mirror of
https://github.com/NicolasBohn/NexQuant.git
synced 2026-07-27 15:37:44 +00:00
feat: 15% monthly return target — infrastructure + daily signal resampling
Phase 1 — Infrastructure:
- RiskMgmt_RISK_PER_TRADE 0.5% → 1.5% (vbt_backtest.py)
- min_monthly_return_pct=15% acceptance filter (strategy_orchestrator)
- --min-monthly-return 15 CLI option (nexquant.py)
- {{ min_monthly_return }}% in strategy prompts
- MIN_MONTHLY_RETURN_PCT=15.0 in gen_strategies_real_bt + smart_strategy_gen
- realistic_backtest_all.py target_monthly 4→15%
Phase 2 — Factor quality:
- IC thresholds: prompt 0.05→0.08, bandit IC weight 0.10→0.20
- Explicite IC > 0.04 target in RAG prompt
- min_ic filters: data_loader 0.0→0.04, strategy_worker 0.02→0.04, ml_trainer 0.01→0.04
Architecture fix — Daily signal resampling:
- Factors have IC at daily resolution, but z-scores on 1-min collapse IC to ~0
- Resample factors to daily before strategy exec, ffill signal to 1-min for backtest
- Walk-forward IS years 3→1 (only 2 years of data available)
- Removed broken intersection() logic that destroyed 99.99% of 1-min data
- ffill stale propagation limited to 2880 bars (2 trading days)
- Fixed logger crash in _load_strategies
- Preflight: removed constant-signal check (false positive on random sandbox data)
- Tests: test_daily_signal_resampling.py (8 tests)
Non-negotiable rules: R1-R10 in AGENTS.md
This commit is contained in:
TPTBusiness
+6
-4
@@ -1481,6 +1481,7 @@ def generate_strategies(
|
||||
min_sharpe: float = typer.Option(1.5, "--min-sharpe", help="Minimum Sharpe for acceptance"),
|
||||
max_drawdown: float = typer.Option(-0.30, "--max-dd", help="Maximum drawdown allowed"),
|
||||
min_win_rate: float = typer.Option(0.40, "--min-winrate", help="Minimum win rate for acceptance"),
|
||||
min_monthly_return: float = typer.Option(15.0, "--min-monthly-return", help="Minimum OOS monthly return %% for acceptance"),
|
||||
):
|
||||
"""
|
||||
Generate trading strategies from top factors using LLM + Optuna optimization.
|
||||
@@ -1498,8 +1499,8 @@ def generate_strategies(
|
||||
$ nexquant generate-strategies --min-sharpe 3.0 # Stricter acceptance
|
||||
$ nexquant generate-strategies -s daytrading # Day trading style
|
||||
$ nexquant generate-strategies --no-optuna # Skip optimization
|
||||
$ nexquant generate-strategies --min-monthly-return 15 # 15% OOS monthly target
|
||||
"""
|
||||
from rich.console import Console as RichConsole
|
||||
from rich.table import Table as RichTable
|
||||
|
||||
console.print(f"\n[bold cyan]{'='*60}[/bold cyan]")
|
||||
@@ -1507,7 +1508,7 @@ def generate_strategies(
|
||||
console.print(f"[bold cyan]{'='*60}[/bold cyan]")
|
||||
console.print(f" Strategies: [cyan]{count}[/cyan] Workers: [cyan]{workers}[/cyan] Style: [cyan]{style}[/cyan]")
|
||||
console.print(f" Optuna: {'[green]Yes[/green]' if optuna else '[yellow]No[/yellow]'} (trials={optuna_trials}) Factors: [cyan]{top_factors}[/cyan]")
|
||||
console.print(f" Accept: Sharpe≥[green]{min_sharpe}[/green] DD≥[green]{max_drawdown}[/green] WR≥[green]{min_win_rate}[/green]")
|
||||
console.print(f" Accept: Sharpe≥[green]{min_sharpe}[/green] DD≥[green]{max_drawdown}[/green] WR≥[green]{min_win_rate}[/green] Mon≥[green]{min_monthly_return}%[/green]")
|
||||
console.print(f"[bold cyan]{'='*60}[/bold cyan]\n")
|
||||
|
||||
try:
|
||||
@@ -1519,6 +1520,7 @@ def generate_strategies(
|
||||
min_sharpe=min_sharpe,
|
||||
max_drawdown=max_drawdown,
|
||||
min_win_rate=min_win_rate,
|
||||
min_monthly_return_pct=min_monthly_return,
|
||||
use_optuna=optuna,
|
||||
optuna_trials=optuna_trials,
|
||||
continuous_optimization=optuna,
|
||||
@@ -1544,7 +1546,7 @@ def generate_strategies(
|
||||
table.add_row(
|
||||
str(i), r.get("strategy_name", "?")[:28],
|
||||
f"{r.get('sharpe_ratio', 0):.2f}", f"{r.get('max_drawdown', 0):.1%}",
|
||||
f"{r.get('win_rate', 0):.1%}", str(r.get('num_trades', '?')),
|
||||
f"{r.get('win_rate', 0):.1%}", str(r.get("num_trades", "?")),
|
||||
)
|
||||
console.print(table)
|
||||
|
||||
@@ -1660,7 +1662,7 @@ def _load_strategies():
|
||||
try:
|
||||
raw = json.loads(p.read_text())
|
||||
except Exception:
|
||||
logger.warning("Failed to load strategy file %s", p, exc_info=True)
|
||||
logger.warning(f"Failed to load strategy file {p}")
|
||||
continue
|
||||
if not isinstance(raw, dict):
|
||||
continue
|
||||
|
||||
@@ -34,9 +34,9 @@ strategy_generation:
|
||||
5. signal.name must be 'signal'
|
||||
|
||||
IC-Guided Factor Selection:
|
||||
- Factors with |IC| > 0.10 are highly predictive - PRIORITIZE these
|
||||
- Factors with |IC| > 0.05 are moderately predictive - USE these
|
||||
- Factors with |IC| < 0.05 are weak - AVOID unless complementary
|
||||
- Factors with |IC| > 0.15 are highly predictive - PRIORITIZE these
|
||||
- Factors with |IC| > 0.08 are moderately predictive - USE these
|
||||
- Factors with |IC| < 0.08 are weak - AVOID unless complementary
|
||||
- Combine factors with different signs of IC for diversification
|
||||
- Weight factors proportionally to their |IC| values
|
||||
|
||||
@@ -62,6 +62,7 @@ strategy_generation:
|
||||
TRADING STYLE: {{ trading_style }}
|
||||
TARGET SHARPE: > {{ min_sharpe }}
|
||||
MAX DRAWDOWN: {{ max_drawdown }}
|
||||
TARGET MONTHLY RETURN: > {{ min_monthly_return }}%
|
||||
|
||||
CRITICAL CODE RULES:
|
||||
