Boxplots are a great way to quickly summarize probability distributions using a high data-ink ratio.
At LiquidLandscape, we toyed around with the idea of a boxplot for continuous data, in particular, cyclical data. We came up with a natural extension, the radial boxplot. It's easy to imagine how one would look once you hear its name.
- Sample data from the Data Canvas - Sense Your City project. Taken from San Francisco between 1/1/15 and 4/1/15.
- rbox.js uses a crossfilter.