Welcome to the repository for my Wheel of Time Natural Language Processing (NLP) project. In this repo you will find the code for my project, some manually collected data, my final presentation as well as the files for my visualizations.
Note: The text is extracted by code from the eBook containing every book in the Wheel of Time series, and thus relies on having a copy of that book available to run.
The structure for this repo is as follows:
- code
- jupyter notebooks are labeled in order of project steps. Helper functions can be found in the .py files
- Data_files
- Excel with collected meta-data
- Manual list of exceptions and exclusions being used in the code to extract the book texts from the epub file.
- When running the code, additional data files will be stored in this same folder to prevent having to re-run time intensive steps
- Presentation
- My final presentation I used to present this topic during my Metis Data Science Bootcamp
- Viz
- My visualizations
- These will be re-generated when running the code