The volunteers who work every day to improve the watershed
What it does
It just cleans the data and follows a nearest neighbor imputing strategy using a workflow to retain as much of the original data as possible.
How I built it
I started with the CMC/CBP data and filled/added additional exogenous variables from publicly available noaa datasets.
Challenges I ran into
Time constraints and missing domain knowledge
Accomplishments that I'm proud of
It was a off to a good start.
What I learned
That there is a treasure trove of publicly available weather data.
What's next for Just some eda
If there ever is a call for further help in watershed pollution modeling, I'd like to take what I've learned and expand upon it to be something more complete and useful.