Guest contribution to Randy Au’s Counting Stuff blog
data collecting
data cleanup
I was inspired by one of Randy’s entries to write up my own experiences with doing data collection over the years, using my current project on tracking litter as the example.
My blog entry on collecting data.
The project
In Geophysics there are basically three main specialties (I have done all three): data acquisition, data processing, and data interpretation. I believe these same three categories apply to any data science project as well. Data has to come from somewhere - whatever the project is. It is basically guaranteed that the data will have issues which need fixing - that’s the processing bit. And finally, of course, what does it all mean - where the rubber meets the road.
I thought I would talk a bit about my latest personal project - in particular about the data acquisition part, because there are a lot of decisions embedded in that step.