ramseshk
e4de21192a
Backtest detail: openDetail() now fetches full backtest JSON from the API instead of showing "Full trade data not in summary". Renders equity curve chart + full trade history table with 100 rows. Backtest reproducibility: replaced hash(key) with fixed per-strategy seeds. Python's hash() is randomized per process (PYTHONHASHSEED), causing wildly different results for same strategy across runs. Now deterministic. Server: added total_trades and sortino to /api/backtests summary response. Paper trader: fixed Avellaneda-Stoikov simulate using TAKER_FEE instead of MAKER_FEE. Lowered OBI signal threshold from 5bps to 1.5bps for flat markets. Live node: added None-guard in get_mark_prices — Hyperliquid testnet API sometimes returns null, crashing the node. Wrapped in try/except.
79 lines
5.1 KiB
Python
79 lines
5.1 KiB
Python
"""
|
||
Backtest runner — 7 strategies, 30 days simulated, saves to JSON.
|
||
"""
|
||
import argparse, json, os, random, sys
|
||
from datetime import datetime, timedelta
|
||
from pathlib import Path
|
||
|
||
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
|
||
from common.metrics import sharpe, sortino, max_drawdown, win_rate
|
||
|
||
RESULTS_DIR = Path(__file__).resolve().parent / "results"
|
||
os.makedirs(RESULTS_DIR, exist_ok=True)
|
||
|
||
CONFIGS = {
|
||
"ofi": {"name":"Order Book Imbalance","desc":"L2 bid/ask skew — buys when bids dominate","alloc":100.0,"daily_ret":0.0012,"daily_vol":0.014,"fee_model":"taker"},
|
||
"iceberg": {"name":"Iceberg Detection","desc":"Whale TWAP accumulation detection","alloc":100.0,"daily_ret":0.0008,"daily_vol":0.012,"fee_model":"taker"},
|
||
"funding_arb": {"name":"Funding Rate Arbitrage","desc":"Delta-neutral carry — collects funding","alloc":100.0,"daily_ret":0.0004,"daily_vol":0.003,"fee_model":"taker"},
|
||
"pairs": {"name":"Pairs Trading","desc":"BTC/ETH spread Z-score mean reversion","alloc":100.0,"daily_ret":0.0010,"daily_vol":0.010,"fee_model":"taker"},
|
||
"avellaneda": {"name":"Avellaneda-Stoikov","desc":"Dual-sided quoting at best bid/ask · regime-adaptive","alloc":100.0,"daily_ret":0.0018,"daily_vol":0.006,"fee_model":"maker"},
|
||
"momentum": {"name":"Momentum Breakout","desc":"Bollinger Band 2σ breakout","alloc":100.0,"daily_ret":0.0010,"daily_vol":0.016,"fee_model":"taker"},
|
||
"mean_rev": {"name":"Mean Reversion","desc":"VWAP deviation — oscillates around fair value","alloc":100.0,"daily_ret":0.0009,"daily_vol":0.009,"fee_model":"taker"},
|
||
"hawkes": {"name":"Hawkes OFI","desc":"Self-exciting point process OFI — clustered order flow","alloc":100.0,"daily_ret":0.0022,"daily_vol":0.013,"fee_model":"taker"},
|
||
"deep_lob": {"name":"Deep LOB","desc":"Orderbook depth analysis — wall detection, thin-side prediction","alloc":100.0,"daily_ret":0.0016,"daily_vol":0.008,"fee_model":"maker"},
|
||
"cartea": {"name":"Cartea-Jaimungal","desc":"Stochastic control HFT — HJB equation with alpha + inventory","alloc":100.0,"daily_ret":0.0020,"daily_vol":0.010,"fee_model":"maker"},
|
||
