Deutsche Bahn (DB) delays

The data was collected using the Timetables and StaDa API from the DB API marketplace during a graduation project from a data scientist bootcamp.
It consists of hourly snapshots of planned train arrivals and departures, as well as any known changes (delays) to them with geolocation, station name, line name, as well as a list of all previous stations passed before the current stop.
Only Trainstops of category 1-5 were taken into account (main junctions to small train stations), roughly 2000 around Germany.
The data was taken 2 minutes after every full hour within a timeframe of exactly 1 week (7 days) from 08.07.2024 00:00 to 14.07.2024 23:59.

Thanks to deutsche Bahn for providing access to the data.

API Marketplace: [https://developers.deutschebahn.com/db-api-marketplace/apis/](https://developers.deutschebahn.com/db-api-marketplace/apis/)
Original Repo with additional older data, EDA and TSA, as well as the scripts used to collect the data: [https://github.com/Nokkyuu/Fantastic_trains_and_when_to_find_them](https://github.com/Nokkyuu/Fantastic_trains_and_when_to_find_them)

该数据集系采用德铁（deutsche Bahn）提供的Timetables和StaDa API，在数据科学家培训营的毕业项目中从DB API市场采集而成。数据集包含预定列车到站与发车的每小时快照，以及相关变更（如延误）信息，并附带地理定位、车站名称、线路名称，以及当前站点之前所有经过站点的列表。数据采集范围仅限于类别1-5的Trainstops（从主要枢纽站至小型火车站），大约涵盖德国境内2000个站点。数据采集时间点为每个整点后2分钟，持续时长为一周（7天），具体时间为2024年7月8日00:00至2024年7月14日23:59。感谢德铁为数据访问提供支持。

API市场：[https://developers.deutschebahn.com/db-api-marketplace/apis/](https://developers.deutschebahn.com/db-api-marketplace/apis/)
原始数据仓库，包含额外旧数据、数据探索与可视化分析（EDA）以及数据采集脚本：[https://github.com/Nokkyuu/Fantastic_trains_and_when_to_find_them](https://github.com/Nokkyuu/Fantastic_trains_and_when_to_find_them)