1. DO NOT define functions - write direct executable code
|
||||
|
||||
@@ -42,8 +42,8 @@ EXTREME_BAR_THRESHOLD = 0.05 # |ret| > 5% on a single 1-min bar → suspicious
|
||||
FTMO_INITIAL_CAPITAL = 100_000.0
|
||||
FTMO_MAX_DAILY_LOSS = 0.05 # 5% of initial → block new trades rest of day
|
||||
FTMO_MAX_TOTAL_LOSS = 0.10 # 10% of initial → simulation ends
|
||||
# Risk-based position sizing: 0.5% equity risk per trade, 10-pip stop, max 1:30 leverage
|
||||
FTMO_RISK_PER_TRADE = 0.005
|
||||
# Risk-based position sizing: 1.5% equity risk per trade, 10-pip stop, max 1:30 leverage
|
||||
FTMO_RISK_PER_TRADE = 0.015
|
||||
FTMO_STOP_PIPS = 10
|
||||
FTMO_PIP = 0.0001
|
||||
FTMO_MAX_LEVERAGE = 30
|
||||
@@ -343,7 +343,7 @@ def _apply_ftmo_mask(
|
||||
OOS_START_DEFAULT = "2024-01-01"
|
||||
|
||||
# Rolling walk-forward default windows (IS years, OOS years, step years)
|
||||
WF_IS_YEARS = 3
|
||||
WF_IS_YEARS = 1
|
||||
WF_OOS_YEARS = 1
|
||||
WF_STEP_YEARS = 1
|
||||
|
||||
|
||||
@@ -387,6 +387,10 @@ class QlibFactorRunner(CachedRunner[QlibFactorExperiment]):
|
||||
warnings.append(
|
||||
f"IC is near zero ({ic_float:.6f}) — factor may not predict returns",
|
||||
)
|
||||
if abs(ic_float) < 0.04:
|
||||
warnings.append(
|
||||
f"IC below target ({ic_float:.4f}) — factor will be excluded from strategy building (min IC=0.04)",
|
||||
)
|
||||
except (ValueError, TypeError):
|
||||
warnings.append(f"IC value is not numeric: {ic_value}")
|
||||
|
||||
|
||||
@@ -94,7 +94,7 @@ class LinearThompsonTwoArm:
|
||||
|
||||
class EnvController:
|
||||
def __init__(self, weights: Tuple[float, ...] = None) -> None:
|
||||
self.weights = np.asarray(weights or (0.1, 0.1, 0.05, 0.05, 0.25, 0.15, 0.1, 0.2))
|
||||
self.weights = np.asarray(weights or (0.2, 0.1, 0.05, 0.05, 0.25, 0.1, 0.1, 0.15))
|
||||
self.bandit = LinearThompsonTwoArm(dim=8, prior_var=10.0, noise_var=0.5)
|
||||
|
||||
def reward(self, m: Metrics) -> float:
|
||||
|
||||
@@ -108,7 +108,7 @@ class QlibQuantHypothesisGen(FactorAndModelHypothesisGen):
|
||||
if len(trace.hist) < 6:
|
||||
qaunt_rag = "Try the easiest and fastest factors to experiment with from various perspectives first."
|
||||
else:
|
||||
qaunt_rag = "Now, you need to try factors that can achieve high IC (e.g., machine learning-based factors)! Do not include factors that are similar to those in the SOTA factor library!"
|
||||
qaunt_rag = "Now, you need to try factors that can achieve high IC (target |IC| > 0.04, e.g., machine learning-based factors)! Do not include factors that are similar to those in the SOTA factor library!"
|
||||
elif action == "model":
|
||||
qaunt_rag = "1. In Quantitative Finance, market data could be time-series, and GRU model/LSTM model are suitable for them. Do not generate GNN model as for now.\n2. The training data consists of approximately 478,000 samples for the training set and about 128,000 samples for the validation set. Please design the hyperparameters accordingly and control the model size. This has a significant impact on the training results. If you believe that the previous model itself is good but the training hyperparameters or model hyperparameters are not optimal, you can return the same model and adjust these parameters instead.\n"
|
||||
|
||||
|
||||
@@ -15,20 +15,27 @@ Usage:
|
||||
# With parallel workers (default: CPU count)
|
||||
TRADING_STYLE=daytrading WORKERS=4 python nexquant_gen_strategies_real_bt.py 20
|
||||
"""
|
||||
import os, sys, json, time, math, random, logging, warnings, subprocess
|
||||
from pathlib import Path
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import random
|
||||
import subprocess
|
||||
import sys
|
||||
import time
|
||||
import warnings
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
from rich.console import Console
|
||||
from rich.progress import Progress, SpinnerColumn, TextColumn, BarColumn, TimeElapsedColumn
|
||||
from dotenv import load_dotenv
|
||||
from rich.console import Console
|
||||
from rich.progress import BarColumn, Progress, SpinnerColumn, TextColumn, TimeElapsedColumn
|
||||
|
||||
# Suppress warnings and noisy loggers that bleed into Rich progress output
|
||||
warnings.filterwarnings('ignore')
|
||||
for _noisy in ('rdagent', 'litellm', 'LiteLLM', 'litellm.utils',
|
||||
'litellm.main', 'httpx', 'httpcore', 'openai', 'urllib3'):
|
||||
warnings.filterwarnings("ignore")
|
||||
for _noisy in ("rdagent", "litellm", "LiteLLM", "litellm.utils",
|
||||
"litellm.main", "httpx", "httpcore", "openai", "urllib3"):
|
||||
logging.getLogger(_noisy).setLevel(logging.CRITICAL)
|
||||
# Suppress litellm verbose flag if already imported
|
||||
try:
|
||||
@@ -42,36 +49,38 @@ except Exception:
|
||||
# ============================================================================
|
||||
# Configuration
|
||||
# ============================================================================
|
||||
OHLCV_PATH = Path('/home/nico/NexQuant/git_ignore_folder/factor_implementation_source_data/intraday_pv.h5')
|
||||
FACTORS_DIR = Path('/home/nico/NexQuant/results/factors')
|
||||
STRATEGIES_DIR = Path('/home/nico/NexQuant/results/strategies_new')
|
||||
OHLCV_PATH = Path("/home/nico/NexQuant/git_ignore_folder/factor_implementation_source_data/intraday_pv.h5")
|
||||
FACTORS_DIR = Path("/home/nico/NexQuant/results/factors")
|
||||
