Social Graph of New York
Projects | | Links:
A social graph of New York’s well-to-do generated from the image captions of more than a thousand website pages.
Note: The code and the end result cannot be publicly displayed due to copywrite by The Data Incubator; however, they can be sent privately upon request.
The website links along with the party dates were pulled from the New York Social Diary’s Party Picture Archives. Then after html parsing and a great deal of text cleaning, I was able to put together a graph of everyone appearing in any caption of any party in the archive. The edge weights were determined based on the number of times two nodes had been included in the same photo caption.
Learning Points: html parsing, string parsing, BeautifulSoup, graph manipulation