壁紙アプリの30カテゴリ分類で、エージェントに選ばせる範囲をどこまで狭めるか

{
  "task": "classify_wallpaper_observation",
  "id": 210756,
  "allowed_tags": [
    "night", "city", "skyline", "street",
    "mountain", "sea", "sky", "forest",
    "flower", "petal", "cat", "dog", "bird",
    "gradient", "geometric", "texture"
  ],
  "rules": [
    "allowed_tags 以外の語を出力しない",
    "確信が持てないタグは付けない",
    "1枚あたり最大5タグ"
  ],
  "output": { "id": 210756, "tags": ["night", "forest"] }
}

#!/usr/bin/env python3
"""tags.jsonl -> カテゴリ別 ID リスト（決定的な写像）"""
import json, sys
from pathlib import Path
 
CATEGORY_ORDER = ["人気", "風景", "夜景", "花", "動物", "抽象"]
 
RULES = [
    ("夜景", {"all": ["night"], "any": ["city", "skyline", "street"]}),
    ("風景", {"any": ["mountain", "sea", "sky", "forest"]}),
    ("花",   {"any": ["flower", "petal"]}),
    ("動物", {"any": ["cat", "dog", "bird"]}),
    ("抽象", {"any": ["gradient", "geometric", "texture"],
              "none": ["cat", "dog", "bird"]}),
    ("人気", {"any": ["featured"]}),
]
 
VOCAB = {t for _, r in RULES for k in ("all", "any", "none") for t in r.get(k, [])}
 
 
def match(rule, tags):
    if any(t not in tags for t in rule.get("all", [])):
        return False
    if rule.get("any") and not any(t in tags for t in rule["any"]):
        return False
    if any(t in tags for t in rule.get("none", [])):
        return False
    return True
 
 
def main(path):
    buckets = {c: [] for c in CATEGORY_ORDER}
    unknown, unassigned = {}, []
    for line in Path(path).read_text(encoding="utf-8").splitlines():
        if not line.strip():
            continue
        rec = json.loads(line)
        wid, tags = str(rec["id"]), set(rec["tags"])
        for t in tags - VOCAB:                 # 語彙外は捨てずに数える
            unknown[t] = unknown.get(t, 0) + 1
        hit = [c for c, r in RULES if match(r, tags)]
        if not hit:
            unassigned.append(wid)             # 穴を明示的に残す
        for c in hit:
            buckets[c].append(wid)
    for c in CATEGORY_ORDER:                   # 出力順はテンプレート固定
        print(f"{c}: " + ", ".join(buckets[c]))
    print(f"[unassigned] {len(unassigned)} -> {unassigned}", file=sys.stderr)
    print(f"[unknown-tags] {sorted(unknown.items())}", file=sys.stderr)
 
 
if __name__ == "__main__":
    main(sys.argv[1])

CATEGORY_ORDER = ["人気", "風景", "夜景", "夜の自然", "花", "動物", "抽象"]
 
RULES = [
    ("夜景",     {"all": ["night"], "any": ["city", "skyline", "street"]}),
    ("夜の自然", {"all": ["night"], "any": ["forest", "mountain", "sea"]}),
    ("風景",     {"any": ["mountain", "sea", "sky", "forest"],
                  "none": ["night"]}),
    # 以下は変更なし
]

#!/usr/bin/env python3
"""新旧の写像結果を比べ、所属が変わったIDだけを出す"""
import subprocess, sys, collections
 
def load(script, data):
    out = subprocess.run([sys.executable, script, data],
                         capture_output=True, text=True).stdout
    m = collections.defaultdict(set)
    for line in out.splitlines():
        cat, _, ids = line.partition(":")
        for i in ids.split(","):
            if i.strip():
                m[i.strip()].add(cat.strip())
    return m
 
old, new = load(sys.argv[1], sys.argv[3]), load(sys.argv[2], sys.argv[3])
moved = 0
for wid in sorted(set(old) | set(new)):
    a, b = old.get(wid, set()), new.get(wid, set())
    if a != b:
        moved += 1
        print(f"{wid}: {sorted(a) or ['-']} -> {sorted(b) or ['-']}")
print(f"moved={moved} / total={len(set(old) | set(new))}")

{
  "last_updated": "2026-08-15T10:00:00",
  "total_images": 748,
  "last_processed_id": 211700,
  "skipped_ids": [211042, 211043],
  "current_batch": 19,
  "last_output_file": "category_list_562.txt",
  "status": "in_progress"
}