Understanding human mobility patterns is important in applications as diverse as urban planning, public health, and political organizing. One rich source of data on human mobility is taxi ride data. Using the city of Chicago as a case study, we examine data from taxi rides in 2016 with the goal of understanding how neighborhoods are interconnected. This analysis will provide a sense of which neighborhoods individuals are using taxis to travel between, suggesting regions to focus new public transit development efforts. Additionally, this analysis will map traffic circulation patterns and provide an understanding of where in the city people are traveling from and where they are heading to - perhaps informing traffic or road pollution mitigation efforts. For the first application, representing the data as an undirected graph will suffice. Transit lines run in both directions so simply a knowledge of which neighborhoods have high rates of taxi travel between them provides an argument for placing public transit along those routes. However, in order to understand the flow of people throughout a city, we must make a distinction between the neighborhood from which people are departing and the areas to which they are arriving - this requires methods that can deal with directed graphs. All developed codes can be found at https://github.com/Nikunj-Gupta/Spectral-Clustering-Directed-Graphs.

翻译：理解人类流动模式在城市规划、公共卫生和政治组织等多种应用中具有重要意义。出租车出行数据是研究人类流动性的丰富数据源之一。本研究以芝加哥市为例，通过分析2016年出租车出行数据，旨在理解各社区之间的互联关系。该分析将揭示个体使用出租车往返于哪些社区之间，从而为公共交通新线路的开发提供重点区域参考。此外，该分析还将绘制交通流量模式图，呈现城市中人们的出发地与目的地分布——这或许能为交通或道路污染缓解措施提供依据。对于第一个应用场景，将数据表示为无向图即可满足需求。由于公交线路双向运行，仅需掌握哪些社区间出租车出行频率较高，即可建议在这些路线上设置公共交通。然而，为理解城市中的人流方向，我们必须区分人们的出发社区与到达区域——这需要能够处理有向图的方法。所有开发的代码可访问https://github.com/Nikunj-Gupta/Spectral-Clustering-Directed-Graphs。