dataset_delaunay_generate: Generate Delaunay triangulation network data
In rdinnager/rspektral: What the Package Does (One Line, Title Case)

Generates a dataset of Delaunay triangulations as described by Zambon et al. (2017). Node attributes are the 2D coordinates of the points. Two nodes are connected if they share an edge in the Delaunay triangulation. Labels represent the class of the graph (0 to 20, each class index i represent the "difficulty" of the classification problem 0 v. i. In other words, the higher the class index, the more similar the class is to class 0).

dataset_delaunay_generate(
  classes = 0L,
  n_samples_in_class = 1000L,
  n_nodes = 7L,
  support_low = 0,
  support_high = 10,
  drift_amount = 1,
  one_hot_labels = TRUE,
  support = NULL,
  seed = NULL,
  return_type = "numpy"
)

`classes`	classes indices of the classes to load (integer, or list of integers between 0 and 20)
`n_samples_in_class`	number of generated samples per class
`n_nodes`	n_nodes number of nodes in a graph
`support_low`	support_low lower bound of the uniform distribution from which the support is generated
`support_high`	support_high upper bound of the uniform distribution from which the support is generated
`drift_amount`	drift_amount coefficient to control the amount of change between classes
`one_hot_labels`	one_hot_labels one-hot encode dataset labels
`support`	support custom support to use instead of generating it randomly
`seed`	seed random numpy seed
`return_type`	Data format to return data in. One of either "list", or "tidygraph"

if return_type='list', the adjacency matrix, node features, and an array containing labels, in a list
if return_type='tidygraph', a tidygraph object, with node features and labels as node data

rdinnager/rspektral documentation built on June 12, 2021, 1:26 a.m.