You can find the Jupyter Notebook for this venture here.
For accessibility the .csv file, that had been too-large to publish to Github, make use of Contact form to my internet site.
OKCupid info? Okay!
As a millennial which spent a good part of my personal 20’s on OKCupid, i used to be very thrilled for your chance to discover and shape a dataset that contains practically 60,000 OKCupid profiles as the equipment mastering capstone task. Because the scholastic history is linguistics, i used to be interested to see if how most people talk about our selves, our personal relationships, plus the community around us all maybe regularly foresee expertise like degree level, sex, and/or era. After some deliberation, I decided to get rid of the data down by sex. After all, we & most queer individuals I am sure posses all of our identifications securely rooted in our queerness, and for valid reason: to date, you still enjoy construction discrimination. Although work discrimination was decided illegal by way of the Supreme the courtroom this Summer, the existence of at-will employment nonetheless means a company can spice an LGBT+ staff for “not becoming a good fit,” “dress signal infractions,” or other coded homo- and transphobic reasons, some thing many of us have experienced happen or maybe even experienced directly. Read more