|
|
RECLAIM_ATR_BUFFER = 0.25
|
|
|
|
|
|
def _sqlite_url(path: Path) -> str:
|
|
return f"sqlite+aiosqlite:///{path.resolve().as_posix()}"
|
|
|
|
|
|
def _parse_args() -> argparse.Namespace:
|
|
parser = argparse.ArgumentParser(description=__doc__)
|
|
parser.add_argument("snapshot")
|
|
parser.add_argument("--start-date", default="2024-07-01")
|
|
parser.add_argument("--workers", type=int, default=6)
|
|
parser.add_argument("--out", default=None)
|
|
parser.add_argument(
|
|
"--candidate-cache",
|
|
default=None,
|
|
help="Optional pickle cache for the expensive weekly candidate replay.",
|
|
)
|
|
parser.add_argument("--quiet", action="store_true")
|
|
parser.add_argument(
|
|
"--cooldowns",
|
|
type=int,
|
|
nargs="+",
|
|
default=None,
|
|
help=(
|
|
"Run an immediate baseline plus the given cooldown lengths instead "
|
|
"of the gate-reset policy study (for example: 3 5 7 10)."
|
|
),
|
|
)
|
|
return parser.parse_args()
|
|
|
|
|
|
def _default_output_path() -> Path:
|
|
stamp = datetime.now().strftime("%Y%m%d-%H%M%S")
|
|
return Path("reports") / f"post-stop-reentry-{stamp}.json"
|
|
|
|
|
|
class DailySetupEngine:
|
|
"""Point-in-time daily setup and universe-rank cache."""
|
|
|
|
def __init__(
|
|
self,
|
|
prices: dict[str, tuple],
|
|
recommendation_config: dict,
|
|
activation: dict,
|
|
benchmark_closes: dict[date, float],
|
|
) -> None:
|
|
from app.services import backtest_service as bt
|
|
|
|
self.bt = bt
|
|
self.prices = prices
|
|
self.recommendation_config = recommendation_config
|
|
self.activation = activation
|
|
self.benchmark_closes = benchmark_closes
|
|
self.threshold = float(activation.get("min_momentum_percentile", 80.0))
|
|
self.dates = {
|
|
symbol: [date.fromordinal(value) for value in columns[0]]
|
|
for symbol, columns in prices.items()
|
|
}
|
|
self.index_of = {
|
|
symbol: {value: index for index, value in enumerate(columns[0])}
|
|
for symbol, columns in prices.items()
|
|
}
|
|
self.rank_cache: dict[int, dict[str, tuple[float, float]]] = {}
|
|
self.candidate_cache: dict[tuple[str, int], dict | None] = {}
|
|
self.atr_cache: dict[tuple[str, int], float | None] = {}
|
|
|
|
@staticmethod
|
|
def _percentiles(values: dict[str, float]) -> dict[str, float]:
|
|
ordered = sorted(values, key=lambda symbol: values[symbol])
|
|
denominator = len(ordered) - 1
|
|
return {
|
|
symbol: (rank / denominator * 100.0) if denominator > 0 else 100.0
|
|
for rank, symbol in enumerate(ordered)
|
|
}
|
|
|
|
def _ranks(self, asof_ord: int) -> dict[str, tuple[float, float]]:
|
|
cached = self.rank_cache.get(asof_ord)
|
|
if cached is not None:
|
|
return cached
|
|
|
|
momentum_values: dict[str, float] = {}
|
|
volatility_values: dict[str, float] = {}
|
|
for symbol, columns in self.prices.items():
|
|
idx = bisect.bisect_right(columns[0], asof_ord) - 1
|
|
if idx < 0:
|
|
continue
|
|
closes = columns[4]
|
|
if idx >= 252:
|
|
momentum = self.bt._residual_momentum_12_1(
|
|
self.dates[symbol], closes, idx, self.benchmark_closes
|
|
)
|
|
if momentum is None and closes[idx - 252] > 0:
|
|
momentum = closes[idx - 21] / closes[idx - 252] - 1.0
|
|
if momentum is not None:
|
|
momentum_values[symbol] = float(momentum)
|
|
volatility = self.bt._realized_vol_6m(closes, idx)
|
|
if volatility is not None:
|
|
volatility_values[symbol] = float(volatility)
|
|
|
|
momentum_pct = self._percentiles(momentum_values)
|
|
volatility_pct = self._percentiles(volatility_values)
