Policy

Lead Poisoning [KDD ‘15] [GitHub] [Chicago Tribune, The Atlantic, South Side Weekly]
In collaboration with the Chicago Department of Public Health, I led the development of a predictive model to drive targeted home lead investigations which we are currently in the process of piloting.

Hazardous Waste [Preprint] [GitHub]
I led a collaboration with the New York State Department of Environmental Conservation to predict violations of the Resource Conservation and Recovery Act which governs the management of hazardous waste.

Election Information
My article Why It’s So Hard To Find Out Where the Candidates Stand about the history and future of election information was published in the Washington Monthly.

Data

drain [GitHub]
This is a simple and powerful Python framework for reproducible and parallel data science workflows.

collate [GitHub]
This is a Python library for generating spatiotemporal aggregation SQL queries, primarily for building features for machine learning and other models.

acs2pgsql [GitHub]
This is a drake pipeline for bulk importing the American Community Survey (ACS) data and TIGER shapefiles from the U.S. Census FTP into a PostgreSQL database.

dmr [GitHub]
For the University of Chicago’s Environmental Law Clinic, this software downloads and imports discharge monitoring reports from the Illinois EPA website.

Miscellaneous

Higher Ground [GitHub][blog][CBS]
This work-in-progress uses OpenStreetMap data to analyze and visualize urban greenspace.

Visible Hand [GitHub]
This software calculates the carbon footprint of flights and utilities by parsing e-mail receipts and integrating various aircraft and energy emissions databases.

Cook Scheduler [GitHub]
This code uses linear programming to optimize the selection of a cook schedule given each cook’s preferences.

Projects - Eric Potash