Gahow Wang
722cade974
Share point-in-time signals and a cash-funded order ledger across backtests and trading. Correct eligibility, missing-price fills, quality factors, regime inputs, warmup windows, and cash-injection accounting. Add reproducible registered-strategy comparisons and paired forward candidates with a 20% resize band. Validation: 125 Python tests, 23 web tests, TypeScript/Vite build, 87 strategy causality checks, and real-data target/order/equity parity for 10 strategies.
308 lines
14 KiB
Python
308 lines
14 KiB
Python
import argparse
|
|
|
|
import matplotlib.pyplot as plt
|
|
import numpy as np
|
|
import pandas as pd
|
|
|
|
import data_manager
|
|
import factor_attribution
|
|
import metrics
|
|
import universe_history as uh
|
|
from strategies.adaptive_momentum import AdaptiveMomentumStrategy
|
|
from strategies.base import BarStrategy
|
|
from signals import session_targets
|
|
from execution import simulate_book
|
|
from strategies.buy_and_hold import BuyAndHoldStrategy
|
|
from strategies.dual_momentum import DualMomentumStrategy
|
|
from strategies.inverse_vol import InverseVolatilityStrategy
|
|
from strategies.mean_reversion import MeanReversionStrategy
|
|
from strategies.momentum import MomentumStrategy
|
|
from strategies.momentum_quality import MomentumQualityStrategy
|
|
from strategies.multi_factor import MultiFactorStrategy
|
|
from strategies.recovery_momentum import RecoveryMomentumStrategy
|
|
from strategies.trend_following import TrendFollowingStrategy
|
|
from universe import UNIVERSES
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Backtest engine
|
|
# ---------------------------------------------------------------------------
|
|
|
|
def strategy_positions(strategy, data: pd.DataFrame, open_data: pd.DataFrame | None = None,
|
|
bars: dict[str, pd.DataFrame] | None = None,
|
|
eligible: pd.DataFrame | None = None) -> pd.DataFrame:
|
|
"""Weights held over (close t-1, close t], after a feasible prior close fill."""
|
|
if eligible is None and bars is not None:
|
|
eligible = bars.get("eligible")
|
|
return session_targets(strategy, data, open_data, bars, eligible).shift(1).fillna(0.0)
|
|
|
|
|
|
def simulate_live_book(held: pd.DataFrame, data: pd.DataFrame, initial_capital: float,
|
|
transaction_cost: float = 0.001, fixed_fee: float = 0.0,
|
|
fee_base: float = 0.0, fee_per_share: float = 0.0,
|
|
min_trade_value: float = 0.0, resize_band: float = 0.0,
|
|
*, fresh_prices: pd.DataFrame | None = None,
|
|
integer_shares: bool = False, lot_size: int = 1):
|
|
targets = held.reindex_like(data).shift(-1).fillna(0.0)
|
|
# No decision after the last row is represented by `held`; preserve the book.
|
|
result = simulate_book(targets.iloc[:-1], data.iloc[:-1], initial_capital,
|
|
fresh_prices=fresh_prices.iloc[:-1] if fresh_prices is not None else None,
|
|
transaction_cost=transaction_cost, fixed_fee=fixed_fee,
|
|
fee_base=fee_base, fee_per_share=fee_per_share,
|
|
min_trade_value=min_trade_value, resize_band=resize_band,
|
|
integer_shares=integer_shares, lot_size=lot_size)
|
|
traded = pd.DataFrame(0.0, index=data.index, columns=data.columns)
|
|
for trade in result["trade_log"]:
|
|
i = data.index.get_loc(pd.Timestamp(trade["date"]))
|
|
value = result["pretrade_equity"].iloc[i]
|
|
traded.iloc[i + 1, data.columns.get_loc(trade["ticker"])] += (
|
|
trade["value"] / value * (1 if trade["action"] == "BUY" else -1)) if value else 0.0
|
|
marks = data.ffill().iloc[-1].dropna().to_dict()
|
|
from execution import portfolio_value
|
|
last = portfolio_value(result["holdings"], marks,
|
|
float(result["cash"].iloc[-1]) if len(result["cash"]) else initial_capital)
|
|
equity = pd.concat([result["equity"], pd.Series([last], index=data.index[-1:])])
|
|
return equity, traded
|
|
|
|
|
|
def backtest(
|
|
strategy,
|
|
data: pd.DataFrame,
|
|
initial_capital: float = 100_000,
|
|
transaction_cost: float = 0.001,
|
|
fixed_fee: float = 0.0,
|
|
fee_base: float = 0.0,
|
|
fee_per_share: float = 0.0,
|
|
open_data: pd.DataFrame | None = None,
|
|
min_trade_value: float = 0.0,
|
|
bars: dict[str, pd.DataFrame] | None = None,
|
|
resize_band: float = 0.0,
|
|
) -> pd.Series:
|
|
"""
|
|
Cash-funded backtest with next-session execution and drifting holdings.
