I am a Charleston, SC-based full stack engineer and data scientist. My current focus is on learning and applying new technologies to create accessible, dynamic web applications.
I graduated from the University of South Carolina with a Bachelor of Science in Biochemistry and Molecular Biology. Upon graduation, I worked at the Medical University of South Carolina in the Mulholland Lab, where I was a Research Scientist. In this position, I developed an affinity for the use of software in solving complex problems, including behavioral classification and gene expression analysis.
This site serves to showcase some analysis techniques I have picked up, and has accompanying code and data in case you, kind reader, would like to code along, replicate results, or perform some novel analysis of your own!
If you'd like to reach me, my contact info can be found in the footer. Thanks for visiting.
This work, done as a project for the MIT Schwarzman School of Computing DSML Certificate program, involved the training and comparison of 4 types of model:
This work also provided experience in statistical analysis using various popular Python packages and libraries, including pandas, numpy, seaborn, matplotlib, and sklearn. Data for this project can be downloaded here.
This work, done as a sort of replication of a study performed at the University of California - San Franciso, provided me with the opportunity to learn some proprietary genomic analysis techniques:
This project provided me with an opportunity to turn a relatively simple data set (a user and some movie ratings s/he gave) into an accurate predictor for future ratings. This work involved the creation of three popular machine learning models:
Static webpage with an API to tmdb, a frequently updated movie and television show database. The program ties HTML, CSS, and Javascript together to allow for the generation of a random film based on genre chosen. NOTE: the application currently requires you to enter your own API key to function properly.