Inspired by the ever-expanding Uber and Lyft services, we were prompted to analyze their effects on traffic congestion. Though initially such services were advertised to reduce the number of cars on the road, the reality may be different altogether. Firstly, the idling and mindless driving of such vehicles, especially in urban areas, creates additional road discomfort. Secondly, such services reduce the number of passengers utilizing public transport. Thus, the question rises: did these services really indeed achieve the sustainability goals they aimed for?
What it does
The application displays the levels of congestion in every district of San Francisco correlated with the number of Uber/Lyft pickup and drop offs. The goal was to indicate the impact of Uber service on congestion, therefore, for every Uber car within a given total, a penalty was awarded to the Uber car, so as to indicate that it lingers and thus increases congestion in the district. We have showed the congested areas at rush hour on a given day.
How I built it
The application is fully built in Python (data manipulation, modelling, and frontend). Moreover, the frontend was implemented with the Plotly framework and geopandas.
Challenges I ran into
Combining different datasets and visions of geospace, into one so that they may be integrated appropriately. Our vision was too great for the initial goal for such a short span of time.
Accomplishments that I'm proud of
The application provides a solid display, and indication of the effects of Uber on traffic congestion!
What I learned
How traffic conditions change! (Python, for some people :) and various new Python libraries)!
What's next for DDDD
Adding an input of the time of the day, day of the week, and a variable percentage of cars being Ubers, and the number of total cars on the road.