shuim/auto-stock
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

백테스트 수정중

Browse Source
This commit is contained in:
shuim
2026-03-07 13:16:01 +09:00
parent ea355eb60c
commit 7c9b596098
13 changed files with 908 additions and 303 deletions
Download Patch File Download Diff File Expand all files Collapse all files

290
backend/app/api/endpoints/backtest.py
View File

@@ -27,10 +27,57 @@ from app.services.backtest_engine import (
from app.services.stock_universe import StockUniverse, StockFilter
from app.services.ml_ensemble import get_ensemble
from app.services.feature_engineering import FEATURE_COLUMNS
from app.services.strategy_config_service import strategy_cfg
router = APIRouter()
logger = logging.getLogger(__name__)
# ── 전략 프리셋 정의 (모듈 레벨) ───────────────────────────────────────────────
_STRATEGY_PRESETS: Dict[str, Dict[str, Any]] = {
"conservative": {
"name": "보수적",
"params": {
"MEAN_REVERSION_STOP_LOSS_PCT": -5.0,
"MEAN_REVERSION_TAKE_PROFIT_PCT": 8.0,
"MAX_TOTAL_POSITIONS": 3,
"MEAN_REVERSION_RSI_THRESHOLD": 25,
},
},
"balanced": {
"name": "균형형",
"params": {
"MEAN_REVERSION_STOP_LOSS_PCT": -6.0,
"MEAN_REVERSION_TAKE_PROFIT_PCT": 12.0,
"MAX_TOTAL_POSITIONS": 5,
"MEAN_REVERSION_RSI_THRESHOLD": 30,
},
},
"aggressive": {
"name": "공격적",
"params": {
"MEAN_REVERSION_STOP_LOSS_PCT": -8.0,
"MEAN_REVERSION_TAKE_PROFIT_PCT": 20.0,
"MAX_TOTAL_POSITIONS": 8,
"MEAN_REVERSION_RSI_THRESHOLD": 35,
},
},
}
async def _get_preset(preset_key: str) -> Optional[Dict[str, Any]]:
"""프리셋 이름으로 파라미터 반환. 'current'이면 DB 현재 설정 로드."""
if preset_key == "current":
await strategy_cfg._refresh()
params = {
"MEAN_REVERSION_STOP_LOSS_PCT": strategy_cfg.get("STOP_LOSS_PERCENT", -6.0),
"MEAN_REVERSION_TAKE_PROFIT_PCT": strategy_cfg.get("TAKE_PROFIT_PERCENT", 12.0),
"MAX_TOTAL_POSITIONS": strategy_cfg.get("MAX_HOLDINGS_COUNT", 5),
"MEAN_REVERSION_RSI_THRESHOLD": strategy_cfg.get("MEAN_REVERSION_RSI_THRESHOLD", 30.0),
}
return {"name": "현재 설정", "params": params}
return _STRATEGY_PRESETS.get(preset_key)
# 전역 변수: 생성된 학습 데이터 임시 저장
_cached_training_data: Optional[Dict[str, Any]] = None
@@ -65,6 +112,14 @@ class ComparePresetsRequest(BaseModel):
presets: List[str] = Field(["conservative", "balanced", "aggressive"], description="비교할 프리셋 목록")
class ComparePresetsUniverseRequest(BaseModel):
universe_preset: str = Field("large_cap", description="유니버스 프리셋")
start_date: str
end_date: str
initial_capital: float = 10_000_000
presets: List[str] = Field(["conservative", "balanced", "aggressive"], description="비교할 프리셋 목록")
class RunUniverseBacktestRequest(BaseModel):
"""전체 종목 백테스트 요청"""
universe_preset: str = Field("large_cap", description="유니버스 프리셋 (large_cap, kospi_all, ...)")
