Happy and giant waterfall-adjacent
In 2011, I served in AmeriCorps at the lovely & bustling Rondo Community Outreach Library in Saint Paul, Minnesota. I spent my time at the Rondo teaching adult learners from diverse backrounds how to use computers from the ground-up: double-clicking, browsing Wikipedia, and (eventually!) entering functions into Excel.
Over the last eight years, I have grown my fondness for digital instruction into a deep engagement with data science. My fous today is to craft insight from messy, heterogenous data, while always putting everyday folks and their needs at the center of my work.
As the Social Science and Geospatial Data Librarian at Cornell University, I specialize in teaching methods of finding & interpreting data across the social sciences. My techniques of choice include exploring semi-structured and unstructured data, introducing learners to the Python and R data science ecosystems, writing data narratives using visualization packages and Jupyter Notebook, and helping researchers understand machine learning algorithms better.
And as a data scientist and technical writer, I investigate messy, heterogenous data directly using machine learning techniques. I am equally comfortable implementing models ranging from logistic regression or a recurrent neural network model as is appropriate for the investigation at hand. As I experiment and grow, I help others do the same by writing essays and tutorials.
Natural language processing; data visualization; machine learning; deep learning; technical writing; web application development; mixed methods research
Packages: pandas, tidyverse, seaborn, bokeh, d3.js, scikit-learn, TensorFlow, sqlite3, keras, Spark, django, flask
Software: Tableau, Adobe Creative Suite
Outside of work I love writing, pinball, zines, hikes, cats, speculative fiction, making games, playing pick-up basketbll, and riding trains. I lived in Tokyo for half a year. I would love to moonlight as a pinball mechanic someday.