feat(insta-lab): keyword_extractor.extract_with_weights for category proportions

This commit is contained in:
2026-05-16 17:51:16 +09:00
parent bd1773e29e
commit 6bb5c2fb40
2 changed files with 90 additions and 0 deletions

View File

@@ -81,3 +81,22 @@ def extract_for_category(category: str, limit: int = KEYWORDS_PER_CATEGORY) -> L
})
saved.append({"id": kid, **kw, "category": category})
return saved
def extract_with_weights(weights: Dict[str, float], total_limit: int) -> List[Dict[str, Any]]:
"""카테고리 가중치 비율대로 키워드를 분배 추출."""
from .config import DEFAULT_CATEGORY_SEEDS
if not weights or sum(weights.values()) == 0:
cats = list(DEFAULT_CATEGORY_SEEDS.keys())
weights = {c: 1.0 for c in cats}
total_weight = sum(weights.values())
out: List[Dict[str, Any]] = []
for category, w in weights.items():
if w <= 0:
continue
per_cat = round(total_limit * w / total_weight)
if per_cat <= 0:
continue
out.extend(extract_for_category(category, limit=per_cat))
return out