GeorgeM2000/CDC-SMART-BRFSS-City-and-County-Data-Analysis

This project aims to compare traditional Machine Learning methods for tabular data classification, such as Ensemble methods, Decision Trees, and Naive Bayes, with NLP classification methods like Multinomial Naive Bayes, RNNs, and Transformers. We are utilizing survey data from the CDC via the Behavioral Risk Factor Surveillance System (BRFSS)

Jupyter NotebookMIT