Writing

In this post, I explain what Epic (Chronicles, Clarity, etc.), OMOP CDM, and Stanford STARR are, how they are all related, and what the benefits/features of each are.

If you’ve ever had to ssh into a server to run programs, you may be taking an unnecessary productivity hit each time you relegate yourself to coding in a Jupyter notebook on localhost:8000.

Most people know that a batting average over .300 is the mark of a great hitter, and that hitting .200 will land you on the bench.

Goal: Publish a .ipynb on my Jekyll static site as painlessly as possible.

These are all taken from this great 3-hr YouTube tutorial by Ben Root from SciPy 2018. I’ve condensed the main takeaways of the talk into the following list of key concepts / tricks that I hadn’t previously been aware of.

For the below examples, assume we have a binary classification task where the class label is $y \in {0, 1}$, and the model’s predictions are $\hat{y} \in {0, 1}$

A brief cheat sheet / reference guide containing the definitions, formulas, and explanations of the most commonly used model evaluation metrics for binary classification tasks.

The definition of “tidy data” is simple:

I’ve always been intimidated by vim. After taking MIT’s Missing Semester Course (a free online course that I’d highly recommend), I learned about a built-in utility called vimtutor that automatically comes installed with vim.

tl;dr – If you have XCode installed, then you could easily be wasting up to 10% of your disk space.

In Season 4, Episode 3 of his podcast Revisionist History, Malcolm Gladwell argues against the use of the LSAT in law school admissions. A full transcript of the episode can be read here.