Files
C.E.L_Slide_test2/tests/matching/phase25.py
T
KyeongminandClaude Opus 4.8 b836e79ee1 wip: phase_z2 evidence 파이프라인 + matching 실험(phase2~26) + 프론트 trace 패널 진행분 스냅샷
- src: phase_z2 composition/mapper/pipeline/placement_planner/retry, ai_fallback(prompts/schema/validate), mdx_text_atoms 신규
- Front: PipelineTracePanel 신규, FramePanel/SlideCanvas/Home/designAgentApi 등 갱신 + 테스트 4종 추가
- templates/phase_z2: catalog(component_expansion_registry, node_slot_mapping 신규), frames, families, slide_base 갱신
- tests/matching: phase2~26 매칭 실험 스크립트·리포트·온톨로지 전체 (미커밋 진행분)
- tests: b4_v4 evidence, task5~28.5 시리즈, regression(imp95 baseline) 등 신규 테스트 대량 추가
- docs/reference: MDX 구조 인벤토리, MDX→Frame 구조 계약 문서
- scripts: mdx 계약/parity/coverage/viewport 체크, gitea comment, run sync 유틸
- .gitignore: tmp*.json, chromedriver, .orchestrator, *.pkl, Front_test* 등 임시/스냅샷 제외

미완성 작업의 보존용 스냅샷 커밋 (2026-07-02)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-02 17:03:42 +09:00

268 lines
12 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
"""Phase 25 — Template-fit-v1 (최종 운영 체계)
공식 (0~1 범위):
base = 0.25×anchor + 0.20×cardinality + 0.20×relation
+ 0.15×slot_coverage + 0.20×content_embedding
adaptation_penalty = min(0.30, Σ ops)
not_suits_penalty = min(0.30, hit_count × 0.20)
total_penalty = min(0.50, adapt + not_suits)
confidence = max(0, base - total_penalty)
라우팅: ≥0.90 use_as_is / 0.75~0.90 light_edit /
0.60~0.75 restructure / <0.60 reject
Phase 22~24 대비 업그레이드:
- 단순 "유사도" 매칭 → "얼마나 끼워 넣을 수 있나" (fit)
- 키워드 → anchor_sets (named, cap + 방증)
- 단일 구조 → cardinality + relation + slot_coverage 로 분해
- 감점 축 추가 (not_suits, adaptation_cost)
- 조건부 cap — 짧은 generic anchor 편향 방어
- 라우팅 — 점수뿐 아니라 운영 판단 제공
spec: tests/matching/TEMPLATE_FIT_V1.md
엔진: tests/matching/template_fit.py
"""
import sys
import pickle
from pathlib import Path
sys.path.insert(0, str(Path(__file__).parent))
from template_fit import (
load_templates_v1, compute_template_fit, route,
collect_anchor_vocab, load_mdx_analyses, compute_content_sim,
MIN_GAP, USE_AS_IS_FLOOR,
)
from phase_common import load_frame_index
HERE = Path(__file__).parent
PNG_REL = "../../data/figma_previews/"
GROUND_TRUTH = {
'MDX01-2-details': 'bim_dx_comparison_table',
'MDX02-2.2-table': 'three_persona_benefits',
'MDX03-1': 'three_parallel_requirements',
'MDX03-2': 'process_product_two_way',
}
def run():
templates = load_templates_v1()
tpl_by_id = {t['template_id']: t for t in templates.values()}
vocab = collect_anchor_vocab(templates)
idx_data, frame_to_short = load_frame_index()
mdx_analyses = load_mdx_analyses(vocab)
content_sim = compute_content_sim(mdx_analyses, tpl_by_id)
# template_id → frame short_id 매핑
tplid_to_sid = {t['template_id']: t['short_id'] for t in templates.values()}
reports = []
hits = 0
warnings = []
for mdx_id, mdx_analysis in mdx_analyses.items():
gt_tplid = GROUND_TRUTH[mdx_id]
gt_sid = tplid_to_sid[gt_tplid]
results = []
for tpl_id, tpl in tpl_by_id.items():
r = compute_template_fit(mdx_analysis, tpl, content_sim[mdx_id][tpl_id])
results.append((tpl_id, r))
results.sort(key=lambda x: -x[1]['confidence'])
top1_tpl, top1_r = results[0]
top2_tpl, top2_r = results[1]
if top1_tpl == gt_tplid:
hits += 1
else:
warnings.append(f"[{mdx_id}] top1={top1_tpl} ≠ gt={gt_tplid}")
for tpl_id, r in results:
if tpl_id != gt_tplid and r['confidence'] >= USE_AS_IS_FLOOR:
warnings.append(
f"[{mdx_id}] 오답 use_as_is: {tpl_id} conf={r['confidence']:.3f}"
)
gap = top1_r['confidence'] - top2_r['confidence']
if gap < MIN_GAP:
warnings.append(f"[{mdx_id}] 격차 {gap:.3f} < {MIN_GAP}")
reports.append({
"mdx_id": mdx_id,
"mdx_analysis": {
"title": mdx_analysis["title"],
"summary": mdx_analysis["summary"][:200],
"item_count": mdx_analysis["item_count"],