@@ -76,6 +131,17 @@ class RunUniverseBacktestRequest(BaseModel):
top_n_results: int = Field(20, description="성과 상위 N개만 반환")
class GenerateTrainingDataUniverseRequest(BaseModel):
"""전체 종목 ML 학습 데이터 생성 요청"""
universe_preset: str = Field("large_cap", description="유니버스 프리셋")
start_date: str = Field(..., description="시작일 (YYYY-MM-DD)")
end_date: str = Field(..., description="종료일 (YYYY-MM-DD)")
forward_days: int = Field(5, description="N일 후 수익률로 라벨링")
up_threshold: float = Field(0.03, description="UP 레이블 임계값")
down_threshold: float = Field(-0.03, description="DOWN 레이블 임계값")
min_samples_per_stock: int = Field(50, description="종목당 최소 샘플 수")
# ── API 엔드포인트 ─────────────────────────────────────────────────────
@router.get("/universe-presets")
@@ -129,31 +195,13 @@ async def api_run_universe_backtest(req: RunUniverseBacktestRequest) -> Dict[str
logger.info(f"전체 백테스트 시작: {len(stock_codes)}종목")
# 2. 전략 파라미터
PRESETS = {
"conservative": {
"MEAN_REVERSION_STOP_LOSS_PCT": -5.0,
"MEAN_REVERSION_TAKE_PROFIT_PCT": 8.0,
"MAX_TOTAL_POSITIONS": 3,
"MEAN_REVERSION_RSI_THRESHOLD": 25,
},
"balanced": {
"MEAN_REVERSION_STOP_LOSS_PCT": -6.0,
"MEAN_REVERSION_TAKE_PROFIT_PCT": 12.0,
"MAX_TOTAL_POSITIONS": 5,
"MEAN_REVERSION_RSI_THRESHOLD": 30,
},
"aggressive": {
"MEAN_REVERSION_STOP_LOSS_PCT": -8.0,
"MEAN_REVERSION_TAKE_PROFIT_PCT": 20.0,
"MAX_TOTAL_POSITIONS": 8,
"MEAN_REVERSION_RSI_THRESHOLD": 35,
},
}
strategy_params = PRESETS.get(req.strategy_preset, PRESETS["balanced"])
# 2. 전략 파라미터 ('current'이면 DB에서 로드)
preset = await _get_preset(req.strategy_preset) or await _get_preset("balanced")
strategy_params = preset["params"]
# 3. 각 종목별로 백테스트 (병렬)
no_data_count = 0
async def backtest_single(code: str) -> Optional[Dict[str, Any]]:
try:
config = BacktestConfig(
@@ -167,7 +215,11 @@ async def api_run_universe_backtest(req: RunUniverseBacktestRequest) -> Dict[str
)
engine = BacktestEngine()
result = await engine.run_backtest(config)
# DB에 해당 종목/기간 데이터 없으면 제외
if not result.equity_curve:
return None
return {
"stock_code": code,
"total_return_pct": result.total_return_pct,
@@ -179,15 +231,17 @@ async def api_run_universe_backtest(req: RunUniverseBacktestRequest) -> Dict[str
except Exception as e:
logger.error(f"{code} 백테스트 실패: {e}")
return None
# 병렬 실행 (10개씩 배치)
results = []
batch_size = 10
for i in range(0, len(stock_codes), batch_size):
batch = stock_codes[i:i + batch_size]
batch_results = await asyncio.gather(*[backtest_single(code) for code in batch])
results.extend([r for r in batch_results if r is not None])
logger.info(f"진행률: {len(results)}/{len(stock_codes)}")
valid = [r for r in batch_results if r is not None]
no_data_count += len(batch) - len(valid)
results.extend(valid)
logger.info(f"진행률: {len(results)}/{len(stock_codes)} (데이터없음: {no_data_count})")
# 4. 수익률 상위 N개 정렬
results_sorted = sorted(results, key=lambda x: x["total_return_pct"], reverse=True)
@@ -197,6 +251,7 @@ async def api_run_universe_backtest(req: RunUniverseBacktestRequest) -> Dict[str
return {
"total_tested": len(results),
"no_data_count": no_data_count,
"top_performers": top_results,
"universe_preset": req.universe_preset,
"strategy_preset": req.strategy_preset,
@@ -205,6 +260,61 @@ async def api_run_universe_backtest(req: RunUniverseBacktestRequest) -> Dict[str
}
@router.post("/generate-training-data-universe")
async def api_generate_training_data_universe(req: GenerateTrainingDataUniverseRequest) -> Dict[str, Any]:
"""
전체 종목 ML 학습 데이터 생성 (유니버스 프리셋 기반)
유니버스에 속한 모든 종목의 과거 데이터를 병렬로 수집하여 학습 데이터를 생성합니다.
