feat(spot): 2단계 인과 기법 분석 파이프라인 마무리

common/spot/futures 경로 정비, 캔들 데이터 모듈 복원, MTF 규칙 자동 저장 및 2단계 설계·최종 정리 문서를 반영해 3단계 착수 기반을 확정한다.

Co-authored-by: Cursor <cursoragent@cursor.com>

scripts/2_run_causal_sim.py

@@ -18,7 +18,10 @@ 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 (
+    best_technique_chart_path,
     build_causal_sim_report,
+    pick_best_technique_row,
+    render_best_technique_comparison_chart,
     render_causal_sim_html,
     render_technique_sim_chart,
     run_technique_causal_sim,
@@ -145,6 +148,30 @@ def main() -> int:
     json_path = save_causal_sim_report(report, settings.causal_sim_report_json)
     html_path = render_causal_sim_html(report, settings.causal_sim_report_html)
 
+    best_row = pick_best_technique_row(report)
+    if best_row:
+        best_result = next(
+            (r for r in results if r.technique_id == best_row["technique_id"]),
+            None,
+        )
+        if best_result is not None:
+            best_chart = best_technique_chart_path(analysis_dir)
+            render_best_technique_comparison_chart(
+                db_path=settings.db_path,
+                symbol=settings.symbol,
+                gt_result=gt_result,
+                result=best_result,
+                sim_pnl=sim_pnls[best_result.technique_id],
+                output_path=best_chart,
+                chart_lookback_days=settings.download_days,
+            )
+            print(
+                f"1단계 v3 대조 차트: {best_chart} "
+                f"({best_result.technique_name}, "
+                f"{sim_pnls[best_result.technique_id].get('total_return_pct', 0):+.2f}%)",
+                flush=True,
+            )
+
     elapsed = time.monotonic() - t0
     print(f"\n=== 2단계 인과 sim 완료 ({elapsed/60:.1f}분) ===", flush=True)
     if stage1_sim: