tamedata
An R package providing interesting examples for use in R instead of mtcars, iris, and diamonds
Ideas
- If you'd like to contribute ideas to this package (and help me build it), please add Issues and explain clearly why your data set is interesting. Currently, I'd like to focus on data sets of social relevance to be more inclusive, but I'm open to other interesting datasets too.
- Datasets included here should be accessible to students being exposed to data for the first time in R. They are "tame" in the sense that a lot of the raw-ness of the data has been cleaned up, but maybe they aren't perfectly clean and need a little more taming.
- The data sets should be clearly documented as to
- which public/ok-to-share resource they came from,
- where were they downloaded from/what was the process to create them (be as reproducible as possible),
- what code was needed to convert them from "raw" to "tame", and
- what the license is on the data (so that a future CRAN version of the package with that data is a thing).
Sources to begin
- https://github.com/caesar0301/awesome-public-datasets
- Need help documenting which of these are actually "awesome"
- A Google Sheet going through and categorizing them as useful or not would be helpful