STRATEGIES_DIR = Path("/home/nico/NexQuant/results/strategies_new")
|
||||
STRATEGIES_DIR.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
# Trading style
|
||||
TRADING_STYLE = os.getenv('TRADING_STYLE', 'swing')
|
||||
N_WORKERS = int(os.getenv('WORKERS', os.cpu_count() or 4))
|
||||
TRADING_STYLE = os.getenv("TRADING_STYLE", "swing")
|
||||
N_WORKERS = int(os.getenv("WORKERS", os.cpu_count() or 4))
|
||||
|
||||
if TRADING_STYLE == 'daytrading':
|
||||
FORWARD_BARS = int(os.getenv('FORWARD_BARS', '12'))
|
||||
if TRADING_STYLE == "daytrading":
|
||||
FORWARD_BARS = int(os.getenv("FORWARD_BARS", "12"))
|
||||
MIN_IC = 0.02
|
||||
MIN_SHARPE = 0.5
|
||||
MIN_TRADES = 300
|
||||
MAX_DRAWDOWN = -0.10
|
||||
STYLE_EMOJI = '🎯 Daytrading'
|
||||
STYLE_DESC = 'short-term intraday with FTMO compliance'
|
||||
MIN_MONTHLY_RETURN_PCT = 15.0
|
||||
STYLE_EMOJI = "🎯 Daytrading"
|
||||
STYLE_DESC = "short-term intraday with FTMO compliance"
|
||||
else:
|
||||
FORWARD_BARS = int(os.getenv('FORWARD_BARS', '96'))
|
||||
FORWARD_BARS = int(os.getenv("FORWARD_BARS", "96"))
|
||||
MIN_IC = 0.02
|
||||
MIN_SHARPE = 0.5
|
||||
MIN_TRADES = 10
|
||||
MAX_DRAWDOWN = -0.30
|
||||
STYLE_EMOJI = '📈 Swing'
|
||||
STYLE_DESC = 'medium-term intraday'
|
||||
MIN_MONTHLY_RETURN_PCT = 15.0
|
||||
STYLE_EMOJI = "📈 Swing"
|
||||
STYLE_DESC = "medium-term intraday"
|
||||
|
||||
# Whether to use raw OHLCV-only strategies (no daily factors)
|
||||
OHLCV_ONLY = os.getenv('OHLCV_ONLY', '0') == '1'
|
||||
OHLCV_ONLY = os.getenv("OHLCV_ONLY", "0") == "1"
|
||||
|
||||
TXN_COST_BPS = float(os.getenv('TXN_COST_BPS', '2.14')) # 2.35 pip realistic EUR/USD costs
|
||||
TXN_COST_BPS = float(os.getenv("TXN_COST_BPS", "2.14")) # 2.35 pip realistic EUR/USD costs
|
||||
|
||||
# ── Logging setup: everything printed goes to log file + stdout ───────────────
|
||||
_LOG_DIR = Path(__file__).parent.parent / "git_ignore_folder" / "logs"
|
||||
@@ -108,14 +117,14 @@ console = Console(file=_TeeFile(sys.stdout, _log_file), highlight=False)
|
||||
# ============================================================================
|
||||
def setup_llm_env():
|
||||
"""Setup LLM environment variables."""
|
||||
load_dotenv(Path(__file__).parent.parent / '.env')
|
||||
if os.getenv('OPENAI_API_KEY') == 'local' or os.getenv('LLM_BACKEND', '').lower() == 'local':
|
||||
load_dotenv(Path(__file__).parent.parent / ".env")
|
||||
if os.getenv("OPENAI_API_KEY") == "local" or os.getenv("LLM_BACKEND", "").lower() == "local":
|
||||
return
|
||||
router_key = os.getenv('OPENROUTER_API_KEY', '')
|
||||
router_key = os.getenv("OPENROUTER_API_KEY", "")
|
||||
if router_key:
|
||||
os.environ['OPENAI_API_KEY'] = router_key
|
||||
os.environ['OPENAI_API_BASE'] = 'https://openrouter.ai/api/v1'
|
||||
os.environ['CHAT_MODEL'] = os.getenv('OPENROUTER_MODEL', 'openrouter/google/gemma-4-26b-a4b-it:free')
|
||||
os.environ["OPENAI_API_KEY"] = router_key
|
||||
os.environ["OPENAI_API_BASE"] = "https://openrouter.ai/api/v1"
|
||||
os.environ["CHAT_MODEL"] = os.getenv("OPENROUTER_MODEL", "openrouter/google/gemma-4-26b-a4b-it:free")
|
||||
|
||||
# ============================================================================
|
||||
# Factor Loading (cached at module level for each process)
|
||||
@@ -127,20 +136,20 @@ def load_available_factors(top_n=20):
|
||||
global _FACTORS_CACHE
|
||||
if _FACTORS_CACHE is not None:
|
||||
return _FACTORS_CACHE[:top_n]
|
||||
|
||||
|
||||
factors = []
|
||||
for f in FACTORS_DIR.glob('*.json'):
|
||||
for f in FACTORS_DIR.glob("*.json"):
|
||||
try:
|
||||
data = json.load(open(f))
|
||||
fname = data.get('factor_name', '')
|
||||
ic = data.get('ic') or 0
|
||||
safe = fname.replace('/','_').replace('\\','_')[:150]
|
||||
if (FACTORS_DIR / 'values' / f"{safe}.parquet").exists():
|
||||
factors.append({'name': fname, 'ic': ic})
|
||||
fname = data.get("factor_name", "")
|
||||
ic = data.get("ic") or 0
|
||||
safe = fname.replace("/","_").replace("\\","_")[:150]
|
||||
if (FACTORS_DIR / "values" / f"{safe}.parquet").exists():
|
||||
factors.append({"name": fname, "ic": ic})
|
||||
except:
|
||||
pass
|
||||
|
||||
factors.sort(key=lambda x: abs(x['ic']), reverse=True)
|
||||
|
||||
factors.sort(key=lambda x: abs(x["ic"]), reverse=True)
|
||||
_FACTORS_CACHE = factors
|
||||
return factors[:top_n]
|
||||
|
||||
@@ -154,18 +163,18 @@ def load_ohlcv_data():
|
||||
global _OHLCV_CACHE
|
||||
if _OHLCV_CACHE is not None:
|
||||
return _OHLCV_CACHE
|
||||
|
||||
|
||||
if not OHLCV_PATH.exists():
|
||||
raise FileNotFoundError(f"OHLCV data not found: {OHLCV_PATH}")
|
||||
|
||||
ohlcv = pd.read_hdf(str(OHLCV_PATH), key='data')
|
||||
if '$close' in ohlcv.columns:
|
||||
close = ohlcv['$close']
|
||||
elif 'close' in ohlcv.columns:
|
||||
close = ohlcv['close']
|
||||
|
||||
ohlcv = pd.read_hdf(str(OHLCV_PATH), key="data")
|
||||
if "$close" in ohlcv.columns:
|
||||
close = ohlcv["$close"]
|
||||
elif "close" in ohlcv.columns:
|
||||
close = ohlcv["close"]
|
||||
else:
|
||||
close = ohlcv.select_dtypes(include=[np.number]).iloc[:, 0]
|
||||
|
||||
|
||||
_OHLCV_CACHE = close.dropna()
|
||||
return _OHLCV_CACHE
|
||||
|
||||
@@ -175,16 +184,16 @@ def load_ohlcv_data():
|
||||
def generate_single_strategy(args):
|
||||
"""Generate and backtest ONE strategy. Runs in separate process."""
