Repository for the Data 606 Project.
Authors:
- Daniel Thang
- Reed Balentine
- Khiran Kumar
This is a repository that stores our work on the Natural Language Prediction model based on NPR transcript data.
- The Exploration folder contains the Exploratory Data Analysis.
- The Final_Models folder contains the two notebooks, Logistic Regression and MulitnomialNB, that have the final models.
- The Machine Learning folder contains a record of some notebooks and the progression of modelling attempts and the BERT attempt.
- The Presentations folder contains the three presentations given. Please note that the final presentaion was split into three .zip files to respect GitHubs file size limit.
- The Website folder contains the data for the website as a .py file.
- The blog post is in the main directory