Towards the end of the first day of the hackathon, Spencer and I realized all of our efforts so far had gone towards examining and manipulating the wrong dataset. After this setback, we refocused and developed a plan for the second day (Saturday). Starting Saturday morning, I wrote a Python script that takes as input the (correct) raw data set, and outputs a more usable and easily analyzed data set in the same style as Rafa had showed us. Spencer contributed on the data cleaning side, as well as valuable communication on the Slack channel and github.
Log in or sign up for Devpost to join the conversation.