feat(data): parse 3-agency PDF transition matrices to CSV #task-290

- New: data/parse_pdf_matrices.py (KR/NICE/SCI PDF parser)
  - KR: text-based parser (space-separated numbers + dashes)
  - NICE: text-based parser (clean numeric format)
  - SCI: pdfplumber table extraction (column-position-aware)
  - WR redistribution, B이하→B mapping, CCC extrapolation from PD patterns
- Modified: data/transition_matrices.py (added source='real' loader)
- Modified: config.yaml (data.transition_source: 'real')
- Modified: main.py (reads transition source from config)
- Output: 112 CSV files (KR/NICE/SCI/AVG × 28 years)
This commit is contained in:
Variet Agent
2026-03-11 01:07:27 +09:00
parent ebdc6b805b
commit 8af743e6f3
116 changed files with 1714 additions and 3 deletions

View File

@@ -15,6 +15,11 @@ ecos:
cpi: "901Y009" # 소비자물가지수 / ITEM: 0 (총지수, level→YoY% 변환)
composite_leading: "901Y067" # 경기종합지수 / ITEM: I16A (선행, 월별→연평균)
# 전이행렬 데이터 소스
data:
transition_source: "real" # "real" (3사 실제) | "builtin" (내장 샘플)
transition_dir: null # null이면 기본 data/real/
# 모형 파라미터
model:
# 자산상관계수 (Basel IRB 기준 0.12~0.24, 기업 평균 ~0.20)