This is a repository for the IBM Data Science capstone project. It consists of a mini-project and a main project.
I first used Toronto data to learn and test using Foursqure API to cluster neighborhoods. I scraped Toronto postcode data from a webpage and used it to obtain Toronto neighborhood coordinates. Then I searched for venues using Foursquare API and conducted K-Means Clustering onto the resulting data.
For the main project, I chose to inspect differences about venue types among the 77 Chicago community areas, and try to relate such divergence to the racial and economic segregation prevailing the city.
Codes for the project are stored in a the folder "Segregation_Consumption_Chicago", in a Jupyter Notebook file named "Segregation and Shopping Options in Chicago";
full report is stored in the PDF file named "Coursera Captone Report" in the same folder.
A shortened report, published as a blogpost, can be accessed via this link: https://medium.com/@wang37h/segregation-consumption-options-in-chicago-d62cb6852579