The final report and correspoding slides can be found here
Databases are big for GitHub. They can be downloaded from this GoogleDrive link
The script folder contains the following:
i) my_fns.py : the functions used for the descriptive analysis and preprocessing
ii) 200611_final_project.ipynb: the Jupyter Notebook with the code and outputs of the preprocessing and Machine Learning algorithms.
iii) db_consolidation.py: the code used for the ETL process of the data.
iv) varlists.py: contains the list of variables used for time operators.