November 15, 2018 I set out on a mission to create a drug-review sentiment analysis model.
It began as most ideas do… with a problem.
For the past 24 months my wife has struggled through a major depressive episode. Treatment protocol has taken her from one medication trial (and failure) to the next. Each drug trial takes anywhere between 8 to 16 weeks depending on titration, follow-up appointments, and tapering off. Throughout this process she’s experienced the whole gambit of side effects. Nausea, fatigue, drowsiness, and severe anxiety to name a few. Some drugs helped a little with the depression…
Kaggle has made sizable real-world datasets accessible to data scientists in a transparent and unsurpassed way. Unfortunately as more new data scientists rely on Kaggle to hand them data they miss out on developing one of the most important skill sets for our field: hunting for and acquiring hard to find or privately held datasets.
This post will help you discover unpublished datasets and will teach you a simple framework to “ask and acquire”.
Eventually you will need data and a google search won’t be enough to get it. It happened to me this weekend. IT WILL HAPPEN TO YOU.