This notebook shows the initial data cleanup workflow for a capstone project in fulfilment of Springboard’s Data Science Track Program.
The data was retrieved from the National Transportation and Safety Board website. The original data resides in a 20-table MS Access database. The pertinent information was exported to Coma-Separated Value (CSV) files utilizing Access’ query functions. This resulted in six distinct files. The data was then imported, analyzed, and cleaned utilizing Python Pandas methods and other libraries. Finally, a single merged file was exported ready for Exploratory Data Analysis (EDA).
Birr-Data 