Overview
Environmental contaminants are an important public health concern, yet understanding their relationship with disease at the population level requires integrating data from multiple sources. This project examines whether county-level exposure to health-based drinking water violations is associated with age-adjusted cancer incidence across Georgia. The analysis combines publicly available data from the Georgia Department of Public Health and the U.S. Environmental Protection Agency using Python to build a reproducible analytical workflow. The project was completed as part of graduate coursework in Biological Data Science at Arizona State University.
Research Question
Is exposure to contaminated drinking water associated with cancer incidence across Georgia counties?
Project Goals
The objectives of this project were to:
- Extract county-level cancer incidence data from publicly available reports.
- Clean and integrate environmental and public health datasets.
- Create county-level measures of health-based drinking water violations.
- Prepare an analysis-ready dataset for exploratory statistical analysis.
- Evaluate whether patterns in drinking water violations are associated with cancer incidence across Georgia counties.
Methods
The workflow included:
- Extracting cancer incidence data from PDF reports using
pdfplumber - Cleaning and validating public health data
- Identifying and resolving duplicate EPA violation records
- Converting suppressed values to missing values where appropriate
- Aggregating drinking water violations to the county level
- Merging environmental exposure and cancer incidence datasets
- Preparing the integrated dataset for statistical analysis using Python, pandas, NumPy, and Matplotlib.
Skills Demonstrated
- Python
- pandas
- NumPy
- Data cleaning and quality control
- Data integration
- Public health data analysis
- Environmental epidemiology
- Exploratory data analysis
- Scientific documentation
Data Sources
- Georgia Department of Public Health
- U.S. Environmental Protection Agency Safe Drinking Water Act (SDWA) ECHO database
Project Status
This is an ongoing graduate research project. The notebook documents the complete analytical workflow from data acquisition through data cleaning and integration. Additional statistical analyses and visualizations will be added as the project develops.
Notebook
📓 View the Jupyter Notebook on GitHub
chelsea Doop 