Urban Traffic Speed Dataset of Guangzhou, China

This is an urban traffic speed dataset which consists of 214 anonymous road segments (mainly consist of urban expressways and arterials) within two months (i.e., 61 days from August 1, 2016 to September 30, 2016) at 10-minute interval, and the speed observations were collected in Guangzhou, China. In practice, it can be used to conduct missing data imputation, short-term traffic prediction, and traffic pattern discovery experiments.

According to the spatial and temporal attributes, we can easily derive a third-order tensor as \(\mathcal{X}\in\mathbb{R}^{214\times 61\times 144}\) and its dimensions include road segment, day and time window (see the file tensor.mat). The total number of speed observations (or non-zero entries of the tensor \(\mathcal{X}\)) is \(1,855,589\). If the dataset is complete, then we have \(214\times 61\times 144=1,879,776\) observations, therefore, the original missing rate of this dataset is \(1.29\%\).

Note that the file traffic_speed_data.csv is the original traffic speed data with four columns including road segment attribute, day attribute, time window attribute, and traffic speed value. The file day_information_table.csv is a table referring to the specific date, and the file time_information_table.csv is a table expressing time window with start time and end time information.

Feel free to email me with any questions: [e-mail] (author: Xinyu Chen).

Acknowledgement: Mr. Weiwei Sun (affiliated with Sun Yat-Sen University) also provided insightful suggestion and help for publishing this data set. Thank you!

本数据集为城市交通速度数据集，涵盖中国广州市2016年8月1日至2016年9月30日（共61天）内的214条匿名道路路段（以城市快速路与主干道为主）的交通速度观测数据，采样间隔为10分钟。实际应用中，该数据集可用于缺失数据补全、短期交通预测以及交通模式发现等实验研究。

基于时空属性，可便捷构造三阶张量(mathcal{X}inmathbb{R}^{214 imes 61 imes 144})，其维度分别对应道路路段、日期与时间窗口（详见tensor.mat文件）。该张量的非零元素（即有效速度观测值）总数为1,855,589。若数据集完整，理论总观测数应为(214 imes 61 imes 144=1,879,776)，因此本数据集的原始缺失率为1.29%。

需注意，traffic_speed_data.csv为原始交通速度数据文件，共包含四列字段：道路路段属性、日期属性、时间窗口属性以及交通速度值。day_information_table.csv为具体日期信息表，time_information_table.csv为包含起始时间与结束时间的时间窗口信息表。

如有任何疑问，请致信作者陈新宇：[e-mail]。

致谢：中山大学孙巍巍先生为本数据集的发布提供了富有启发性的建议与协助，特此致谢！