{"schema_version":"1.0","language":"zh-CN","generated_from":"NEWVAR 从零开始学AI structured Markdown","write_access":false,"full_text_access":false,"content_boundary":"This endpoint exposes metadata, objectives, prerequisites, labs and source summaries. It does not expose chapter body text or answer text.","chapter":{"slug":"data-lifecycle","title":"数据生命周期：采集、清洗、字典与许可","english_title":"Data lifecycle","chapter_number":10,"volume":1,"volume_title":"第一卷：计算与数学地基","month":3,"unit_title":"Git、数据、SQL与可复现性","review_status":"draft","updated_at":"2026-08-06","estimated_hours":8,"focus":"从问题定义到删除策略管理数据，记录来源、字段含义、许可、缺失与偏差。","objectives":["从问题定义到删除策略管理数据，记录来源、字段含义、许可、缺失与偏差。","解释核心数学关系并完成最小实现","运行单变量实验并记录失败样例","完成工程线或研究线至少一项迁移任务"],"prerequisites":["git-and-cli"],"exercise_count":3,"tracks":["engineering","research"],"human_url":"/learn/data-lifecycle"},"labs":[{"id":"lab-data-lifecycle","chapter_slug":"data-lifecycle","title":"数据生命周期：采集、清洗、字典与许可：单变量实验","kind":"missing_rate","data_status":"教学模拟","variable":{"label":"缺失比例","unit":"%","min":0,"max":80,"step":5,"default":10},"objective":"只改变“缺失比例”，观察结果、代价和风险如何一起变化，理解从问题定义到删除策略管理数据，记录来源、字段含义、许可、缺失与偏差。","static_fallback":"静态替代：把缺失比例分别设为0%、10%和80%，手工比较三组教学模拟输出。","keyboard":"聚焦滑块后使用方向键微调，Page Up/Page Down大步调整，Home/End到达边界。","measurement_note":"页面数值由公开公式生成，只用于教学，不代表真实模型性能或现实世界因果效果。","source_ids":["S007","S008","S020","S072","S080"]}],"project":{"id":"project-03","month":3,"title":"建立一个可复现的公开数据小仓库","brief":"保存数据字典、清洗脚本、SQL查询、环境说明、随机种子和实验日志，不保存个人信息。","deliverables":["问题与边界说明","可运行最小实现","实验记录与失败分析","来源与许可清单","风险、隐私与人工闸门","复现README"]},"sources":[{"id":"S007","author":"Scott Chacon, Ben Straub","title":"Pro Git","source_level":"官方托管开放教材","published_at":"持续更新","accessed_at":"2026-08-06","doi_or_url":"https://git-scm.com/book/en/v2"},{"id":"S008","author":"SQLite Project","title":"SQLite Documentation","source_level":"官方文档","published_at":"持续更新","accessed_at":"2026-08-06","doi_or_url":"https://www.sqlite.org/docs.html"},{"id":"S020","author":"scikit-learn developers","title":"scikit-learn User Guide","source_level":"官方文档","published_at":"持续更新","accessed_at":"2026-08-06","doi_or_url":"https://scikit-learn.org/stable/user_guide.html"},{"id":"S072","author":"Timnit Gebru et al.","title":"Datasheets for Datasets","source_level":"同行评审论文预印本","published_at":"2018","accessed_at":"2026-08-06","doi_or_url":"https://arxiv.org/abs/1803.09010"},{"id":"S080","author":"ACM","title":"Artifact Review and Badging","source_level":"专业学会复现规范","published_at":"持续更新","accessed_at":"2026-08-06","doi_or_url":"https://www.acm.org/publications/policies/artifact-review-and-badging-current"}]}