A sunburst visualization of a BigML decision tree built on the SMS Spam dataset.
The model uses BigML's upcoming automatic text processing to find important words when separating the spam from the ham.
The initial center circle represents the root of the tree. Each outer circle contains the children of the inner circle's nodes. The number of training instances captured by a node determine its arc length (or its size in radians).
Clicking on a node will zoom in to the subtree. After zooming in, selecting the new center point will zoom out one level.