Who am I?
Greetings! I'm Zach, and I love digging into deep questions using data analysis techniques. I started my career by getting a Ph.D. in Physics and applying my love of statistics and coding to the "deep problems of the universe." I've run experiments that studied how nuclei split apart to release energy (nuclear fission), what makes up a nucleus, and numerous other physics topics. All of these tasks shared two common themes: how do we get tons of data and what do we do with it once we have it? Solving these problems was the key to unlocking the answers to the puzzles of the universe. However, for me, what always mattered the most was problem solving through data techniques. So, yes, I've loved working with huge collaborations to study what happened in the first nanoseconds after the Big Bang... but I'm just as excited to use analysis techniques to predict what soup someone will eat based on their lifestyle! I'm fluent in C++, Python and UNIX, and I have a working knowledge of R, Java, BASH, LaTeX, C#, and Javascript. I'm also a musician, a rock climber, and have a deep love of green chile. See More...
Featured Projects:
Compendium of Talks
Want to hear me talk about data science? That's a thing I do sometimes.
What Makes Neural Nets Special
Why do data scientists love neural nets so much when we still have linear regression?
Who's Driving Twitter Discussions - Network Analysis
Using graph theory, social network analysis, and a twitter streamer - we examine how we can extract the users who are leading the discussions on Twitter via highly retweeted content.
NLP Pipeline Manager
Natural Language Processing (NLP) has a lot of very frustrating parts. In this post, I introduce a library I wrote, and how I hope it makes NLP suck less.