|
|
ranks = {
|
|
symbol: (momentum_pct[symbol], volatility_pct.get(symbol, 0.0))
|
|
for symbol in momentum_pct
|
|
}
|
|
self.rank_cache[asof_ord] = ranks
|
|
return ranks
|
|
|
|
def atr(self, symbol: str, asof_ord: int) -> float | None:
|
|
key = (symbol, asof_ord)
|
|
if key in self.atr_cache:
|
|
return self.atr_cache[key]
|
|
columns = self.prices[symbol]
|
|
idx = self.index_of[symbol].get(asof_ord)
|
|
if idx is None:
|
|
idx = bisect.bisect_right(columns[0], asof_ord) - 1
|
|
if idx < 0:
|
|
self.atr_cache[key] = None
|
|
return None
|
|
try:
|
|
value = self.bt.compute_atr(
|
|
columns[2][: idx + 1],
|
|
columns[3][: idx + 1],
|
|
columns[4][: idx + 1],
|
|
)["atr"]
|
|
result = float(value) if value and value > 0 else None
|
|
except Exception:
|
|
result = None
|
|
self.atr_cache[key] = result
|
|
return result
|
|
|
|
def candidate(self, symbol: str, asof_ord: int) -> dict | None:
|
|
key = (symbol, asof_ord)
|
|
if key in self.candidate_cache:
|
|
cached = self.candidate_cache[key]
|
|
return dict(cached) if cached is not None else None
|
|
|
|
columns = self.prices[symbol]
|
|
idx = self.index_of[symbol].get(asof_ord)
|
|
if idx is None or idx < self.bt.MIN_LOOKBACK - 1:
|
|
self.candidate_cache[key] = None
|
|
return None
|
|
records = [
|
|
SimpleNamespace(
|
|
date=date.fromordinal(o),
|
|
open=op,
|
|
high=high,
|
|
low=low,
|
|
close=close,
|
|
volume=volume,
|
|
)
|
|
for o, op, high, low, close, volume in zip(
|
|
columns[0][: idx + 1],
|
|
columns[1][: idx + 1],
|
|
columns[2][: idx + 1],
|
|
columns[3][: idx + 1],
|
|
columns[4][: idx + 1],
|
|
columns[5][: idx + 1],
|
|
)
|
|
]
|
|
setups = self.bt._window_setups(
|
|
records, self.recommendation_config, self.activation
|
|
)
|
|
setup = next((row for row in setups if row["direction"] == "long"), None)
|
|
rank = self._ranks(asof_ord).get(symbol)
|
|
gate_passed = bool(
|
|
setup is not None
|
|
and rank is not None
|
|
and self.bt._momentum_qualifies(
|
|
{
|
|
"meets_core": setup["meets_core"],
|
|
"direction": "long",
|
|
self.bt.PRODUCTION_PERCENTILE_KEY: rank[0],
|
|
},
|
|
self.threshold,
|
|
)
|
|
)
|
|
if not gate_passed or setup is None or rank is None:
|
|
self.candidate_cache[key] = None
|
|
return None
|
|
|
|
strategy_rank = (
|
|
rank[0] * self.bt.STRATEGY_RANK_MOMENTUM_WEIGHT
|
|
+ rank[1] * (1.0 - self.bt.STRATEGY_RANK_MOMENTUM_WEIGHT)
|
|
)
|
|
candidate = {
|
|
"symbol": symbol,
|
|
"date": date.fromordinal(asof_ord).isoformat(),
|
|
"direction": "long",
|
|
"entry": float(setup["entry"]),
|
|
"stop": float(setup["stop"]),
|
|
"target": float(setup["target"]),
|
|
"qualified": True,
|
|
self.bt.PRODUCTION_PERCENTILE_KEY: rank[0],
|
|
self.bt.RESIDUAL_HIGH_VOL_BLEND_80_20_KEY: strategy_rank,
|
|
}
|
|
self.candidate_cache[key] = candidate
|
|
return dict(candidate)
|
|
|
|
|
|
class ReentryPolicy:
|
|
def __init__(self, name: str, engine: DailySetupEngine) -> None:
|
|
self.name = name
|
|
self.engine = engine
|
|
self.checks = 0
|
|
self.gate_passes = 0
|
|
self.emitted = Counter()
|
|
|
|
def __call__(
|
|
self,
|
|
symbol: str,
|
|
asof_ord: int,
|
|
state: dict,
|
|
bar: Any,
|
|
) -> dict | None:
|
|
self.checks += 1
|
|
if "reentry_trigger" not in state:
|
|
stop_atr = self.engine.atr(symbol, state["stop_ord"])
|
|
state["reentry_trigger"] = (
|
|
state["stop_day_high"] + RECLAIM_ATR_BUFFER * stop_atr
|
|
if stop_atr is not None
|
|
else state["stop_day_high"]
