Before running the analysis make sure to install all required python packages.
Input data and other data extracts are stored in the data folder.
This folder contains the Notebook (and associated preprocessing routines) with all relevant steps and results related to the FastText part of our report. It also writes the re-processed data for use in the keyword analysis rerun.
This folder contains the Notebook (and associated library utilities) with all relevant steps and results related to the quantitative keyword analysis part of our report.
This folder contains the Notebook with all relevant steps and results related to the TF-IDF modeling part of our report.
This folder contains collected visualizations and documentation of analysis approaches and results.
Notebooks and scripts in this folder were only used for experimentation but do not contain results used for the final report.
Approach Overview