This project was an early exploration of COVID-19 community risk factors. It used early data and machine learning to create a model that would predict the severity of an outbreak within a region based on features. From there, coeffecient analysis was used to identify useful features that could be used to identify risk factors for COVID spread in the United States.
The project was done very early in the pandemic with very limited data (A few weeks of data had been collected).
A paper on the results of this study is found in COVID_19_EDA.pdf
All the code can be found in the final Jupyter Notebook titled Final_Project_Codes.ipynb.