Well, here goes. Since I want to fill this blog as quickly as possible, I thought a good place to start would be little breakdowns of my thesis work - my "Excepts of the Thesis" series, if you may. So in this, my initial post. I'll just take time to talk a little about what I did:
"Identifying Subtypes of Minority Diabetes Type II Data Using Cluster Analysis"
So basically the point of this project was to extract a dataset of Diabetes Type II patients from Howard University's Inpatient health data. I used cluster analysis to divide these clusters into groups, and then extrapolated what were the top co-morbidities in each group - "the top other diseases" they may have had - and how they related to features that stood out in each cluster. This was my first big Data Science project by the way, so I'll to recap my thought process through each excerpt, even thinking of how I'd do things differently given the chance.
This should be an adventure - let's go!