|
||||
idx, factor_subset, feedback, attempt = args
|
||||
|
||||
|
||||
try:
|
||||
setup_llm_env()
|
||||
|
||||
|
||||
from rdagent.oai.llm_utils import APIBackend
|
||||
|
||||
|
||||
factor_list = "\n".join([f"- {f['name']} (IC={f['ic']:.4f})" for f in factor_subset])
|
||||
|
||||
|
||||
# Optimized prompts for daytrading vs swing
|
||||
if TRADING_STYLE == 'daytrading' and OHLCV_ONLY:
|
||||
if TRADING_STYLE == "daytrading" and OHLCV_ONLY:
|
||||
system_prompt = """You are an expert EUR/USD intraday quant. You build strategies that work ONLY on raw price data (OHLCV), computing all indicators directly from the 1-minute close series.
|
||||
|
||||
CRITICAL RULES:
|
||||
@@ -219,9 +228,10 @@ Hard requirements:
|
||||
- Use EMA crossover thresholds of 0 (cross above/below) for maximum trade frequency
|
||||
- Use causal indicators only: rolling windows, shift(1) — NO look-ahead bias
|
||||
- No factor data — compute everything from 'close'
|
||||
- Keep it simple: 2-3 indicators max"""
|
||||
- Keep it simple: 2-3 indicators max
|
||||
- TARGET MONTHLY RETURN: Generate signals that can achieve >15% OOS monthly return after FTMO costs (2.35 pip/trade). Use high-conviction entries only."""
|
||||
|
||||
elif TRADING_STYLE == 'daytrading':
|
||||
elif TRADING_STYLE == "daytrading":
|
||||
system_prompt = f"""You are an expert daytrading quant specializing in EUR/USD scalping and intraday strategies.
|
||||
|
||||
CRITICAL RULES for {STYLE_DESC} (forward horizon: {FORWARD_BARS} bars = ~{FORWARD_BARS} minutes):
|
||||
@@ -247,7 +257,8 @@ Hard requirements:
|
||||
- NEVER use ffill() or forward-fill on the signal — recompute fresh at every bar
|
||||
- Use rolling z-scores with windows of 5-20 bars (not 50-100), thresholds ±0.2 to ±0.5
|
||||
- Combine 2 factors: one momentum, one mean-reversion
|
||||
- NO global mean/std — always use rolling(window).mean() with shift(1) to avoid look-ahead bias"""
|
||||
- NO global mean/std — always use rolling(window).mean() with shift(1) to avoid look-ahead bias
|
||||
- TARGET MONTHLY RETURN: Generate signals that can achieve >15% OOS monthly return after FTMO costs (2.35 pip/trade). Use high-conviction entries only."""
|
||||
|
||||
else:
|
||||
system_prompt = f"""You are a quantitative trading expert specializing in EUR/USD daily swing strategies.
|
||||
@@ -278,26 +289,26 @@ Output ONLY valid JSON with these fields:
|
||||
|
||||
{f'Previous feedback: {feedback}' if feedback else 'First attempt - be creative!'}
|
||||
|
||||
Use daily-level signal logic (factor above/below rolling daily mean). Signal changes once per day."""
|
||||
|
||||
Use daily-level signal logic (factor above/below rolling daily mean). Signal changes once per day. TARGET MONTHLY RETURN: Generate signals that can achieve >15% OOS monthly return after FTMO costs (2.35 pip/trade)."""
|
||||
|
||||
api = APIBackend()
|
||||
response = api.build_messages_and_create_chat_completion(
|
||||
user_prompt=user_prompt, system_prompt=system_prompt, json_mode=True
|
||||
user_prompt=user_prompt, system_prompt=system_prompt, json_mode=True,
|
||||
)
|
||||
strategy_data = json.loads(response)
|
||||
|
||||
|
||||
# Validate response
|
||||
if 'code' not in strategy_data or 'factor_names' not in strategy_data:
|
||||
return {'status': 'invalid', 'reason': 'Missing required fields', 'idx': idx}
|
||||
|
||||
if "code" not in strategy_data or "factor_names" not in strategy_data:
|
||||
return {"status": "invalid", "reason": "Missing required fields", "idx": idx}
|
||||
|
||||
return {
|
||||
'status': 'generated',
|
||||
'strategy': strategy_data,
|
||||
'idx': idx
|
||||
"status": "generated",
|
||||
"strategy": strategy_data,
|
||||
"idx": idx,
|
||||
}
|
||||
|
||||
|
||||
except Exception as e:
|
||||
return {'status': 'error', 'reason': str(e)[:200], 'idx': idx}
|
||||
return {"status": "error", "reason": str(e)[:200], "idx": idx}
|
||||
|
||||
# ============================================================================
|
||||
# Backtest Runner (runs in main process to avoid re-loading data)
|
||||
@@ -345,32 +356,32 @@ signal.fillna(0).to_pickle('signal.pkl')
|
||||
|
||||
with tempfile.TemporaryDirectory() as td:
|
||||
tdp = Path(td)
|
||||
close.to_pickle(str(tdp / 'close.pkl'))
|
||||
close.to_pickle(str(tdp / "close.pkl"))
|
||||
if not OHLCV_ONLY and factors_df is not None:
|
||||
factors_df.to_pickle(str(tdp / 'factors.pkl'))
|
||||
(tdp / 'run.py').write_text(script)
|
||||
factors_df.to_pickle(str(tdp / "factors.pkl"))
|
||||
(tdp / "run.py").write_text(script)
|
||||
|
||||
try:
|
||||
result = subprocess.run(
|
||||
['python', 'run.py'],
|
||||
["python", "run.py"],
|
||||
capture_output=True, text=True, timeout=60,
|
||||
cwd=str(tdp)
|
||||
cwd=str(tdp),
|
||||
)
|
||||
if result.returncode != 0:
|
||||
return {'status': 'failed', 'reason': (result.stderr or result.stdout)[:200]}
|
||||
return {"status": "failed", "reason": (result.stderr or result.stdout)[:200]}
|
||||
|
||||
signal = pd.read_pickle(tdp / 'signal.pkl')
|
||||
signal = pd.read_pickle(tdp / "signal.pkl")
|
||||
except subprocess.TimeoutExpired:
|
||||
return {'status': 'failed', 'reason': 'Timeout (60s)'}
|
||||
return {"status": "failed", "reason": "Timeout (60s)"}
|
||||
except Exception as e:
