파이프라인 산출물(data/, docs/)을 Git 추적에서 제외하고 히스토리를 단일 커밋으로 재구성해 저장소 용량을 경량화한다. Co-authored-by: Cursor <cursoragent@cursor.com>
170 lines
5.6 KiB
Python
170 lines
5.6 KiB
Python
#!/usr/bin/env python3
|
|
"""2단계: 인과 기법 sim + 차트 (1단계와 동일 거래 기간·초기 자본)."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import argparse
|
|
import logging
|
|
import sys
|
|
import time
|
|
from pathlib import Path
|
|
|
|
ROOT = Path(__file__).resolve().parents[1]
|
|
SRC = ROOT / "src"
|
|
if str(SRC) not in sys.path:
|
|
sys.path.insert(0, str(SRC))
|
|
|
|
from deepcoin.config import load_settings
|
|
from deepcoin.data.candle_loader import load_candles
|
|
from deepcoin.data.intervals import interval_label
|
|
from deepcoin.evaluation.causal_sim import (
|
|
build_causal_sim_report,
|
|
render_causal_sim_html,
|
|
render_technique_sim_chart,
|
|
run_technique_causal_sim,
|
|
save_causal_sim_report,
|
|
technique_sim_chart_path,
|
|
)
|
|
from deepcoin.techniques.runner import load_ground_truth, load_technique_results
|
|
|
|
|
|
def _configure_logging(verbose: bool) -> None:
|
|
"""로깅 레벨을 설정한다."""
|
|
level = logging.DEBUG if verbose else logging.INFO
|
|
logging.basicConfig(
|
|
level=level,
|
|
format="%(asctime)s [%(levelname)s] %(message)s",
|
|
datefmt="%Y-%m-%d %H:%M:%S",
|
|
)
|
|
|
|
|
|
def _print_progress(phase: str, current: int, total: int, detail: str) -> None:
|
|
"""진행률을 stdout에 출력한다."""
|
|
pct = current / total * 100.0 if total else 100.0
|
|
msg = f"[{phase}] {current}/{total} ({pct:.1f}%) — {detail}"
|
|
print(msg, flush=True)
|
|
logging.info(msg)
|
|
|
|
|
|
def main() -> int:
|
|
"""CLI 진입점."""
|
|
parser = argparse.ArgumentParser(description="2단계: 인과 기법 sim + 차트")
|
|
parser.add_argument(
|
|
"--techniques",
|
|
type=str,
|
|
default=None,
|
|
help="대상 기법 ID (쉼표 구분). 기본: 전체",
|
|
)
|
|
parser.add_argument(
|
|
"--no-charts",
|
|
action="store_true",
|
|
help="개별 sim 차트 HTML 생략 (요약 리포트만)",
|
|
)
|
|
parser.add_argument("-v", "--verbose", action="store_true")
|
|
args = parser.parse_args()
|
|
|
|
_configure_logging(args.verbose)
|
|
settings = load_settings()
|
|
gt_result = load_ground_truth(settings.ground_truth_file)
|
|
gt_meta = gt_result.get("meta", {})
|
|
|
|
technique_ids = None
|
|
if args.techniques:
|
|
technique_ids = [t.strip() for t in args.techniques.split(",") if t.strip()]
|
|
|
|
results = load_technique_results(settings.techniques_dir, technique_ids)
|
|
if not results:
|
|
logging.error(
|
|
"기법 결과 없음: %s — 먼저 2_run_techniques.py 실행",
|
|
settings.techniques_dir,
|
|
)
|
|
return 1
|
|
|
|
stage1_sim = gt_result.get("sim_pnl")
|
|
if not stage1_sim:
|
|
logging.warning("GT JSON에 1단계 sim_pnl 없음 — 1_ground_truth_sim.py 권장")
|
|
|
|
df = load_candles(
|
|
db_path=settings.db_path,
|
|
symbol=settings.symbol,
|
|
interval_min=settings.gt_interval_min,
|
|
lookback_days=settings.gt_lookback_days,
|
|
)
|
|
last_close = float(df["close"].iloc[-1])
|
|
data_end = gt_meta.get("data_to")
|
|
analysis_dir = settings.causal_sim_report_json.parent
|
|
|
|
print("\n=== 2단계 인과 sim ===", flush=True)
|
|
print(
|
|
f"거래 기간: 최근 {settings.gt_sim_lookback_days}일 | "
|
|
f"초기 {settings.gt_initial_cash_krw:,.0f}원 | "
|
|
f"기법 {len(results)}개",
|
|
flush=True,
|
|
)
|
|
|
|
sim_pnls: dict[str, dict] = {}
|
|
total = len(results)
|
|
t0 = time.monotonic()
|
|
|
|
for idx, result in enumerate(results, start=1):
|
|
sim_pnl = run_technique_causal_sim(
|
|
result,
|
|
initial_cash_krw=settings.gt_initial_cash_krw,
|
|
fee_rate=settings.gt_trading_fee_rate,
|
|
sim_lookback_days=settings.gt_sim_lookback_days,
|
|
data_end=data_end,
|
|
last_mark_price=last_close,
|
|
)
|
|
sim_pnls[result.technique_id] = sim_pnl
|
|
_print_progress(
|
|
"sim",
|
|
idx,
|
|
total,
|
|
f"{result.technique_id} → {sim_pnl.get('total_return_pct', 0):+.2f}%",
|
|
)
|
|
|
|
if not args.no_charts:
|
|
chart_path = technique_sim_chart_path(analysis_dir, result.technique_id)
|
|
render_technique_sim_chart(
|
|
db_path=settings.db_path,
|
|
symbol=settings.symbol,
|
|
gt_meta=gt_meta,
|
|
result=result,
|
|
sim_pnl=sim_pnl,
|
|
output_path=chart_path,
|
|
chart_lookback_days=settings.gt_sim_lookback_days,
|
|
)
|
|
_print_progress("chart", idx, total, str(chart_path.name))
|
|
|
|
report = build_causal_sim_report(results, gt_result, settings.symbol, sim_pnls)
|
|
report["meta"] = {
|
|
"interval_label": interval_label(settings.gt_interval_min),
|
|
"initial_cash_krw": settings.gt_initial_cash_krw,
|
|
"sim_lookback_days": settings.gt_sim_lookback_days,
|
|
}
|
|
json_path = save_causal_sim_report(report, settings.causal_sim_report_json)
|
|
html_path = render_causal_sim_html(report, settings.causal_sim_report_html)
|
|
|
|
elapsed = time.monotonic() - t0
|
|
print(f"\n=== 2단계 인과 sim 완료 ({elapsed/60:.1f}분) ===", flush=True)
|
|
if stage1_sim:
|
|
print(
|
|
f"1단계 벤치마크(v3): {stage1_sim.get('total_return_pct', 0):+.2f}% "
|
|
f"({stage1_sim.get('period_from', '')} ~ {stage1_sim.get('period_to', '')})",
|
|
flush=True,
|
|
)
|
|
top = report["ranking"][:3]
|
|
for i, row in enumerate(top, start=1):
|
|
print(
|
|
f" {i}. {row['technique_name']}: {row['sim_return_pct']:+.2f}% "
|
|
f"(GT정합 {row['gt_align_score']*100:.1f})",
|
|
flush=True,
|
|
)
|
|
print(f"요약 JSON: {json_path}", flush=True)
|
|
print(f"요약 HTML: {html_path}", flush=True)
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
raise SystemExit(main())
|