For this project, the group created a website that shows the team-control Approximate Value generated by each team’s draft class and the individual picks made that year. We also used Random Forest Regression to predict the Approximate Value for individual players in the draft using a combination of combine results and college football statistics.
In this project, we used the Lahman Database and the Google Maps API to determine where most MLB players come from and to see if some areas are better at developing certain types of players.
The purpose of this project was to focus on the ETL process. We extracted streaming network data from Kaggle and transformed the data set into individual movie, director and actor tables. We then entered those tables into a database, so that people could perform SQL queries to get the results they desire.