|
||||
return {'status': 'failed', 'reason': str(e)[:200]}
|
||||
return {"status": "failed", "reason": str(e)[:200]}
|
||||
|
||||
# Main process: FTMO-realistic backtest (leverage + daily/total loss limits).
|
||||
from rdagent.components.backtesting.vbt_backtest import backtest_signal_ftmo
|
||||
|
||||
common = close.index.intersection(signal.index)
|
||||
if len(common) < 100:
|
||||
return {'status': 'failed', 'reason': f'Not enough aligned data ({len(common)} bars)'}
|
||||
return {"status": "failed", "reason": f"Not enough aligned data ({len(common)} bars)"}
|
||||
|
||||
close_a = close.loc[common]
|
||||
signal_a = signal.reindex(common).fillna(0)
|
||||
@@ -409,9 +420,9 @@ def _rescale_thresholds(code: str, scale: float) -> str:
|
||||
return f"{val * scale:.3f}"
|
||||
|
||||
# RSI-style thresholds: integers/floats between 10 and 90
|
||||
code = re.sub(r'\b([1-9]\d(?:\.\d+)?)\b', replace_rsi, code)
|
||||
code = re.sub(r"\b([1-9]\d(?:\.\d+)?)\b", replace_rsi, code)
|
||||
# Small float thresholds: 0.05 – 2.99
|
||||
code = re.sub(r'\b(0\.\d+|[12]\.\d+)\b', replace_small, code)
|
||||
code = re.sub(r"\b(0\.\d+|[12]\.\d+)\b", replace_small, code)
|
||||
return code
|
||||
|
||||
|
||||
@@ -426,12 +437,12 @@ def tune_thresholds(close, factors_df, code: str) -> tuple:
|
||||
for scale in [1.0, 0.7, 0.5, 0.35, 0.2, 0.1, 0.05]:
|
||||
tuned = _rescale_thresholds(code, scale) if scale < 1.0 else code
|
||||
bt = run_backtest(close, factors_df, tuned)
|
||||
if bt is None or bt.get('status') != 'success':
|
||||
if bt is None or bt.get("status") != "success":
|
||||
continue
|
||||
trades = bt.get('n_trades', 0)
|
||||
sharpe = bt.get('sharpe', -999)
|
||||
trades = bt.get("n_trades", 0)
|
||||
sharpe = bt.get("sharpe", -999)
|
||||
if trades >= MIN_TRADES:
|
||||
if best_bt is None or sharpe > best_bt.get('sharpe', -999):
|
||||
if best_bt is None or sharpe > best_bt.get("sharpe", -999):
|
||||
best_bt = bt
|
||||
best_code = tuned
|
||||
break # first scale that hits MIN_TRADES wins (they get looser after this)
|
||||
@@ -461,46 +472,46 @@ def main(target_count=10):
|
||||
console.print(f" Forward bars: {FORWARD_BARS}")
|
||||
console.print(f" Target: {target_count} accepted strategies")
|
||||
console.print(f" Workers: {N_WORKERS}\n")
|
||||
|
||||
|
||||
# Load data (main process only)
|
||||
close = load_ohlcv_data()
|
||||
factors = load_available_factors(20)
|
||||
|
||||
|
||||
console.print(f"[green]✓[/green] Loaded {len(factors)} factors, {len(close):,} OHLCV bars\n")
|
||||
|
||||
|
||||
# Load factor time-series
|
||||
factor_data = {}
|
||||
with Progress(SpinnerColumn(), TextColumn("[bold blue]Loading factors..."), BarColumn(), TimeElapsedColumn()) as progress:
|
||||
task = progress.add_task("Loading...", total=len(factors))
|
||||
for f_info in factors:
|
||||
safe = f_info['name'].replace('/','_').replace('\\','_')[:150]
|
||||
pf = FACTORS_DIR / 'values' / f"{safe}.parquet"
|
||||
safe = f_info["name"].replace("/","_").replace("\\","_")[:150]
|
||||
pf = FACTORS_DIR / "values" / f"{safe}.parquet"
|
||||
if pf.exists():
|
||||
try:
|
||||
series = pd.read_parquet(str(pf)).iloc[:, 0]
|
||||
factor_data[f_info['name']] = series
|
||||
factor_data[f_info["name"]] = series
|
||||
except:
|
||||
pass
|
||||
progress.update(task, advance=1)
|
||||
|
||||
|
||||
# Align factors with close prices
|
||||
all_factor_series = [factor_data[n] for n in factor_data if n in factor_data]
|
||||
if not all_factor_series:
|
||||
console.print("[red]✗ No factor data loaded![/red]")
|
||||
return
|
||||
|
||||
|
||||
df_factors = pd.DataFrame({n: factor_data[n] for n in factor_data if n in factor_data})
|
||||
common_idx = close.index.intersection(df_factors.dropna(how='all').index)
|
||||
common_idx = close.index.intersection(df_factors.dropna(how="all").index)
|
||||
close_aligned = close.loc[common_idx]
|
||||
df_aligned = df_factors.loc[common_idx]
|
||||
|
||||
|
||||
console.print(f"[green]✓[/green] Aligned {len(df_aligned):,} data points\n")
|
||||
|
||||
|
||||
# Strategy generation loop
|
||||
accepted = []
|
||||
feedback_history = []
|
||||
max_attempts = target_count * 10 # Allow 10x attempts
|
||||
|
||||
|
||||
with Progress(
|
||||
SpinnerColumn(),
|
||||
TextColumn("[bold blue]{task.description}"),
|
||||
@@ -511,11 +522,11 @@ def main(target_count=10):
|
||||
redirect_stderr=True,
|
||||
) as progress:
|
||||
task = progress.add_task("Generating...", total=max_attempts)
|
||||
|
||||
|
||||
for attempt in range(max_attempts):
|
||||
if len(accepted) >= target_count:
|
||||
break
|
||||
|
||||
|
||||
# Select random factor subset (2-5 factors) — empty for OHLCV-only mode
|
||||
if OHLCV_ONLY:
|
||||
factor_subset = []
|
||||
@@ -528,51 +539,51 @@ def main(target_count=10):
|
||||
# Generate in main process (LLM doesn't parallelize well)
|
||||
gen_result = generate_single_strategy((attempt, factor_subset, feedback, attempt))
|
||||
|
||||
if gen_result['status'] != 'generated':
|
||||
if gen_result["status"] != "generated":
|
||||
progress.update(task, advance=1)
|
||||
continue
|
||||
|
||||
strategy = gen_result['strategy']
|
||||
strategy = gen_result["strategy"]
|
||||
|
||||
# Backtest (main process - needs data access)
|
||||
if OHLCV_ONLY:
|
||||
strat_factors = None
|
||||
bt_result = run_backtest(close, None, strategy.get('code', ''))
|
||||
bt_result = run_backtest(close, None, strategy.get("code", ""))
|
||||
else:
|
||||
strat_factors = df_aligned[[f for f in strategy.get('factor_names', []) if f in df_aligned.columns]]
|
||||
strat_factors = df_aligned[[f for f in strategy.get("factor_names", []) if f in df_aligned.columns]]
|
||||
if len(strat_factors.columns) < 2:
|
||||
progress.update(task, advance=1)
|
||||
continue
|
||||
bt_result = run_backtest(close_aligned, strat_factors, strategy.get('code', ''))
|
||||
|
||||
if bt_result and bt_result.get('status') == 'success':
|
||||
ic = bt_result.get('ic', 0)
|
||||
sharpe = bt_result.get('sharpe', 0)
|
||||
trades = bt_result.get('n_trades', 0)
|
||||
dd = bt_result.get('max_drawdown', 0)
|
||||
bt_result = run_backtest(close_aligned, strat_factors, strategy.get("code", ""))
|
||||
|
||||
if bt_result and bt_result.get("status") == "success":
|
||||
ic = bt_result.get("ic", 0)
|
||||
sharpe = bt_result.get("sharpe", 0)
|
||||
trades = bt_result.get("n_trades", 0)
|
||||
dd = bt_result.get("max_drawdown", 0)
|
||||
|
||||
# If too few trades, auto-tune thresholds before giving up
|
||||
original_code = strategy.get('code', '')
|
||||
