NOAA Data Collection Automation

This project automates the data collection of king tide dates for NOAA, allowing them to easily pick the best dates to gather data. After gathering the data, the king tide predictions for all of the stations within a region are compared to a specified primary station in order to determine the date with the highest king tide for the entire region. This has allowed NOAA to expand their operation outside of the state of Hawaii and throughout the pacific as a whole. More information about their project can be found here. An instructional video for this project can be found here, clearly detailing the notebook’s use and does not assume any prior programming knowledge.

This project provided me with an exceptional opportunity to apply my data science and project management skills outside of the classroom. I had to interface with NOAA’s data api to retrieve the king tide data, and the gspread API to export my finalized predictions to Google Drive. Actually organizing, sanitizing, and analyzing the data required strong python skills and the numpy and pandas libraries. Project management skills were needed to communicate with NOAA, detail the project specifications, determine the required revisions after the first draft, and communicate the notebook and how to use it.

An example of the notebook’s user interface, requiring no coding experience to use

You can view the whole code in the GitHub repository for this project.