Description Usage Arguments Value Examples
This method takes an adjacency matrix, which can be created with
CreateAdjMatrix
, and computes the diffusion kernel matrix. If the
dimensions of the adjacency matrix are large (at least 10,000 x 10,000), then this
step can take an hour or more to run.
1 | CreateKernel(adj.mat, lambda = 0.1, normalize = FALSE, autosave = FALSE)
|
adj.mat |
Required. An adjacency matrix. Can be produced using |
lambda |
Optional. Defaults to standard of 0.1. Adjusts the amount of diffusion done. Not recommended to change unless there is specific rationale for doing so. |
normalize |
Optional. Defaults to false. If set to true, the normalized version of the laplacian is computed prior to kernel computation. |
autosave |
Optional. Since this function can take a while to compute, it may be preferable to have the kernel be saved immediately once it is computed. If autosave is set to TRUE, a copy of the kernel will be saved in the current working directory. |
The regularized laplacian kernel matrix.
1 2 3 4 | data(ignition.example.edges)
adj.matrix = CreateAdjMatrix(ignition.example.edges)
kernel = CreateKernel(adj.matrix) #if not using autosave
kernel = CreateKernel(adj.matrix,autosave=TRUE) #if using autosave
|
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.