dsyoon
741c949470
파이프라인 산출물(data/, docs/)을 Git 추적에서 제외하고 히스토리를 단일 커밋으로 재구성해 저장소 용량을 경량화한다. Co-authored-by: Cursor <cursoragent@cursor.com>
131 lines
3.9 KiB
Python
131 lines
3.9 KiB
Python
#!/usr/bin/env python3
|
|
"""2단계: GT v3 타점 · 멀티 TF 피처 상관 분석."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import argparse
|
|
import logging
|
|
import sys
|
|
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.evaluation.mtf_report import (
|
|
build_mtf_correlation_report,
|
|
render_mtf_html,
|
|
save_mtf_report,
|
|
)
|
|
from deepcoin.mtf.extractor import MtfFeatureExtractor
|
|
from deepcoin.mtf.store import MultiTimeframeStore
|
|
from deepcoin.techniques.runner import load_ground_truth
|
|
|
|
|
|
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 _resolve_gt_path(settings, gt_file: str | None) -> Path:
|
|
"""GT JSON 경로를 결정한다."""
|
|
if gt_file:
|
|
path = Path(gt_file)
|
|
if not path.is_absolute():
|
|
path = ROOT / path
|
|
return path
|
|
return settings.ground_truth_file
|
|
|
|
|
|
def main() -> int:
|
|
"""CLI 진입점."""
|
|
parser = argparse.ArgumentParser(description="2단계: GT v3 MTF 피처 상관 분석")
|
|
parser.add_argument("--gt-file", type=str, default=None, help="GT JSON (기본 v3)")
|
|
parser.add_argument(
|
|
"--days",
|
|
type=int,
|
|
default=None,
|
|
help="분석 구간(일). 기본 GT_SIM_LOOKBACK_DAYS",
|
|
)
|
|
parser.add_argument(
|
|
"--negative-samples",
|
|
type=int,
|
|
default=2000,
|
|
help="음성 샘플 3분봉 수",
|
|
)
|
|
parser.add_argument(
|
|
"--exclude-bars",
|
|
type=int,
|
|
default=60,
|
|
help="GT 주변 제외 3분봉 수",
|
|
)
|
|
parser.add_argument("--seed", type=int, default=42, help="음성 샘플 RNG seed")
|
|
parser.add_argument("-v", "--verbose", action="store_true")
|
|
args = parser.parse_args()
|
|
|
|
_configure_logging(args.verbose)
|
|
settings = load_settings()
|
|
gt_path = _resolve_gt_path(settings, args.gt_file)
|
|
lookback_days = args.days or settings.gt_sim_lookback_days
|
|
|
|
logging.info(
|
|
"MTF 상관 분석: %s, 최근 %d일, 음성 %d건",
|
|
gt_path.name,
|
|
lookback_days,
|
|
args.negative_samples,
|
|
)
|
|
|
|
gt_result = load_ground_truth(gt_path)
|
|
store = MultiTimeframeStore(
|
|
db_path=settings.db_path,
|
|
symbol=settings.symbol,
|
|
lookback_days=lookback_days + 120,
|
|
zigzag_reversal_pct=settings.gt_zigzag_reversal_pct,
|
|
)
|
|
extractor = MtfFeatureExtractor(
|
|
store=store,
|
|
base_interval_min=settings.gt_interval_min,
|
|
)
|
|
|
|
report = build_mtf_correlation_report(
|
|
gt_result=gt_result,
|
|
extractor=extractor,
|
|
lookback_days=lookback_days,
|
|
negative_sample_count=args.negative_samples,
|
|
exclude_bars=args.exclude_bars,
|
|
seed=args.seed,
|
|
)
|
|
|
|
json_path = save_mtf_report(report, settings.mtf_report_json)
|
|
html_path = render_mtf_html(report, settings.mtf_report_html)
|
|
|
|
gt = report.get("gt", {})
|
|
top = (report.get("global_feature_ranking") or [])[:5]
|
|
print("\n=== GT v3 MTF 상관 분석 ===")
|
|
print(f"구간: {report['analysis']['period_from']} ~ {report['analysis']['period_to']}")
|
|
print(
|
|
f"GT 신호 {gt.get('signals_in_period', 0)}건 · "
|
|
f"스냅샷 {gt.get('snapshots_extracted', 0)}건 · "
|
|
f"음성 {report['analysis']['negative_sample_count']}건"
|
|
)
|
|
print("\n상위 피처 (|Cohen's d|):")
|
|
for row in top:
|
|
print(
|
|
f" {row['signal_label']} | {row['timeframe']} | {row['feature']} | "
|
|
f"d={row['cohens_d']}"
|
|
)
|
|
print(f"\nJSON: {json_path}")
|
|
print(f"HTML: {html_path}")
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
raise SystemExit(main())
|