|
|
)
|
|
|
|
candidate = self.engine.candidate(symbol, asof_ord)
|
|
if candidate is None:
|
|
state["gate_went_unqualified"] = True
|
|
return None
|
|
self.gate_passes += 1
|
|
|
|
reason: str | None = None
|
|
sessions = int(state["sessions_since_stop"])
|
|
if self.name == "immediate":
|
|
reason = "gate_still_or_again_qualified"
|
|
elif self.name.startswith("cooldown_"):
|
|
cooldown_sessions = int(self.name.removeprefix("cooldown_"))
|
|
if sessions >= cooldown_sessions:
|
|
reason = f"{cooldown_sessions}_session_cooldown_complete"
|
|
elif self.name == "gate_reset":
|
|
if state["gate_went_unqualified"]:
|
|
reason = "gate_failed_then_requalified"
|
|
elif self.name == "gate_reset_or_reclaim":
|
|
if state["gate_went_unqualified"]:
|
|
reason = "gate_failed_then_requalified"
|
|
elif (
|
|
bar.close > state["reentry_trigger"]
|
|
and float(candidate["stop"]) > state["previous_stop"]
|
|
):
|
|
reason = "price_reclaim_with_improved_stop"
|
|
else:
|
|
raise ValueError(f"Unknown re-entry policy: {self.name}")
|
|
|
|
if reason is None:
|
|
return None
|
|
emitted = dict(candidate)
|
|
emitted["_reentry_reason"] = reason
|
|
self.emitted[reason] += 1
|
|
return emitted
|
|
|
|
def summary(self) -> dict:
|
|
return {
|
|
"daily_checks": self.checks,
|
|
"qualified_checks": self.gate_passes,
|
|
"emitted_by_reason": dict(self.emitted),
|
|
}
|
|
|
|
|
|
def _trade_summary(trades: list[dict]) -> dict:
|
|
reentries = [trade for trade in trades if trade.get("is_reentry")]
|
|
waits = [
|
|
int(trade["reentry_wait_sessions"])
|
|
for trade in reentries
|
|
if trade.get("reentry_wait_sessions") is not None
|
|
]
|
|
return {
|
|
"transaction_cost": round(
|
|
sum(float(trade["transaction_cost"]) for trade in trades), 2
|
|
),
|
|
"reentry_trades": len(reentries),
|
|
"same_day_reentries": sum(wait == 0 for wait in waits),
|
|
"next_day_reentries": sum(wait == 1 for wait in waits),
|
|
"reentries_within_5_sessions": sum(wait <= 5 for wait in waits),
|
|
"avg_reentry_wait_sessions": round(sum(waits) / len(waits), 1)
|
|
if waits
|
|
else None,
|
|
"reentry_win_rate": round(
|
|
sum(float(trade["pnl"]) > 0 for trade in reentries)
|
|
/ len(reentries)
|
|
* 100.0,
|
|
1,
|
|
)
|
|
if reentries
|
|
else None,
|
|
"reentry_total_pnl": round(
|
|
sum(float(trade["pnl"]) for trade in reentries), 2
|
|
),
|
|
}
|
|
|
|
|
|
async def _main() -> None:
|
|
args = _parse_args()
|
|
snapshot = Path(args.snapshot)
|
|
if not snapshot.exists():
|
|
raise SystemExit(f"Snapshot not found: {snapshot}")
|
|
try:
|
|
start_date = date.fromisoformat(args.start_date)
|
|
except ValueError as exc:
|
|
raise SystemExit("--start-date must use YYYY-MM-DD") from exc
|
|
|
|
os.environ["BACKTEST_SNAPSHOT_OFFLINE"] = "1"
|
|
os.environ["BACKTEST_ALLOW_SPAWN"] = "1"
|
|
|
|
from app.models.ticker import Ticker
|
|
from app.services import backtest_service as bt
|
|
from app.services.admin_service import get_activation_config
|
|
from app.services.paper_trade_service import get_exit_policy
|
|
from app.services.recommendation_service import get_recommendation_config
|
|
|
|
engine = create_async_engine(_sqlite_url(snapshot), pool_pre_ping=True)
|
|
Session = async_sessionmaker(engine, class_=AsyncSession, expire_on_commit=False)
|
|
try:
|
|
async with Session() as db:
|
|
recommendation_config = await get_recommendation_config(db)
|
|
activation = await get_activation_config(db)
|
|
