This project is going to find insights in the FDA Drugs data for their FDA Open Data Challenge.

I will be specifically focusing on the labeling / adverse events categories

Link: https://open.fda.gov/update/an-open-challenge-to-tap-public-data/

This project has now pivoted to analyze drug labels to find any that are under labeled. This repo shows how to access the data, clean the data, extract topics, cluster, and identify outliers.

fda_data_entry.py

fda_exploratory_data_analysis.py

fda_data_exploration.py

fda_initial_data_analysis.py

fda_adverse_events_cleaning.py

fda_labels_cleaning.py

fda_recalls_cleaning.py

fda_reactions_cleaning.py

See Topics_Labels folder

fda_clustering.py

Coming soon!