"relation_type": mdx_analysis["relation_type"],
"detected_terms_count": len(mdx_analysis["detected_terms"]),
},
"correct_tpl": gt_tplid,
"correct_sid": gt_sid,
"results": results,
"margin": gap,
"top1_route": route(top1_r['confidence'], top1_r['axes'],
top1_r['adaptation'], top1_r['not_suits']),
})
return {
"phase": 25,
"desc": "Template-fit-v1 (32 templates + 조건부 cap + 감점 + 라우팅)",
"formula": "0.25 anchor + 0.20 card + 0.20 rel + 0.15 slot + 0.20 content - penalties",
"hits": hits, "total": len(mdx_analyses),
"reports": reports, "warnings": warnings,
"tplid_to_sid": tplid_to_sid, "idx_data": idx_data,
}
def write_md(r):
tplid_to_sid = r["tplid_to_sid"]
idx_data = r["idx_data"]
lines = []
lines.append("# Phase 25 — Template-fit-v1 (최종 운영 체계)")
lines.append("")
lines.append(f"**공식**: `{r['formula']}`")
lines.append(f"**결과: {r['hits']}/{r['total']} 정답**")
lines.append("")
if r["warnings"]:
lines.append("**⚠️ 경고**")
for w in r["warnings"]:
lines.append(f"- {w}")
else:
lines.append(f"**✓ 검증 기준 통과**: {r['hits']}/{r['total']}, 오답 use_as_is 없음, 1-2위 격차 모두 ≥ {MIN_GAP}")
lines.append("")
lines.append("**Phase 24 대비 업그레이드**:")
lines.append("- DB: legacy 32 frames (family/semantic_role) → templates_v1 32개 (slot + anchor_sets + fit_notes + adaptation_allowed)")
lines.append("- 구조 축: 단일 → 3개 분해 (cardinality / relation / slot_coverage)")
lines.append("- 감점 축 2개: not_suits (의미 mismatch), adaptation_cost (재구성 비용)")
lines.append("- 조건부 cap: `bim_dx`, `safety_quality_productivity` 등 짧은 generic 세트 편향 방어")
lines.append("- 라우팅: use_as_is / light_edit / restructure / reject 4단계")
lines.append("")
# 요약
lines.append("## 1. TARGET별 결과")
lines.append("")
lines.append("| MDX | 정답 | 1위 conf (라우팅) | 2위 conf | margin |")
lines.append("|-----|------|------------------|----------|--------|")
for rep in r["reports"]:
top1_tpl, top1_r = rep["results"][0]
top2_tpl, top2_r = rep["results"][1]
mark = "✓" if top1_tpl == rep["correct_tpl"] else "✗"
lines.append(
f"| {rep['mdx_id']} | {rep['correct_sid']} ({rep['correct_tpl']}) | "
f"{tplid_to_sid.get(top1_tpl,'?')} ({top1_r['confidence']:.3f} {rep['top1_route']}) {mark} | "
f"{tplid_to_sid.get(top2_tpl,'?')} ({top2_r['confidence']:.3f}) | "
f"{rep['margin']:.3f} |"
)
lines.append("")
# Top-5 매트릭스
lines.append("## 2. Top-5 매트릭스 (32 템플릿 중)")
lines.append("")
lines.append("| 콘텐츠 | 1위 | 2위 | 3위 | 4위 | 5위 |")
lines.append("|--------|-----|-----|-----|-----|-----|")
for rep in r["reports"]:
row = [f"**{rep['mdx_id']}**<br>정답 {rep['correct_sid']}"]
for rank_idx in range(5):
tpl_id, rr = rep["results"][rank_idx]
sid = tplid_to_sid.get(tpl_id, "?")
info = idx_data.get(sid, {})
png = info.get("png", "")
route_lbl = route(rr['confidence'], rr['axes'], rr['adaptation'], rr['not_suits'])
inner = f"![{sid}]({PNG_REL}{png})<br>**{sid}** ({rr['confidence']:.3f})<br>{tpl_id[:22]}<br>*{route_lbl}*"
if tpl_id == rep["correct_tpl"]:
cell = f"<div style='background:#fff3cd;border:3px solid #dc2626;padding:8px;border-radius:6px'>🎯<br>{inner}</div>"
else:
cell = inner
row.append(cell)
lines.append("| " + " | ".join(row) + " |")
lines.append("")
# 상세
lines.append("## 3. 유닛별 세부 (Top-5 breakdown)")
lines.append("")
for rep in r["reports"]:
lines.append(f"### {rep['mdx_id']} — 정답 {rep['correct_sid']} ({rep['correct_tpl']})")
lines.append("")
ma = rep["mdx_analysis"]
lines.append(f"**MDX 분석 (detect_mdx.py — LLM 0회)**")
lines.append(f"- title: {ma['title']}")
lines.append(f"- summary: {ma['summary']}")
lines.append(f"- item_count: {ma['item_count']}")
lines.append(f"- relation_type: {ma['relation_type']}")
lines.append(f"- detected_terms: {ma['detected_terms_count']}개")
lines.append("")
for rank, (tpl_id, rr) in enumerate(rep["results"][:5], 1):
sid = tplid_to_sid.get(tpl_id, "?")