"""
global _cached_training_data
try:
start_date = datetime.strptime(req.start_date, "%Y-%m-%d").date()
end_date = datetime.strptime(req.end_date, "%Y-%m-%d").date()
except ValueError:
raise HTTPException(status_code=400, detail="날짜 형식 오류 (YYYY-MM-DD)")
# 유니버스 프리셋에서 종목 리스트
presets = StockUniverse.get_preset_universes()
if req.universe_preset not in presets:
raise HTTPException(status_code=400, detail=f"잘못된 유니버스 프리셋: {req.universe_preset}")
stock_filter = presets[req.universe_preset]["filter"]
stock_codes = await StockUniverse.get_filtered_stocks(stock_filter)
if not stock_codes:
raise HTTPException(status_code=404, detail="해당 유니버스에 종목이 없습니다")
logger.info(f"전체 종목 학습 데이터 생성 시작: {len(stock_codes)}종목")
config = TrainingDataConfig(
stock_codes=stock_codes,
start_date=start_date,
end_date=end_date,
forward_days=req.forward_days,
up_threshold=req.up_threshold,
down_threshold=req.down_threshold,
min_samples_per_stock=req.min_samples_per_stock,
)
result = await generate_training_data(config)
if "error" in result:
raise HTTPException(status_code=500, detail=result["error"])
_cached_training_data = result
return {
"total_samples": result["total_samples"],
"label_distribution": result["label_distribution"],
"config": result["config"],
"universe_preset": req.universe_preset,
"total_stocks_requested": len(stock_codes),
"message": f"{len(stock_codes)}종목에서 {result['total_samples']}개 샘플 생성 완료. /train-model로 학습하거나 /download-training-data로 다운로드하세요.",
}
@router.post("/generate-training-data")
async def api_generate_training_data(req: GenerateTrainingDataRequest) -> Dict[str, Any]:
"""
@@ -308,28 +418,35 @@ async def api_train_model(background_tasks: BackgroundTasks) -> Dict[str, Any]:
async def api_run_backtest(req: RunBacktestRequest) -> Dict[str, Any]:
"""
전략 성과 백테스트 실행
과거 데이터로 전략을 실행하여 수익률, MDD, 승률 등을 계산합니다.
strategy_params가 없으면 전략 설정 페이지의 현재 DB 값을 자동 사용합니다.
"""
try:
start_date = datetime.strptime(req.start_date, "%Y-%m-%d").date()
end_date = datetime.strptime(req.end_date, "%Y-%m-%d").date()
except ValueError:
raise HTTPException(status_code=400, detail="날짜 형식 오류")
# strategy_params 없으면 DB 현재 설정 자동 로드
strategy_params = req.strategy_params
if strategy_params is None:
preset = await _get_preset("current")
strategy_params = preset["params"]
logger.info(f"strategy_params 미지정 → DB 현재 설정 사용: {strategy_params}")
config = BacktestConfig(
stock_codes=req.stock_codes,
start_date=start_date,
end_date=end_date,
initial_capital=req.initial_capital,
strategy_params=req.strategy_params,
strategy_params=strategy_params,
max_positions=req.max_positions,
position_size=req.position_size,
)
engine = BacktestEngine()
result = await engine.run_backtest(config)
# BacktestResult를 dict로 변환
from dataclasses import asdict
return asdict(result)
@@ -348,44 +465,13 @@ async def api_compare_presets(req: ComparePresetsRequest) -> Dict[str, Any]:
except ValueError:
raise HTTPException(status_code=400, detail="날짜 형식 오류")
# 프리셋 정의 (frontend/src/utils/strategyPresets.ts와 동기화)
PRESETS = {
"conservative": {
"name": "보수적",
"params": {
"MEAN_REVERSION_STOP_LOSS_PCT": -5.0,