if trades < MIN_TRADES and bt_result.get('status') == 'success':
|
||||
original_code = strategy.get("code", "")
|
||||
if trades < MIN_TRADES and bt_result.get("status") == "success":
|
||||
_log.info(f"TUNING trades={trades}<{MIN_TRADES} — trying looser thresholds")
|
||||
tuned_bt, tuned_code = tune_thresholds(
|
||||
close if OHLCV_ONLY else close_aligned,
|
||||
None if OHLCV_ONLY else strat_factors,
|
||||
original_code,
|
||||
)
|
||||
if tuned_bt and tuned_bt.get('n_trades', 0) >= MIN_TRADES:
|
||||
if tuned_bt and tuned_bt.get("n_trades", 0) >= MIN_TRADES:
|
||||
bt_result = tuned_bt
|
||||
strategy['code'] = tuned_code
|
||||
ic = bt_result.get('ic', 0)
|
||||
sharpe = bt_result.get('sharpe', 0)
|
||||
trades = bt_result.get('n_trades', 0)
|
||||
dd = bt_result.get('max_drawdown', 0)
|
||||
strategy["code"] = tuned_code
|
||||
ic = bt_result.get("ic", 0)
|
||||
sharpe = bt_result.get("sharpe", 0)
|
||||
trades = bt_result.get("n_trades", 0)
|
||||
dd = bt_result.get("max_drawdown", 0)
|
||||
_log.info(f"TUNED Sharpe={sharpe:.2f} Trades={trades}")
|
||||
|
||||
# OOS metrics — mandatory, no fallback to IS values
|
||||
oos_sharpe = bt_result.get('oos_sharpe')
|
||||
oos_monthly = bt_result.get('oos_monthly_return_pct')
|
||||
oos_trades = bt_result.get('oos_n_trades', 0)
|
||||
oos_sharpe = bt_result.get("oos_sharpe")
|
||||
oos_monthly = bt_result.get("oos_monthly_return_pct")
|
||||
oos_trades = bt_result.get("oos_n_trades", 0)
|
||||
|
||||
# Reject if OOS data is missing (strategy trained on data without OOS period)
|
||||
if oos_sharpe is None or oos_monthly is None:
|
||||
@@ -582,54 +593,54 @@ def main(target_count=10):
|
||||
continue
|
||||
|
||||
# Monte Carlo p-value (edge significance)
|
||||
mc_pvalue = bt_result.get('mc_pvalue')
|
||||
mc_pvalue = bt_result.get("mc_pvalue")
|
||||
|
||||
# Rolling walk-forward metrics
|
||||
wf_consistency = bt_result.get('wf_oos_consistency')
|
||||
wf_sharpe_mean = bt_result.get('wf_oos_sharpe_mean')
|
||||
wf_consistency = bt_result.get("wf_oos_consistency")
|
||||
wf_sharpe_mean = bt_result.get("wf_oos_sharpe_mean")
|
||||
|
||||
# Check acceptance criteria — OOS must be profitable + statistically significant
|
||||
mc_ok = mc_pvalue is None or mc_pvalue < 0.20 # lenient: top 20% non-random
|
||||
wf_ok = wf_consistency is None or wf_consistency >= 0.5 # ≥50% of WF windows profitable
|
||||
if (abs(ic or 0) > MIN_IC and sharpe > MIN_SHARPE and trades > MIN_TRADES and dd > MAX_DRAWDOWN
|
||||
and oos_sharpe > 0.0 and oos_monthly > 0.0 and mc_ok and wf_ok):
|
||||
and oos_sharpe > 0.0 and oos_monthly > MIN_MONTHLY_RETURN_PCT and mc_ok and wf_ok):
|
||||
# ACCEPT
|
||||
strategy['real_backtest'] = bt_result
|
||||
strategy['metrics'] = bt_result
|
||||
strategy['summary'] = {
|
||||
'sharpe': sharpe, 'max_drawdown': dd, 'win_rate': bt_result.get('win_rate', 0),
|
||||
'monthly_return_pct': bt_result.get('monthly_return_pct', 0),
|
||||
'annual_return_pct': bt_result.get('annual_return_pct', 0),
|
||||
'real_ic': ic, 'real_n_trades': trades, 'real_backtest_status': 'success',
|
||||
'n_bars': bt_result.get('n_bars', 0), 'n_months': bt_result.get('n_months', 0),
|
||||
'trading_style': TRADING_STYLE,
|
||||
'ohlcv_only': OHLCV_ONLY,
|
||||
'engine': 'ftmo_v2',
|
||||
'txn_cost_bps': TXN_COST_BPS,
|
||||
strategy["real_backtest"] = bt_result
|
||||
strategy["metrics"] = bt_result
|
||||
strategy["summary"] = {
|
||||
"sharpe": sharpe, "max_drawdown": dd, "win_rate": bt_result.get("win_rate", 0),
|
||||
"monthly_return_pct": bt_result.get("monthly_return_pct", 0),
|
||||
"annual_return_pct": bt_result.get("annual_return_pct", 0),
|
||||
"real_ic": ic, "real_n_trades": trades, "real_backtest_status": "success",
|
||||
"n_bars": bt_result.get("n_bars", 0), "n_months": bt_result.get("n_months", 0),
|
||||
"trading_style": TRADING_STYLE,
|
||||
"ohlcv_only": OHLCV_ONLY,
|
||||
"engine": "ftmo_v2",
|
||||
"txn_cost_bps": TXN_COST_BPS,
|
||||
# Walk-forward OOS split
|
||||
'oos_sharpe': bt_result.get('oos_sharpe'),
|
||||
'oos_monthly_return_pct': bt_result.get('oos_monthly_return_pct'),
|
||||
'oos_max_drawdown': bt_result.get('oos_max_drawdown'),
|
||||
'oos_win_rate': bt_result.get('oos_win_rate'),
|
||||
'oos_n_trades': bt_result.get('oos_n_trades'),
|
||||
'is_sharpe': bt_result.get('is_sharpe'),
|
||||
'is_monthly_return_pct': bt_result.get('is_monthly_return_pct'),
|
||||
'oos_start': bt_result.get('oos_start'),
|
||||
"oos_sharpe": bt_result.get("oos_sharpe"),
|
||||
"oos_monthly_return_pct": bt_result.get("oos_monthly_return_pct"),
|
||||
"oos_max_drawdown": bt_result.get("oos_max_drawdown"),
|
||||
"oos_win_rate": bt_result.get("oos_win_rate"),
|
||||
"oos_n_trades": bt_result.get("oos_n_trades"),
|
||||
"is_sharpe": bt_result.get("is_sharpe"),
|
||||
"is_monthly_return_pct": bt_result.get("is_monthly_return_pct"),
|
||||
"oos_start": bt_result.get("oos_start"),
|
||||
# Rolling walk-forward
|
||||
'wf_n_windows': bt_result.get('wf_n_windows'),
|
||||
'wf_oos_sharpe_mean': wf_sharpe_mean,
|
||||
'wf_oos_sharpe_std': bt_result.get('wf_oos_sharpe_std'),
|
||||
'wf_oos_monthly_return_mean': bt_result.get('wf_oos_monthly_return_mean'),
|
||||
'wf_oos_consistency': wf_consistency,
|
||||
"wf_n_windows": bt_result.get("wf_n_windows"),
|
||||
"wf_oos_sharpe_mean": wf_sharpe_mean,
|
||||
"wf_oos_sharpe_std": bt_result.get("wf_oos_sharpe_std"),
|
||||
"wf_oos_monthly_return_mean": bt_result.get("wf_oos_monthly_return_mean"),
|
||||
"wf_oos_consistency": wf_consistency,
|
||||
# Monte Carlo significance
|
||||
'mc_pvalue': mc_pvalue,
|
||||
'mc_n_permutations': bt_result.get('mc_n_permutations'),
|
||||
"mc_pvalue": mc_pvalue,
|
||||
"mc_n_permutations": bt_result.get("mc_n_permutations"),
|
||||
}
|
||||
|
||||
|
||||
fname = f"{int(time.time())}_{strategy['strategy_name']}.json"
|
||||
with open(STRATEGIES_DIR / fname, 'w') as f:
|
||||
with open(STRATEGIES_DIR / fname, "w") as f:
|
||||
json.dump(strategy, f, indent=2, ensure_ascii=False)
|
||||
|
||||
|
||||
# Generate PDF report
|
||||
try:
|
||||
from nexquant_strategy_report import StrategyPerformanceReporter
|
||||
@@ -637,7 +648,7 @@ def main(target_count=10):
|
||||
reporter.generate_report()
|
||||
except:
|
||||
pass
|
||||
|
||||
|
||||
accepted.append(strategy)
|
||||
_log.success(f"ACCEPTED {strategy['strategy_name']} IC={ic:.4f} Sharpe={sharpe:.3f} Trades={trades} DD={dd:.1%}")
|
||||
feedback_history.append(f"Excellent! IC={ic:.4f}, Sharpe={sharpe:.2f}, Trades={trades}. Try to improve further.")