exit_config = await get_exit_policy(db)
|
|
benchmark_closes = await bt._load_benchmark_closes_for_backtest(
|
|
db, days=None, refresh=False
|
|
)
|
|
ticker_result = await db.execute(select(Ticker).order_by(Ticker.symbol))
|
|
symbols = [ticker.symbol for ticker in ticker_result.scalars().all()]
|
|
prices: dict[str, tuple] = {}
|
|
for index, symbol in enumerate(symbols, 1):
|
|
columns = await bt._fetch_columns(db, symbol)
|
|
if columns is not None:
|
|
prices[symbol] = columns
|
|
if not args.quiet and index % 50 == 0:
|
|
print(f"loaded prices: {index}/{len(symbols)}", flush=True)
|
|
finally:
|
|
await engine.dispose()
|
|
|
|
cache_path = Path(args.candidate_cache) if args.candidate_cache else None
|
|
snapshot_stat = snapshot.stat()
|
|
cache_key = {
|
|
"snapshot": str(snapshot.resolve()),
|
|
"snapshot_size": snapshot_stat.st_size,
|
|
"snapshot_mtime_ns": snapshot_stat.st_mtime_ns,
|
|
"start_date": start_date.isoformat(),
|
|
}
|
|
candidates: list[dict]
|
|
if cache_path is not None and cache_path.exists():
|
|
with cache_path.open("rb") as handle:
|
|
cached_replay = pickle.load(handle) # noqa: S301 - trusted local cache
|
|
if cached_replay.get("key") != cache_key:
|
|
raise SystemExit(f"Candidate cache does not match this run: {cache_path}")
|
|
candidates = list(cached_replay["candidates"])
|
|
if not args.quiet:
|
|
print(f"loaded candidate cache: {cache_path}", flush=True)
|
|
else:
|
|
candidates = []
|
|
workers = max(1, min(int(args.workers), multiprocessing.cpu_count() - 1))
|
|
context = multiprocessing.get_context("spawn")
|
|
with ProcessPoolExecutor(max_workers=workers, mp_context=context) as pool:
|
|
futures = {
|
|
pool.submit(
|
|
bt._replay_candidates_for_period,
|
|
symbol,
|
|
columns,
|
|
recommendation_config,
|
|
activation,
|
|
benchmark_closes,
|
|
start_date,
|
|
): symbol
|
|
for symbol, columns in prices.items()
|
|
}
|
|
for index, future in enumerate(as_completed(futures), 1):
|
|
candidates.extend(future.result())
|
|
if not args.quiet and index % 25 == 0:
|
|
print(f"replayed tickers: {index}/{len(futures)}", flush=True)
|
|
if cache_path is not None:
|
|
cache_path.parent.mkdir(parents=True, exist_ok=True)
|
|
with cache_path.open("wb") as handle:
|
|
pickle.dump(
|
|
{"key": cache_key, "candidates": candidates},
|
|
handle,
|
|
protocol=pickle.HIGHEST_PROTOCOL,
|
|
)
|
|
if not args.quiet:
|
|
print(f"wrote candidate cache: {cache_path}", flush=True)
|
|
|
|
bt._assign_momentum_percentiles(candidates)
|
|
bt._assign_residual_momentum_percentiles(candidates)
|
|
bt._assign_low_volatility_percentiles(candidates)
|
|
bt._assign_activation_momentum_percentiles(candidates)
|
|
bt._assign_residual_high_vol_blend(candidates)
|
|
threshold = float(activation.get("min_momentum_percentile", 80.0))
|
|
for candidate in candidates:
|
|
candidate["qualified"] = bt._momentum_qualifies(candidate, threshold)
|
|
|
|
strategy = next(
|
|
row for row in bt.PORTFOLIO_MONITOR_STRATEGIES if row.get("is_production")
|
|
)
|
|
entry_config = bt._entry_variant_config(str(strategy["entry_variant"]))
|
|
if entry_config is None:
|
|
raise RuntimeError("Production entry configuration missing")
|
|
exit_policy = bt.LIVE_EXIT_MODE_TO_SIM.get(
|
|
str(exit_config.get("mode", "atr_trailing")), "atr_trail3"
|
|
)
|
|
hold_days = int(exit_config.get("hold_days", max(bt.TIME_EXIT_DAYS)))
|
|
trail_multiplier = float(
|
|
exit_config.get("atr_multiplier", bt.ATR_TRAIL_MULTIPLIER)