|
|
|
|
Parameters
|
|
----------
|
|
strategy : Strategy
|
|
Any class implementing generate_signals(data) → DataFrame of weights.
|
|
data : pd.DataFrame
|
|
Adjusted close prices, one column per asset.
|
|
initial_capital : float
|
|
Starting portfolio value.
|
|
transaction_cost : float
|
|
One-way cost per unit of turnover (e.g. 0.001 = 10 bps).
|
|
fixed_fee : float
|
|
Floor of the per-trade fee (e.g. 2.0 = $2 minimum per buy/sell).
|
|
With fee_per_share=0 (default), this is also the actual per-trade fee.
|
|
fee_base : float
|
|
Fixed component of a per-share tiered fee schedule. The actual
|
|
per-trade fee is ``max(fixed_fee, fee_base + fee_per_share * shares)``.
|
|
fee_per_share : float
|
|
Per-share variable component of the tiered fee (e.g. 0.009 = $0.009/share).
|
|
With fee_base=1.88 + fee_per_share=0.009 + fixed_fee=2.0 you get an
|
|
IBKR-style schedule: max(2, 1.88 + 0.009 * shares).
|
|
open_data : pd.DataFrame, optional
|
|
Open prices. When provided, the backtest keeps the book the way the
|
|
live trader does: its signal timing (``strategy_positions``), drifting
|
|
holdings, whole orders and ``resize_band`` (``simulate_live_book``).
|
|
min_trade_value : float
|
|
Per-ticker rebalances smaller than ``max(min_trade_value, 0.1% of
|
|
equity)`` are not charged the per-trade fee, mirroring the live
|
|
trader, which never places such orders. 0 (default) charges every
|
|
weight change.
|
|
bars : dict, optional
|
|
``{field: DataFrame}`` panels for a BarStrategy (close/open/high/low/volume).
|
|
|
|
Returns
|
|
-------
|
|
pd.Series
|
|
Daily equity curve.
|
|
"""
|
|
positions = strategy_positions(strategy, data, open_data=open_data, bars=bars)
|
|
equity, _ = simulate_live_book(positions, data, initial_capital, transaction_cost,
|
|
fixed_fee, fee_base, fee_per_share, min_trade_value, resize_band)
|
|
return equity
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Visualization
|
|
# ---------------------------------------------------------------------------
|
|
|
|
def plot_results(results: pd.DataFrame) -> None:
|
|
"""Two-panel chart: equity curves (top) + drawdowns (bottom)."""