|
||||
@@ -656,27 +667,27 @@ def main(target_count=10):
|
||||
+ (f", MC_p={mc_pvalue:.2f}" if mc_pvalue is not None else "")
|
||||
+ (f", WF_consistency={wf_consistency:.0%}" if wf_consistency is not None else "")
|
||||
+ f". Need |IC|>{MIN_IC}, Sharpe>{MIN_SHARPE}, Trades>{MIN_TRADES}, "
|
||||
f"OOS_Sharpe>0, OOS_Monthly>0, MC_p<0.20, WF_consistency≥50%."
|
||||
f"OOS_Sharpe>0, OOS_Monthly>{MIN_MONTHLY_RETURN_PCT}%, MC_p<0.20, WF_consistency≥50%.",
|
||||
)
|
||||
|
||||
|
||||
progress.update(task, advance=1)
|
||||
|
||||
|
||||
# Summary
|
||||
_log.info(f"DONE accepted={len(accepted)} target={target_count}")
|
||||
for i, s in enumerate(sorted(accepted, key=lambda x: x['real_backtest'].get('ic', 0), reverse=True), 1):
|
||||
bt = s['real_backtest']
|
||||
for i, s in enumerate(sorted(accepted, key=lambda x: x["real_backtest"].get("ic", 0), reverse=True), 1):
|
||||
bt = s["real_backtest"]
|
||||
_log.info(f" #{i} {s['strategy_name']} IC={bt.get('ic',0):.4f} Sharpe={bt.get('sharpe',0):.3f} Monthly={bt.get('monthly_return_pct',0):.2f}%")
|
||||
|
||||
console.print(f"\n[bold green]✓ Generated {len(accepted)}/{target_count} accepted strategies[/bold green]\n")
|
||||
|
||||
if accepted:
|
||||
accepted.sort(key=lambda x: x['real_backtest'].get('ic', 0), reverse=True)
|
||||
accepted.sort(key=lambda x: x["real_backtest"].get("ic", 0), reverse=True)
|
||||
console.print("[bold]Results:[/bold]")
|
||||
for i, s in enumerate(accepted, 1):
|
||||
bt = s['real_backtest']
|
||||
bt = s["real_backtest"]
|
||||
console.print(f" {i}. {s['strategy_name']:30s} IC={bt.get('ic',0):.4f} Sharpe={bt.get('sharpe',0):.3f} "
|
||||
f"Monthly={bt.get('monthly_return_pct',0):.2f}% Trades={bt.get('n_trades',0)}")
|
||||
|
||||
if __name__ == '__main__':
|
||||
if __name__ == "__main__":
|
||||
count = int(sys.argv[1]) if len(sys.argv) > 1 else 10
|
||||
main(count)
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -41,7 +41,7 @@ OUTPUT_DIR = Path("results/realistic_backtest")
|
||||
PIP = 0.0001
|
||||
COST_ENTRY = 2.0 * PIP # spread + slippage
|
||||
COST_EXIT = 0.35 * PIP # commission
|
||||
RISK_PCT = 0.01 # 1% equity risk per trade
|
||||
RISK_PCT = 0.015 # 1.5% equity risk per trade
|
||||
STOP = 10 * PIP # 10-pip hard stop
|
||||
MAX_LEVERAGE = 30 # 1:30 max leverage (FTMO / EU standard)
|
||||
FTMO_MAX_DAILY = 0.05 # 5% max daily loss of initial balance
|
||||
@@ -268,7 +268,7 @@ def _worker(args: tuple) -> dict | None:
|
||||
|
||||
def main() -> None:
|
||||
parser = argparse.ArgumentParser(description="Realistic backtest of all strategies")
|
||||
parser.add_argument("--target-monthly", type=float, default=4.0,
|
||||
parser.add_argument("--target-monthly", type=float, default=15.0,
|
||||
help="Minimum OOS monthly return %% (default: 4.0)")
|
||||
parser.add_argument("--min-trades", type=int, default=30,
|
||||
help="Minimum OOS trades (default: 30)")
|
||||
|
||||
@@ -0,0 +1,127 @@
|
||||
"""Test daily resampling of factors for strategy signal generation.
|
||||
|
||||
Factor IC is measured at daily resolution. Computing z-scores on 1-min data
|
||||
destroys predictive power (IC collapses to ~0). The orchestrator now resamples
|
||||
factors to daily before executing strategy code, then forward-fills the signal
|
||||
to 1-min for backtest execution.
|
||||
"""
|
||||
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
import pytest
|
||||
|
||||
|
||||
class TestDailyResampling:
|
||||
"""Test that daily resampling preserves factor information."""
|
||||
|
||||
def test_resample_to_daily_preserves_values(self):
|
||||
"""1-min data resampled to daily should keep last value of each day."""
