What I learned interviewing with companies of all sizes in one week — This will be a more personal blog than some of my previous technical articles. The reason is there in the title! I had several interviews this week at companies of very different sizes and I wanted to share my experience. This is, of course, only my subjective opinion. Small My first…

Proteomics with Biopython — Human biology is incredibly complex. Even with our ever-growing understanding, our answers only uncover more and more questions. The completion of the Human Genome Project gave many scientists confidence that we could solve pressing issues in biology through genomics. However, as our understanding of biology has grown, we’ve recognized that…

Your One Stop Shop for All Things NetworkX — Graph theory is an incredibly potent data science tool that allows you to visualize and understand complex interactions. As part of an open-source project, I’ve collected information from many primary sources to build a graph of relationships between professional theatre lighting designers in New York City. I used NetworkX, a…

Creating Insightful and Beautiful Bioinformatics Visualizations — There’s a misconception that science is dry, humorless, and overly technical, but that doesn’t need to be the case! Effective visualizations can transform raw DNA into stunning figures that relay a lot of information with clarity. Biopython is the go-to, open-source bioinformatics, or computational molecular biology, package for Python. It…

Why data ≠ analysis — As I researched some applications for data in precision medicine, I came across an interesting claim in “From Big Data to Precision Medicine” an article in Frontiers in Medicine. The article states: “However, ‘Big data’ no longer means what it once did. The term has expanded and now refers not…

Understanding a key assumption in statistics and its implications — The main purpose of data science generally, and machine learning specifically, is to use the past to predict the future. Beyond the specific assumptions of various statistical models, the inescapable assumption is that the future can be predicted from past events. We assume that there is some function we can…

Scraping a ‘table’ from a webpage — A recent passion project exploring the data of Broadway demanded some data that I was having trouble tracking down. But then, success! I found a webpage with a table of earnings and performance information by Broadway show! The problem? How to get that data into a usable format. The answer…

Insights for customer segmentation and extrinsic factors — After a few back-to-back projects featuring neural networks (which you can explore here and here) and deciding to build a NN from scratch, I wanted to start an EDA-focused project to keep my pandas skills sharp and get back to data science’s roots. …

Going Beyond “import keras” — I’m sure you’ve heard this advice before. I know I did. I read it in other blogs, I heard it in many podcasts and interviews, and even had the thought myself, “I really should do that.” But for a long time, I didn’t. If you want to set yourself apart…