|
|
)
|
|
sim_kwargs = {
|
|
"ranking_key": str(
|
|
entry_config.get("ranking_key") or entry_config["percentile_key"]
|
|
),
|
|
"max_positions": int(entry_config["max_positions"]),
|
|
"risk_per_trade": float(entry_config["risk_per_trade"]),
|
|
"atr_trail_multiplier": trail_multiplier,
|
|
"start_date": start_date,
|
|
"include_trades": True,
|
|
}
|
|
|
|
daily_engine = DailySetupEngine(
|
|
prices, recommendation_config, activation, benchmark_closes
|
|
)
|
|
if args.cooldowns is None:
|
|
policy_names = (
|
|
"immediate",
|
|
"cooldown_5",
|
|
"gate_reset",
|
|
"gate_reset_or_reclaim",
|
|
)
|
|
else:
|
|
cooldowns = sorted(set(args.cooldowns))
|
|
if any(value < 1 for value in cooldowns):
|
|
raise SystemExit("--cooldowns values must be positive integers")
|
|
policy_names = ("immediate", *(f"cooldown_{value}" for value in cooldowns))
|
|
|
|
arms: list[dict] = []
|
|
for policy_name in policy_names:
|
|
policy = ReentryPolicy(policy_name, daily_engine)
|
|
sim = bt._simulate_portfolio(
|
|
candidates,
|
|
prices,
|
|
benchmark_closes,
|
|
exit_policy,
|
|
hold_days,
|
|
post_stop_reentry_fn=policy,
|
|
**sim_kwargs,
|
|
)
|
|
if sim is None:
|
|
raise RuntimeError(f"Policy {policy_name} produced no trades")
|
|
trades = list(sim.pop("trade_details"))
|
|
arms.append({
|
|
"arm": policy_name,
|
|
**sim,
|
|
"turnover": _trade_summary(trades),
|
|
"policy": policy.summary(),
|
|
"trade_details": trades,
|
|
})
|
|
|
|
output = Path(args.out) if args.out else _default_output_path()
|
|
report = {
|
|
"generated_at": datetime.now().astimezone().isoformat(),
|
|
"snapshot": str(snapshot.resolve()),
|
|
"period_start": start_date.isoformat(),
|
|
"tickers": len(prices),
|
|
"entry_candidates": len(candidates),
|
|
"qualified_candidates": sum(bool(row["qualified"]) for row in candidates),
|
|
"params": {
|
|
"initial_entry_cadence_days": bt.STEP_DAYS,
|
|
"post_stop_evaluation_cadence_days": 1,
|
|
"setup_stop_atr_multiplier": bt.ATR_MULTIPLIER,
|
|
"exit_policy": exit_policy,
|
|
"exit_atr_multiplier": trail_multiplier,
|
|
"hold_days": hold_days,
|
|
"cost_per_side_pct": bt.COST_PER_SIDE * 100.0,
|
|
"momentum_percentile_floor": threshold,
|
|
"reclaim_atr_buffer": RECLAIM_ATR_BUFFER,
|
|
"cooldown_sessions": cooldowns if args.cooldowns is not None else None,
|
|
},
|
|
"arms": arms,
|
|
"note": (
|
|
"Initial opportunities retain the validated weekly replay cadence. "
|
|
"Only tickers stopped at their initial stop switch to daily evaluation, "
|
|
"which isolates next-day/same-episode re-entry churn. A cooldown of N "
|
|
"sessions permits the first re-entry at wait_sessions=N. Gate reset "
|
|
"requires at least one unqualified daily close before requalification. "
|
|
"The reclaim arm alternatively accepts a close above stop-day high + "
|
|
"0.25 ATR only when the new setup stop is above the prior stop."
|
|
),
|
|
}
|
|
output.parent.mkdir(parents=True, exist_ok=True)
|
|
output.write_text(json.dumps(report, indent=2) + "\n", encoding="utf-8")
|
|
|
|
print(f"Report written: {output}")
|
|
for arm in arms:
|
|
turnover = arm["turnover"]
|
|
print(
|
|
f"{arm['arm']}: Sharpe {arm['sharpe']}, CAGR {arm['cagr_pct']}%, "
|
|
f"DD {arm['max_drawdown_pct']}%, trades {arm['trades']}, "
|
|
f"reentries {turnover['reentry_trades']}, fees ${turnover['transaction_cost']}"
|
|
)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
asyncio.run(_main())
|