#Folders in Repo
Raw Data: Dataset directly retrieved from Kaggle
Data-collection: Retrieving Lyrics for Negative Songs + Retrieve Lyrics and Spotify ID for Positive Songs (To run .py scripts, you must create a developer account and input secret key for Genius API and Spotify respectively)
Feature-Engineering: All notebooks used for feature engineering and data exploration
Model-training: All notebooks for model training, note that the files were run on Google Colab/TPU, please change directory before attempting to run (Note: Final dataset used for training is feature_eng_combined_v2.csv After human cleaning/intervention)