Code is published on my github.Previously, I did some analysis on car2go's location data to find the most popular roads in Austin. But we can do much more. One question I have is: if car2go wants to replace the entire Austin fleet with electric vehicles, where should ... [Read more...]

​IntroductionImage classification is one important field in Computer Vision, not only because so many applications are associated with it, but also a lot of Computer Vision problems can be effectively reduced to image classification. The state of art tool in image classification is Convolutional Neural Network (CNN). In this article, ... [Read more...]

IntroductionShiny app is a new way to present data interactively. Unlike methods like D3, shiny performs complex calculation in real time. As a result, shiny app is more powerful and versatile. However, this also means one cannot simply embed an interactive shiny app in an html document. It needs to ... [Read more...]

It is hard to convincingly evaluate a player's contribution to team offense, given so many factors involved, both objective and subjective. I took a shot at this problem by analyzing what kind of shot a player takes and how's that compared with league average. The result, as we shall see ... [Read more...]

​Previously, I plotted all the routes during a 24 hr span by Car2go customers in Austin. While it shows each individual route and its origin and destination, many of them were covered by the last plotted route if they share the same road. As a result, the plot does not ... [Read more...]

Total Quarterback Rating (Total QBR) is a measure for QB performance created by ESPN in 2011. It was intended to overcome obivous drawbacks of passer rating, which is purely based on passing stats. Total QBR evaluates each play and assigns a value according to many factors (like outcome of the play) ... [Read more...]

Part 1 demonstrates how to grab the location data of the cars (and other status, like fuel, cleaness etc.) at a given time from Car2go API. However, in order to show how did the car moved over an extended period, we need to do a timed loop to grab the ... [Read more...]

After I published an article on how to scrape advanced shooting data from stat.nba.com, a friend of mine contact me to see whether I may be able to scrape some data from zipcar or car2go’s API. So I looked into it and found it is quite ... [Read more...]

Ever since NBA introduced advanced data to track player on-court movement, there have been a lot of interesting blogs/news articles to show how data could improve the understanding (or destroy your intuition) of the game. Reading them is a lot of fun. Here is one example. The newly introduce ... [Read more...]