Thomas Shafer, Ph.D.
Lead Data Scientist
Elder Research, Inc.
Raleigh, NC
contact-at-tshafer
GitHub, Google Scholar, LinkedIn
I've toyed with computer programs since programming for the web
in high school, and my graduate studies let me apply
computational tools to physical theory. Now, serving as a Lead
Scientist, I get to mentor data scientists and study interesting
problems while also contributing technically to help our clients.
Over the last few years, I've led and contributed to major
projects applying Bayesian modeling, graph analytics, deep
learning for computer vision, and much more.
Skills in Brief
Programming Languages
- Python, R, Bash, Stan, SQL, Make, Fortran, HTML, CSS (Proficient)
- Julia, C, Perl, Ruby (Occasional use)
Frameworks and Tools
- PyTorch, Keras, FAIR‘s Detectron2 (Neural networks & deep learning)
- Stan, RStan, CmdStanPy, CmdStanR (Stan probabilistic programming language)
- Gensim, Numba, Numpy, Pandas, Scikit-Learn (Python tools)
- R data.table, Tidyverse, Tidymodels, R Shiny (R tools)
- MLFlow, Tensorboard (Model monitoring)
- Docker, GitLab CI/CD, GitHub Actions (CI/CD and deployment)
- Git, Subversion, and other version control systems (Collaborative code)
Platforms
- EC2, S3, Batch, ParallelCluster (Amazon Web Services)
- Azure Cognitive Services, Azure ML Studio, Databricks (Microsoft Azure)
- macOS, Unix, Windows (Operating systems)
Publications, Talks, and Writing
Publications
- Kingi, H. et al. A numerical evaluation of the accuracy of influence maximization algorithms. Social Network Analysis and Mining 10, 1–10 (2020).
- Bastaki, M. et al. A chemical structure-based approach for estimating the added levels of flavourings to foods for the purpose of assessing consumer intake. Food Additives & Contaminants: Part A (2020).
- Shafer, T. et al. decay of deformed -process nuclei near and , including odd- and odd-odd nuclei, with the Skyrme finite-amplitude method. Phys. Rev. C 94, 055802 (2016).
- Mustonen, M. T., Shafer, T., Zenginerler, Z. & Engel, J. Finite-amplitude method for charge-changing transitions in axially deformed nuclei. Phys. Rev. C 90, 024308 (2014).
- Shafer, T. Calculation of beta-decay rates in heavy deformed nuclei and implications for the astrophysical r process. (2016).
Talks
- Shafer T. Stay at Home, or at Least Tread Lightly: Using County-Level Data to Study the Effectiveness of COVID-19 Policy. Data Science Conference on COVID-19 (2020).
- Elder Research. Using R and AWS for Random Forests. Research Triangle Analysts (2017).
Writing
- Shafer, T. Policy impact on COVID-19 spread. Elder Research Blog (September 4, 2020).
- Shafer, T. The 42 V’s of big data and data science. Elder Research Blog (April 1, 2017).
Education
Ph.D., Physics
The University of North Carolina at Chapel Hill (2009–16)
Advisor: Jonathan Engel
Thesis: Calculation of Beta-decay Rates in Heavy Deformed Nuclei
and Implications for the Astrophysical r Process
B.S., Physics and B.A., Mathematics
The University of North Carolina at Wilmington (2005–09)
University Honors with Honors in Physics