|
||||
idx = pd.date_range("2020-01-01", "2020-01-05 23:59", freq="1min")
|
||||
df = pd.DataFrame({"a": np.arange(len(idx), dtype=float)}, index=idx)
|
||||
|
||||
daily = df.resample("D").last().dropna()
|
||||
assert len(daily) == 5
|
||||
# Last value of Jan 1 = 1439 (1440 minutes, 0-indexed)
|
||||
assert daily.iloc[0].iloc[0] == pytest.approx(1439.0)
|
||||
|
||||
def test_daily_resampling_keeps_last_value(self):
|
||||
"""Daily resample('D').last() keeps the last valid value of each day."""
|
||||
idx = pd.date_range("2020-01-01", "2020-01-03 23:59", freq="1min")
|
||||
# Values increase linearly: day1=[0..1439], day2=[1440..2879], day3=[2880..4319]
|
||||
df = pd.DataFrame({"a": np.arange(len(idx), dtype=float)}, index=idx)
|
||||
|
||||
daily = df.resample("D").last().dropna()
|
||||
assert len(daily) == 3
|
||||
assert daily.iloc[0].iloc[0] == pytest.approx(1439.0) # Last value day 1
|
||||
assert daily.iloc[1].iloc[0] == pytest.approx(2879.0) # Last value day 2
|
||||
assert daily.iloc[2].iloc[0] == pytest.approx(4319.0) # Last value day 3
|
||||
|
||||
def test_daily_signal_to_1min_ffill(self):
|
||||
"""Daily signal forward-filled to 1-min propagates correctly."""
|
||||
daily_idx = pd.date_range("2020-01-01", periods=3, freq="D")
|
||||
daily_signal = pd.Series([1, -1, 0], index=daily_idx, name="signal")
|
||||
|
||||
idx_1min = pd.date_range("2020-01-01", "2020-01-03 23:59", freq="1min")
|
||||
signal_1min = daily_signal.reindex(idx_1min).ffill().fillna(0).astype(int).clip(-1, 1)
|
||||
|
||||
assert (signal_1min.loc["2020-01-01"] == 1).all()
|
||||
assert (signal_1min.loc["2020-01-02"] == -1).all()
|
||||
assert (signal_1min.loc["2020-01-03"] == 0).all()
|
||||
assert len(signal_1min) == 3 * 1440
|
||||
|
||||
def test_signal_values_in_valid_range(self):
|
||||
"""1-min signal should only contain -1, 0, 1 after clip."""
|
||||
daily_idx = pd.date_range("2020-01-01", periods=10, freq="D")
|
||||
daily_signal = pd.Series([2, -2, 0, 1, -1, 0, 5, -3, 0, 1], index=daily_idx)
|
||||
|
||||
idx_1min = pd.date_range("2020-01-01", "2020-01-10 23:59", freq="1min")
|
||||
signal_1min = daily_signal.reindex(idx_1min).ffill().fillna(0).astype(int).clip(-1, 1)
|
||||
|
||||
assert set(signal_1min.unique()) <= {-1, 0, 1}
|
||||
assert signal_1min.isna().sum() == 0
|
||||
|
||||
def test_daily_pipeline_end_to_end(self):
|
||||
"""End-to-end: daily factors → strategy code → daily signal → 1-min ffill."""
|
||||
rng = np.random.default_rng(42)
|
||||
n_days = 500
|
||||
|
||||
# Create daily factor with known IC
|
||||
daily_idx = pd.date_range("2020-01-01", periods=n_days, freq="D")
|
||||
daily_factor = pd.Series(rng.normal(0, 1, n_days), index=daily_idx)
|
||||
daily_fwd_ret = 0.15 * daily_factor + rng.normal(0, 0.1, n_days)
|
||||
daily_fwd_ret = pd.Series(daily_fwd_ret, index=daily_idx)
|
||||
|
||||
from scipy.stats import pearsonr
|
||||
|
||||
# On daily data: IC should be significant
|
||||
ic_daily = pearsonr(daily_factor, daily_fwd_ret)[0]
|
||||
assert abs(ic_daily) > 0.05, f"Daily IC too low: {ic_daily:.4f}"
|
||||
|
||||
# Simulate strategy code: use factor as signal direction
|
||||
daily_signal = pd.Series(0, index=daily_idx)
|
||||
daily_signal[daily_factor > 0.5] = 1
|
||||
daily_signal[daily_factor < -0.5] = -1
|
||||
|
||||
# Forward-fill to 1-min for backtest execution
|
||||
idx_1min = pd.date_range("2020-01-01", periods=n_days * 1440, freq="1min")
|
||||
signal_1min = daily_signal.reindex(idx_1min).ffill().fillna(0).astype(int).clip(-1, 1)
|
||||
|
||||
assert len(signal_1min) == n_days * 1440
|
||||
assert set(signal_1min.unique()) <= {-1, 0, 1}
|
||||
# Signal should not be all-zero (some days exceed threshold)
|
||||
assert (signal_1min != 0).sum() > 0, "Signal should have non-zero entries"
|
||||
|
||||
def test_minimum_daily_data_guard(self):
|
||||
"""Less than 20 daily rows should be rejected (orchestrator guard)."""
|
||||
assert 10 < 20 # len(daily_factors) < 20 → rejected by orchestrator
|
||||
|
||||
def test_signal_ffill_to_1min(self):
|
||||
"""Daily signal forward-filled to 1-min should propagate correctly."""
|
||||
daily_idx = pd.date_range("2020-01-01", periods=3, freq="D")
|
||||
daily_signal = pd.Series([1, -1, 0], index=daily_idx, name="signal")
|
||||
|
||||
idx_1min = pd.date_range("2020-01-01", "2020-01-03 23:59", freq="1min")
|
||||
signal_1min = daily_signal.reindex(idx_1min).ffill().fillna(0).astype(int).clip(-1, 1)
|
||||
|
||||
# Day 1: all 1
|
||||
assert (signal_1min.loc["2020-01-01"] == 1).all()
|
||||
# Day 2: all -1
|
||||
assert (signal_1min.loc["2020-01-02"] == -1).all()
|
||||
# Day 3: all 0
|
||||
assert (signal_1min.loc["2020-01-03"] == 0).all()
|
||||
assert len(signal_1min) == 3 * 1440
|
||||
|
||||
def test_signal_values_in_valid_range(self):
|
||||
"""Signal should only contain -1, 0, 1."""
|
||||
daily_idx = pd.date_range("2020-01-01", periods=10, freq="D")
|
||||
daily_signal = pd.Series([1, -1, 0, 1, -1, 0, 1, -1, 0, 1], index=daily_idx)
|
||||
|
||||
idx_1min = pd.date_range("2020-01-01", "2020-01-10 23:59", freq="1min")
|
||||
signal_1min = daily_signal.reindex(idx_1min).ffill().fillna(0).astype(int).clip(-1, 1)
|
||||
|
||||
assert set(signal_1min.unique()) <= {-1, 0, 1}
|
||||
assert signal_1min.isna().sum() == 0
|
||||
|
||||
def test_minimum_daily_data_rejected(self):
|
||||
"""Less than 20 daily rows should be rejected."""
|
||||
assert 10 < 20 # Orchestrator check: len(daily_factors) < 20 → rejected
|
||||
Reference in New Issue
Block a user