I am a data scientist specializing in Python, machine learning, experimental design, practical statistics and problem solving. I enjoy writing clean robust code with thorough documentation, exploring new methods and technologies, and teaching others the tools to work more efficiently. My full resume is available here.
I am passionate about the scientific method, life-long learning, women in technology, protecting our environment, and snowboarding as much as possible. In past lives I was a PhD astrophysicist and a sponsored competitive snowboarder.
Current Position: Senior ML Engineer (Modeling) at Square.
I am experienced with a number of languages and tools, but my everyday bread and butter is Python and its ecosystem of data-related libraries. In addition to those called out below, I regularly make use of numpy, matplotlib, seaborn, and many others. See my resume for a more complete list of skills and projects.
Over 5 years professional experience coding and designing software in Python. I am co-organizer of the Salt Lake PyLadies and absolutely love the Python community!
Jupyter Notebook is a killer interactive environment for exploratory analyses, prototyping future production software, and joyfully teaching and sharing code with others.
Probably the only library that I import in every single Python session, Pandas is my go-to for getting started exploring a new dataset and coercing it into useful forms.
I reach for this awesome Machine Learning package when faced with problems requiring modeling, predictive analytics, or a deep dive into unsupervised data exploration.
Love the command line! I've been working in various shells on Unix systems for 10+ years, creating shell scripts and automating jobs with cron.
Evangelist for open source software (and data), from academia to industry. I share everything I can on GitHub, including this very website.
Controlling the versions one commit at a time. I teach Git and GitHub to anyone who will listen, including Software Carpentry students.
Skilled in writing complex SQL queries for adhoc requests and large scale projects, and in maintaining automated custom tables in relational databases.