Real world data is messy. Most classes present students with data that has been cleaned up for ‘instructional purposes’, readily available and subset to small, easy-to-work-with sizes. This leaves many students of data science or computer science rather ill-prepared in encountering real-world data, as the very first steps required before they can apply all their knowledge of processing, modeling and visualizing are precisely the steps we didn’t teach. In this course, we work with real-world data.