feat(question_gen): load_benchmark — benchmark JSON 加载
从 JSON 目录 glob *.json 加载题目,stem 作 video_id。 legacy schema 无 difficulty 字段时赋 _LEGACY_DEFAULT_DIFFICULTY 常量。 options/source_nodes 转 tuple 配合 frozen dataclass。 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -0,0 +1,50 @@
|
||||
"""题目加载与分层采样。
|
||||
|
||||
从 benchmark JSON 目录加载题目,提供按对错比例的分层采样。
|
||||
对应训练循环中的 DataLoader 角色。
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
from core.types import GeneratedQuestion
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from pathlib import Path
|
||||
|
||||
_LEGACY_DEFAULT_DIFFICULTY = "medium"
|
||||
|
||||
|
||||
def load_benchmark(questions_dir: Path) -> list[GeneratedQuestion]:
|
||||
"""从 benchmark JSON 目录加载题目列表。
|
||||
|
||||
每个 JSON 文件以文件名(不含扩展名)作为 video_id,
|
||||
文件内容为题目数组。
|
||||
|
||||
参数:
|
||||
questions_dir: 包含 *.json 文件的目录路径。
|
||||
|
||||
返回:
|
||||
按文件名排序加载的题目列表。
|
||||
"""
|
||||
results: list[GeneratedQuestion] = []
|
||||
for path in sorted(questions_dir.glob("*.json")):
|
||||
video_id = path.stem
|
||||
with open(path, encoding="utf-8") as f:
|
||||
qa_list: list[dict] = json.load(f)
|
||||
for qa in qa_list:
|
||||
results.append(
|
||||
GeneratedQuestion(
|
||||
question_id=qa["question_id"],
|
||||
video_id=video_id,
|
||||
task_type=qa["task_type"],
|
||||
question=qa["question"],
|
||||
options=tuple(qa["options"]),
|
||||
answer=qa["answer"],
|
||||
source_nodes=tuple(qa.get("source_nodes", ())),
|
||||
difficulty=qa.get("difficulty", _LEGACY_DEFAULT_DIFFICULTY),
|
||||
)
|
||||
)
|
||||
return results
|
||||
Reference in New Issue
Block a user