This is the source code for a Microsoft Data Science Summer School 2014 project that looks at load imbalance in the CitiBike system.

1. download_trips.sh: grabs historical trip data from CitiBike's site to local csv files

2. filter_availability.py: filters historical station availability to 15 minute intervals

3. clean_data.R: loads and parses historical trip data, station capacity, and station availability and saves results as RData file, clean_citibike.RData

4. simulation.py: runs simulations of system status without van transports, using either original rider routes ('rider' argument) or greedily re-routed trips ('greedy' argument)

5. clean_sim_data.R: loads simulation results and saves results as RData file, simulation.RData

6. analysis.R: generates all results and plots

The code was written by:

• Briana Vecchione (Pace University)
• Franky Rodriguez (St. Joseph's College)
• Donald Hanson (Adelphi University)
• Jahaziel Guzman (Brooklyn College)

Students were mentored by Sharad Goel, Jake Hofman, Justin Rao, and Hanna Wallach.