C.E.L_Slide_test2/tests/matching/phase3.py

"""Phase 3: 9개 방법 × 17 유닛 매트릭스 (의미 매칭 5개 family 비교)
- 키워드 (3): TF-IDF, Char n-gram, Kiwi+BM25
- 구조 (1): 구조 메타데이터
- 의미 (5): SBERT / KoSimCSE / E5 / Cross-encoder / Word-avg
"""
import sys
import json
from pathlib import Path

sys.path.insert(0, str(Path(__file__).parent))

from common import load_figma_texts
from extract_units import extract_units
from methods import (
    method_tfidf, method_char_ngram, method_kiwi_bm25,
    method_structural,
    method_sbert_sentence,
    method_kosimcse, method_e5, method_cross_encoder, method_wordavg,
)

ROOT = Path(r"d:\ad-hoc\kei\design_agent")
PREVIEW_DIR = ROOT / "data" / "figma_previews"

UNIT_ORDER = [
    ("MDX01-intro", "중목차 앞 본문"),
    ("MDX01-intro-details", "팝업"),
    ("MDX01-1", "중목차"),
    ("MDX01-2", "중목차"),
    ("MDX01-2-image", "이미지"),
    ("MDX01-2-details", "팝업+표"),
    ("MDX02-1", "중목차"),
    ("MDX02-1-image", "이미지"),
    ("MDX02-2", "중목차(컨테이너)"),
    ("MDX02-2.1", "소목차"),
    ("MDX02-2.2", "소목차"),
    ("MDX02-2.2-table", "표"),
    ("MDX03-1", "중목차"),
    ("MDX03-2", "중목차(컨테이너)"),
    ("MDX03-2.1", "소목차"),
    ("MDX03-2.1-table", "표"),
    ("MDX03-2.2", "소목차"),
]


def fmt_score(score, method_name):
    # 모두 [0,1] 범위이므로 % 표기
    return f"{score * 100:.0f}%"


def main():
    units = extract_units()
    figma = load_figma_texts()

    with open(PREVIEW_DIR / "index.json", encoding="utf-8") as f:
        idx_data = json.load(f)
    frame_to_short = {info["frame_id"]: sid for sid, info in idx_data.items()}

    methods_def = [
        ("TF-IDF", method_tfidf),
        ("Char-ngram", method_char_ngram),
        ("Kiwi+BM25", method_kiwi_bm25),
        ("Structural", method_structural),
        ("SBERT", method_sbert_sentence),
        ("KoSimCSE", method_kosimcse),
        ("E5", method_e5),
        ("Cross-encoder", method_cross_encoder),
        ("Word-avg", method_wordavg),
    ]

    print("[Phase 3] 9개 방법 × 17 유닛 실행 시작...")
    results = {}
    for i, (uid, unit_text) in enumerate(units.items(), 1):
        print(f"  [{i}/{len(units)}] {uid}")
        results[uid] = {}
        for mname, fn in methods_def:
            if not unit_text.strip():
                results[uid][mname] = []
                continue
            try:
                ranked = fn(unit_text, figma)
                results[uid][mname] = ranked[:3]
            except Exception as e:
                print(f"    ERROR {mname}: {e}")
                results[uid][mname] = []

    # 리포트
    png_rel = "../../data/figma_previews/"
    lines = []
    lines.append("# Phase 3 — 9개 방법 매트릭스 (의미 매칭 5개 family 비교)")
    lines.append("")
    lines.append("3 카테고리: **키워드 (3) + 구조 (1) + 의미 (5 family)**")
    lines.append("")
    lines.append("### 의미 매칭 5 family")
    lines.append("- **SBERT** (jhgan/ko-sroberta-multitask) — NLI+STS 학습, 한국어 기본")
    lines.append("- **KoSimCSE** (BM-K/KoSimCSE-roberta-multitask) — 대조학습 기반 sentence embedding")
    lines.append("- **E5** (intfloat/multilingual-e5-base) — 다국어 retrieval, query/passage 비대칭 prefix")
    lines.append("- **Cross-encoder** (Dongjin-kr/ko-reranker) — 임베딩 X, 질의-문서 쌍 직접 채점")
    lines.append("- **Word-avg** — 단어 임베딩 평균 (FastText 계열 baseline)")
    lines.append("")

    for i, (uid, kind) in enumerate(UNIT_ORDER, 1):
        lines.append(f"---")
        lines.append("")
        lines.append(f"## {i}. {uid} ({kind})")
        lines.append("")
        lines.append("| 방법 | 1순위 | 2순위 | 3순위 |")
        lines.append("|------|-------|-------|-------|")
        for mname, _ in methods_def:
            cells = [mname]
            top3 = results[uid].get(mname, [])
            if not top3:
                cells += ["-", "-", "-"]
            else:
                for fid, score in top3:
                    short = frame_to_short.get(str(fid), "?")
                    info = idx_data.get(short, {})
                    png_file = info.get("png", "")
                    title = info.get("title_text", "").strip().replace("\n", " ") or ""
                    if len(title) > 15:
                        title = title[:15] + "…"
                    cell = f"![{short}]({png_rel}{png_file})<br>**{short}** ({fmt_score(score, mname)})<br>{title}"
                    cells.append(cell)
                while len(cells) < 4:
                    cells.append("-")
            lines.append("| " + " | ".join(cells) + " |")
        lines.append("")

    out_path = Path(__file__).parent / "MATRIX_PHASE3.md"
    out_path.write_text("\n".join(lines), encoding="utf-8")
    print(f"\n완료: {out_path}")


if __name__ == "__main__":
    main()