"MEAN_REVERSION_TAKE_PROFIT_PCT": 8.0,
"MAX_TOTAL_POSITIONS": 3,
"MEAN_REVERSION_RSI_THRESHOLD": 25,
}
},
"balanced": {
"name": "균형형",
"params": {
"MEAN_REVERSION_STOP_LOSS_PCT": -6.0,
"MEAN_REVERSION_TAKE_PROFIT_PCT": 12.0,
"MAX_TOTAL_POSITIONS": 5,
"MEAN_REVERSION_RSI_THRESHOLD": 30,
}
},
"aggressive": {
"name": "공격적",
"params": {
"MEAN_REVERSION_STOP_LOSS_PCT": -8.0,
"MEAN_REVERSION_TAKE_PROFIT_PCT": 20.0,
"MAX_TOTAL_POSITIONS": 8,
"MEAN_REVERSION_RSI_THRESHOLD": 35,
}
},
}
results = {}
for preset_key in req.presets:
if preset_key not in PRESETS:
preset = await _get_preset(preset_key)
if preset is None:
continue
preset = PRESETS[preset_key]
config = BacktestConfig(
stock_codes=req.stock_codes,
start_date=start_date,
@@ -394,10 +480,10 @@ async def api_compare_presets(req: ComparePresetsRequest) -> Dict[str, Any]:
strategy_params=preset["params"],
max_positions=preset["params"]["MAX_TOTAL_POSITIONS"],
)
engine = BacktestEngine()
result = await engine.run_backtest(config)
results[preset_key] = {
"name": preset["name"],
"total_return_pct": result.total_return_pct,
@@ -407,9 +493,71 @@ async def api_compare_presets(req: ComparePresetsRequest) -> Dict[str, Any]:
"total_trades": result.total_trades,
"equity_curve": result.equity_curve,
}
return {
"presets": results,
"period": f"{req.start_date} ~ {req.end_date}",
"stock_count": len(req.stock_codes),
}
@router.post("/compare-presets-universe")
async def api_compare_presets_universe(req: ComparePresetsUniverseRequest) -> Dict[str, Any]:
"""
프리셋 비교 백테스트 (유니버스 프리셋 기반)
선택한 유니버스의 모든 종목을 대상으로 보수적/균형형/공격적 프리셋을 비교합니다.
"""
try:
start_date = datetime.strptime(req.start_date, "%Y-%m-%d").date()
end_date = datetime.strptime(req.end_date, "%Y-%m-%d").date()
except ValueError:
raise HTTPException(status_code=400, detail="날짜 형식 오류")
presets_map = StockUniverse.get_preset_universes()
if req.universe_preset not in presets_map:
raise HTTPException(status_code=400, detail=f"잘못된 유니버스 프리셋: {req.universe_preset}")
stock_filter = presets_map[req.universe_preset]["filter"]
stock_codes = await StockUniverse.get_filtered_stocks(stock_filter)
if not stock_codes:
raise HTTPException(status_code=404, detail="해당 유니버스에 종목이 없습니다")
logger.info(f"유니버스 프리셋 비교 시작: {req.universe_preset} ({len(stock_codes)}종목)")
results = {}
for preset_key in req.presets:
preset = await _get_preset(preset_key)
if preset is None:
continue
config = BacktestConfig(
stock_codes=stock_codes,
start_date=start_date,
end_date=end_date,
initial_capital=req.initial_capital,
strategy_params=preset["params"],
max_positions=preset["params"]["MAX_TOTAL_POSITIONS"],
)
engine = BacktestEngine()
result = await engine.run_backtest(config)
results[preset_key] = {
"name": preset["name"],
"total_return_pct": result.total_return_pct,
"mdd_pct": result.mdd_pct,
"win_rate": result.win_rate,
"sharpe_ratio": result.sharpe_ratio,
"total_trades": result.total_trades,
"equity_curve": result.equity_curve,
}
return {
"presets": results,
"period": f"{req.start_date} ~ {req.end_date}",
"stock_count": len(stock_codes),
"universe_preset": req.universe_preset,
}