|
|
# Compute drawdowns
|
|
drawdowns = results.div(results.cummax()) - 1
|
|
|
|
fig, (ax1, ax2) = plt.subplots(2, 1, figsize=(14, 9), sharex=True,
|
|
gridspec_kw={"height_ratios": [3, 1]})
|
|
|
|
for col in results.columns:
|
|
ax1.plot(results.index, results[col], label=col, linewidth=1.5)
|
|
ax1.set_title("Strategy Comparison — Equity Curves", fontsize=14)
|
|
ax1.set_ylabel("Portfolio Value ($)")
|
|
ax1.legend(loc="upper left")
|
|
ax1.grid(True, alpha=0.3)
|
|
|
|
for col in drawdowns.columns:
|
|
ax2.plot(drawdowns.index, drawdowns[col] * 100, label=col, linewidth=1.0)
|
|
ax2.set_title("Drawdowns")
|
|
ax2.set_ylabel("Drawdown (%)")
|
|
ax2.set_xlabel("Date")
|
|
ax2.grid(True, alpha=0.3)
|
|
|
|
plt.tight_layout()
|
|
plt.show()
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Main
|
|
# ---------------------------------------------------------------------------
|
|
|
|
def main() -> None:
|
|
parser = argparse.ArgumentParser(description="Run strategy backtest")
|
|
parser.add_argument(
|
|
"--market", choices=UNIVERSES.keys(), default="us",
|
|
help="Market universe to backtest (default: us)",
|
|
)
|
|
parser.add_argument(
|
|
"--capital", type=float, default=None,
|
|
help="Initial capital (default: 10000)",
|
|
)
|
|
parser.add_argument(
|
|
"--top-n", type=int, default=None,
|
|
help="Number of stocks for selective strategies (default: ~10%% of universe)",
|
|
)
|
|
parser.add_argument(
|
|
"--years", type=int, default=None,
|
|
help="Limit backtest to last N years of data",
|
|
)
|
|
parser.add_argument(
|
|
"--no-plot", action="store_true",
|
|
help="Skip plotting charts",
|
|
)
|
|
parser.add_argument(
|
|
"--fixed-fee", type=float, default=0.0,
|
|
help="Fixed dollar cost per trade, e.g. 2.0 means $2 per buy or sell",
|
|
)
|
|
parser.add_argument(
|
|
"--execution", choices=["close", "open-close"], default="close",
|
|
help="Execution mode: 'close' (default, signal & execute on close) or "
|
|
"'open-close' (signal on morning open, execute at close)",
|
|
)
|
|
parser.add_argument(
|
|
"--attribution", action="store_true",
|
|
help="Run factor attribution after performance metrics",
|
|
)
|
|
parser.add_argument(
|
|
"--attribution-model", choices=["capm", "ff5", "ff5plus", "all"], default="all",
|
|
help="Factor model selection for attribution output",
|
|
)
|
|
parser.add_argument(
|
|
"--attribution-export", default=None,
|
|
help="Directory to export factor attribution CSVs",
|
|
)
|
|
parser.add_argument("--offline", action="store_true", help="Use local prices and membership without refreshing")
|
|
args = parser.parse_args()
|
|
initial_capital = args.capital if args.capital is not None else 10_000
|
|
use_open = args.execution == "open-close"
|
|
|
|
universe = UNIVERSES[args.market]
|
|
tickers = [] if args.offline else universe["fetch"]()
|
|
benchmark = universe["benchmark"]
|
|
benchmark_label = universe["benchmark_label"]
|
|
|
|
membership = uh.pit_membership(args.market, pd.DatetimeIndex([pd.Timestamp.today()]), refresh=not args.offline)
|
|
all_tickers = sorted(set(tickers) | set(membership.columns) | {benchmark})
|
|
fields = ["close", "open", "volume"]
|
|
panels = (data_manager.load_fields(args.market, fields) if args.offline else
|
|
data_manager.update(args.market, all_tickers, fields=fields))
|
|
data = data_manager.load_raw(args.market).reindex_like(panels["close"])
|
|
sessions = data.index[data[benchmark].notna()]
|
|
data = data.loc[sessions]
|
|
open_data = panels["open"].reindex_like(data) if use_open else None
|
|
member = uh.pit_membership(args.market, data.index).reindex(columns=data.columns, fill_value=False)
|
|
member[benchmark] = True
|
|
tickers = sorted(t for t in member.columns if t != benchmark and member[t].any())
|
|
if len(data) <= 315:
|
|
raise ValueError("Need 315 pre-window trading sessions")
|
|
requested = data.index[-1] - pd.DateOffset(years=args.years) if args.years else data.index[0]
