KMVis is a library for visualizing kernel machines in Python. In general, kernel machines are associated with a variety of rich mathematical structures, the visualization of which can provide a unique insight into the geometry of the data in either the input or feature space. Unfortunately, there is a paucity of available tools for the visualization of these structures; in particular, while libraries exist which perform visualization piecemeal (for example the decision boundaries generated by a kernel SVM in input space), a holistic approach tackling a variety of kernel machines is lacking. The goal of this library is to provide such an approach.

Please see http://hassankingravi.com/KMVis for more information about the current state of the library, and what will be supported in future.