Agent/examples_how/overall_derivation/pattern_data_process.py

#!/usr/bin/env python3
"""
pattern 数据精简：5 种 depth 合并为一份，按 items 去重；
pattern 仅保留 s/l/i，i 为去重后字符串 "A+B+C"，单行 JSON。
"""
import json
from pathlib import Path

INPUT_FILE = (
    Path(__file__).resolve().parent / "input/家有大志/原始数据/pattern/processed_edge_data.json"
)
OUTPUT_DIR = Path(__file__).resolve().parent / "input/家有大志/pattern"
OUTPUT_FILE = OUTPUT_DIR / "processed_edge_data.json"

TOP_KEYS = [
    "depth_max_with_name",
    "depth_mixed",
    "depth_max_concrete",
    "depth2_medium",
    "depth1_abstract",
]
SUB_KEYS = ["two_x", "one_x", "zero_x"]


def slim_pattern(p):
    """提取 name 列表，去重保序，返回 (support, length, items_key)。"""
    names = [item["name"] for item in (p.get("items") or [])]
    # 内部去重，保序
    seen = set()
    unique = []
    for n in names:
        if n not in seen:
            seen.add(n)
            unique.append(n)
    support = round(float(p["support"]), 4)
    length = p["length"]
    return support, length, unique


def to_short_entry(support, length, names):
    """短格式：无 id，s/l/i，i 为 'A+B+C'。"""
    return {"s": support, "l": length, "i": "+".join(names)}


def merge_and_dedupe(patterns):
    """按 items 的 name 集合去重（不区分顺序），留 support 最大；再按 s*l 降序；输出短格式。"""
    key_to_best = {}
    for p in patterns:
        support, length, unique = slim_pattern(p)
        key = tuple(sorted(unique))  # 同名字集合、顺序不同算同一条
        if key not in key_to_best or support > key_to_best[key][0]:
            key_to_best[key] = (support, length)
    out = [to_short_entry(s, l, list(k)) for k, (s, l) in key_to_best.items() if s >= 0.1]
    out.sort(key=lambda x: x["s"] * x["l"], reverse=True)
    return out


def main():
    with open(INPUT_FILE, "r", encoding="utf-8") as f:
        data = json.load(f)

    all_patterns = []
    for top in TOP_KEYS:
        if top not in data:
            continue
        block = data[top]
        for sub in SUB_KEYS:
            all_patterns.extend(block.get(sub) or [])

    result = merge_and_dedupe(all_patterns)
    result.sort(key=lambda x: x["s"], reverse=True)
    result = result[:500]

    OUTPUT_DIR.mkdir(parents=True, exist_ok=True)
    with open(OUTPUT_FILE, "w", encoding="utf-8") as f:
        json.dump(result, f, ensure_ascii=False, indent=None, separators=(",", ":"))
        f.write("\n")

    print(f"已输出: {OUTPUT_FILE} (共 {len(result)} 条 pattern)")


if __name__ == "__main__":
    main()