Competition Site: https://www.drivendata.org/competitions/57/nepal-earthquake/
Rank = 50 out of ~ 1400 competitors.
We used a RandomForest with frequency and mean encoding on geographic id variables to predict the damage grade to buildings affected by the 2015 Gorkha Earthquake in Nepal.
Project Structure:
src - code Jupyter Notebook name can start with initials to track of code easily. example: NB_notebook.ipynb
input - unprocessed downloaded input files or links
output - any ouput from code is saved here