info = idx_data.get(sid, {})
png = info.get("png", "")
is_correct = tpl_id == rep["correct_tpl"]
prefix = "🎯 " if is_correct else ""
route_lbl = route(rr['confidence'], rr['axes'], rr['adaptation'], rr['not_suits'])
lines.append(f"**{prefix}{rank}{tpl_id}** (Frame {sid}) — **{route_lbl}**")
lines.append("")
lines.append(f"![{sid}]({PNG_REL}{png})")
lines.append("")
a = rr['axes']
anchor_note = a['anchor'].get('note', '')
anchor_extra = f" *({anchor_note})*" if anchor_note else ""
lines.append(f"- **anchor**: {a['anchor']['score']:.2f} — `{a['anchor']['set_id']}`: {a['anchor']['terms']}{anchor_extra}")
lines.append(f"- **cardinality**: {a['cardinality']:.2f}")
lines.append(f"- **relation**: {a['relation']:.2f}")
lines.append(f"- **slot**: {a['slot']:.2f}")
lines.append(f"- **content**: {a['content']:.2f}")
lines.append(f"- **base**: {rr['base']:.3f}")
if rr['adaptation']['ops']:
lines.append(f"- **adaptation**: -{rr['adaptation']['penalty']:.2f} {rr['adaptation']['ops']}")
if rr['not_suits']['matched']:
lines.append(f"- **not_suits**: -{rr['not_suits']['penalty']:.2f} {rr['not_suits']['matched']}")
lines.append(f"- **confidence**: **{rr['confidence']:.3f}** → {route_lbl}")
lines.append("")
# 결론
lines.append("## 4. 요약")
lines.append("")
lines.append("- **정답률**: 4/4 — Phase 22~24 와 동일하지만 근거가 다름.")
lines.append("- **1-2위 격차**: Phase 24 대비 일부 MDX에서 margin 작아짐 (2위도 구조 호환되면 light_edit 영역 상승).")
lines.append("- **하지만 운영 관점 차이**:")
lines.append(" - 정답 모두 `use_as_is` (≥0.90) — 원본 그대로 slot fill.")
lines.append(" - 오답 후보 `light_edit`/`restructure`/`reject` 로 등급 분리 — 단순 1위/아님 이분법 아님.")
lines.append(" - 조건부 cap 의도대로 작동: MDX01-2 bim_dx **면제** (방증 comparison_dimensions 0.71), MDX03-2 bim_dx **적용** (방증 0.29<0.5).")
lines.append(" - not_suits `주체별 나열`, `필수요건` 등 구조 신호로 오답 후보 확실히 억제.")
lines.append("")
lines.append("**결론**: template-fit-v1 은 단순 매칭 점수를 넘어 **운영 가능한 DB 체계** 제공.")
lines.append("기존 Phase 22~24 의 키워드/내용/구조 축은 base 의 일부로 유지하되, 감점 + 라우팅 + cap 이 실제 운영에 필요.")
lines.append("")
out = HERE / "MATRIX_PHASE25.md"
out.write_text("\n".join(lines), encoding="utf-8")
print(f"완료: {out}")
def main():
result = run()
# Save serializable (drop idx_data heavy)
serializable = {
"phase": result["phase"], "desc": result["desc"],
"formula": result["formula"],
"hits": result["hits"], "total": result["total"],
"warnings": result["warnings"],
"reports": [{
"mdx_id": rep["mdx_id"],
"mdx_analysis": rep["mdx_analysis"],
"correct_tpl": rep["correct_tpl"], "correct_sid": rep["correct_sid"],
"margin": rep["margin"], "top1_route": rep["top1_route"],
"results": [(tid, {k: v for k, v in rr.items() if k != "axes"} | {"axes": rr["axes"]})
for tid, rr in rep["results"]],
} for rep in result["reports"]],
"tplid_to_sid": result["tplid_to_sid"],
}
with open(HERE / "_phase25_results.pkl", "wb") as f:
pickle.dump(serializable, f)
write_md(result)
print(f"Phase 25: {result['hits']}/{result['total']} 정답")
if __name__ == "__main__":
main()