Context

My team and I have concluded a data science course in May. Since quality public data in Brazil is hard to gather, we decided to post everything we gathered for our final project and make it easily downloadable. We hope that, by doing so, other people may be able to help to improve São Paulo's bus system.

Check our GitHub for more! https://github.com/ds4a-team-21

Content

In the GTFS, you can find data about the shapes and coordinates of routes and bus stops; assign bus stops to their respective bus routes; and see the current frequencies of buses at each bus stop. There is also data about the daily amount of passengers in each bus line from 2013 until April 2020 and real-time gathered on bus positions from April 28th until May 6th.

Acknowledgements

We wouldn't be here without the help of Correlation One's team, which helped us through this journey. Thank you!

Inspiration

We hope that by making this dataset available, data scientists from all over the world will be able to help us optimize São Paulo's Public Bus System in terms of speed and number of passengers transported. Our future goals were to develop a model that could help São Paulo's Town Hall to make decisions such as where to put bus stops to increase speed, which bus frequency is optimal for each bus stop, and which factors impact the most in the bus speed.### Context

My team and I have concluded a data science course in May. Since quality public data in Brazil is hard to gather, we decided to post everything we gathered for our final project and make it easily downloadable.