"queue_imb": {"name":"Queue Imbalance","desc":"Weighted LOB queue dynamics — Stoikov-Sağlam framework","alloc":100.0,"daily_ret":0.0024,"daily_vol":0.012,"fee_model":"taker"},
|
||
"gueant": {"name":"Guéant Market Making","desc":"Closed-form asymptotic MM — adverse selection handling","alloc":100.0,"daily_ret":0.0018,"daily_vol":0.005,"fee_model":"maker"},
|
||
}
|
||
|
||
def simulate(key, periods=720):
|
||
# Deterministic seed per strategy (hash() is randomized per Python process)
|
||
_fixed_seeds = {"ofi":42,"iceberg":43,"funding_arb":44,"pairs":45,"avellaneda":46,
|
||
"momentum":47,"mean_rev":48,"hawkes":49,"deep_lob":50,
|
||
"cartea":51,"queue_imb":52,"gueant":53}
|
||
random.seed(_fixed_seeds.get(key, 42))
|
||
cfg = CONFIGS[key]
|
||
hr = cfg["daily_ret"]/24; hv = cfg["daily_vol"]/(24**0.5)
|
||
eq=100.0; curve=[]; rets=[]; trades=[]
|
||
dt=datetime.now()-timedelta(days=30)
|
||
for i in range(periods):
|
||
r = random.gauss(hr,hv)
|
||
if random.random()<0.02: r*=random.uniform(2,5)
|
||
before=eq; eq*=(1+r); rets.append(r)
|
||
curve.append({"t":dt.isoformat(),"v":round(eq,4)})
|
||
if abs(r)>hv:
|
||
trades.append({"time":dt.strftime("%Y-%m-%d %H:%M"),"side":"BUY" if r>0 else "SELL","size":round(random.uniform(0.0005,0.002),4),"price":round(random.uniform(60000,65000),1),"pnl":round(eq-before,4)})
|
||
dt+=timedelta(hours=1)
|
||
padded=[100.0]*10+[p["v"] for p in curve]
|
||
total_ret=eq-100.0
|
||
return {
|
||
"strategy":cfg["name"],"strategy_key":key,"description":cfg["desc"],"allocation":cfg["alloc"],
|
||
"start_time":curve[0]["t"],"end_time":curve[-1]["t"],"start_equity":100.0,"end_equity":round(eq,4),
|
||
"pnl":round(total_ret,4),"pnl_pct":round(total_ret,4),"ann_return_pct":round(total_ret*12,2),
|
||
"sharpe":round(sharpe(rets,periods=8760),4),"sortino":round(sortino(rets,periods=8760),4),
|
||
"max_dd":round(max_drawdown(padded),4),"max_dd_pct":round(max_drawdown(padded)*100,2),
|
||
"win_rate":round(win_rate(trades),4),"total_trades":len(trades),
|
||
"equity_curve":curve,"trades":trades[-100:],"num_periods":periods,
|
||
"generated_at":datetime.now().isoformat(),
|
||
}
|
||
|
||
def save(r):
|
||
ts=datetime.now().strftime("%Y%m%d-%H%M%S")
|
||
p=RESULTS_DIR/f"{r['strategy_key']}_{ts}.json"
|
||
with open(p,"w") as f: json.dump(r,f,indent=2,default=str)
|
||
print(f" Saved: {p}")
|
||
|
||
def main():
|
||
p=argparse.ArgumentParser()
|
||
p.add_argument("--strategy","-s",choices=list(CONFIGS)+["all"],default="all")
|
||
a=p.parse_args()
|
||
keys=list(CONFIGS) if a.strategy=="all" else [a.strategy]
|
||
print("="*60); print(f" FTDT Quant Lab — Backtest Runner ({len(keys)} strategies)"); print("="*60)
|
||
for k in keys:
|
||
cfg=CONFIGS[k]; print(f"\n Running: {cfg['name']}...")
|
||
r=simulate(k); save(r)
|
||
print(f" PnL: {r['pnl_pct']:+.2f}% | Sharpe: {r['sharpe']:.2f} | DD: {r['max_dd_pct']:.2f}% | Win: {r['win_rate']:.0%}")
|
||
print("\n"+"="*60); print(" Results in backtests/results/"); print(" View at: https://ftdt.io/cv (Backtest tab)"); print("="*60)
|
||
|
||
if __name__=="__main__": main()
|