|
|
start = max(requested, data.index[315])
|
|
days = data.index[data.index >= start]
|
|
print(f"--- Scoring {days[0].date()} to {days[-1].date()}; prior history is retained ---")
|
|
|
|
top_n = args.top_n if args.top_n else max(5, len(tickers) // 10)
|
|
print(f"--- Selective strategies will pick top {top_n} stocks ---")
|
|
if args.fixed_fee > 0:
|
|
print(f"--- Fixed fee: ${args.fixed_fee:.2f} per trade ---")
|
|
if use_open:
|
|
print(f"--- Execution: open-close (signal on open, execute at close) ---")
|
|
|
|
# Build strategy tuples: (strategy, close_data, open_data_or_None)
|
|
open_tickers = open_data[tickers] if open_data is not None else None
|
|
open_all = open_data if open_data is not None else None
|
|
|
|
strategies = {
|
|
# --- Original strategies ---
|
|
"Buy & Hold": (BuyAndHoldStrategy(asset=benchmark), data[[benchmark]], open_data[[benchmark]] if open_data is not None else None),
|
|
"Momentum": (MomentumStrategy(lookback=252, skip=21, top_n=top_n), data[tickers], open_tickers),
|
|
"Inverse Volatility": (InverseVolatilityStrategy(vol_window=20), data[tickers], open_tickers),
|
|
"Multi-Factor": (MultiFactorStrategy(tickers=tickers, benchmark=benchmark, top_n=top_n), data, open_all),
|
|
# --- New strategies ---
|
|
"Mean Reversion": (MeanReversionStrategy(top_n=top_n), data[tickers], open_tickers),
|
|
"Trend Following": (TrendFollowingStrategy(ma_window=150, momentum_period=126, top_n=top_n), data[tickers], open_tickers),
|
|
"Dual Momentum": (DualMomentumStrategy(top_n=top_n), data[tickers], open_tickers),
|
|
"Momentum+Quality": (MomentumQualityStrategy(momentum_period=252, skip=21, top_n=top_n), data[tickers], open_tickers),
|
|
"Mom+InvVol": (AdaptiveMomentumStrategy(top_n=top_n), data[tickers], open_tickers),
|
|
"Recovery+Mom Top20": (RecoveryMomentumStrategy(top_n=min(20, top_n)), data[tickers], open_tickers),
|
|
"Recovery+Mom Top10": (RecoveryMomentumStrategy(top_n=10), data[tickers], open_tickers),
|
|
}
|
|
|
|
results: dict[str, pd.Series] = {}
|
|
for name, (strategy, strat_data, strat_open) in strategies.items():
|
|
print(f"\nRunning: {name}")
|
|
targets = session_targets(strategy, strat_data, strat_open,
|
|
eligible=member.reindex_like(strat_data))
|
|
run = simulate_book(targets.loc[days], strat_data.loc[days], initial_capital,
|
|
previous_prices=strat_data.ffill().shift(1).loc[days],
|
|
volume=panels["volume"].reindex(index=days, columns=strat_data.columns),
|
|
market=args.market, integer_shares=True,
|
|
lot_size=100 if args.market == "cn" else 1,
|
|
fixed_fee=args.fixed_fee, min_trade_value=50, resize_band=.10)
|
|
anchor = pd.Series([initial_capital], index=[days[0] - pd.Timedelta(days=1)])
|
|
results[name] = pd.concat([anchor, run["equity"]])
|
|
|
|
bench = data[benchmark].reindex(days).ffill().dropna()
|
|
results[benchmark_label] = pd.concat([anchor, bench / bench.iloc[0] * initial_capital])
|
|
|
|
results_df = pd.DataFrame(results)
|
|
|
|
# --- Performance metrics ---
|
|
for name, equity in results_df.items():
|
|
eq = equity.dropna()
|
|
if len(eq) < 2:
|
|
print(f"\n {name}: insufficient data, skipping")
|
|
continue
|
|
metrics.summary(eq, name=name)
|
|
|
|
if args.attribution:
|
|
summary_df, loadings_df = factor_attribution.attribute_strategies(
|
|
results_df=results_df,
|
|
benchmark_label=benchmark_label,
|
|
benchmark=benchmark,
|
|
price_data=data,
|
|
market=args.market,
|
|
model_selection=args.attribution_model,
|
|
)
|
|
factor_attribution.print_attribution_summary(summary_df)
|
|
if args.attribution_export:
|
|
factor_attribution.export_attribution(summary_df, loadings_df, args.attribution_export)
|
|
print(f"Attribution CSVs written to {args.attribution_export}")
|
|
|
|
# --- Visualization ---
|
|
if not args.no_plot:
|
|
plot_results(results_df.dropna())
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|