plot_cluster_network function

Network plot of a (low dimensional) ADPROCLUS solution

Produce a representation of a (low dimensional) ADPROCLUS solution, where each cluster is a vertex and the edge between two vertices represents the overlap between the corresponding clusters. The size of a vertex corresponds to the cluster size. The overlap is represented through color, width and numerical label of the edge. The numerical edge labels can be relative (number of overlap observations / total observations) or absolute (number of observations in both clusters). NOTE: This function can be called through the plot(model, type = "network") function with model an object of class adpc.

plot_cluster_network(
  model,
  title = NULL,
  relative_overlap = TRUE,
  filetype = NULL,
  filename = "network_plot",
  ...
)

Arguments

• model: ADPROCLUS solution (class: adpc). Low dimensional model possible.

• title: String. Optional title.

• relative_overlap: Logical. If TRUE (default), the number of observations belonging to two clusters is divided by the total number of observations. If FALSE

  the number of observations in a cluster overlap will be displayed on the edges.

• filetype: Optional. Choose type of file to save the plot. Possible choices: "R", "pdf", "svg", "tex", "jpg", "tiff", "png", ""

  Default: NULL does not create a file.

• filename: Optional. Name of the file without extension. Default: "network_plot"

• ...: Additional arguments passing to the qgraph::qgraph() function, to customize the graph visualization.

Returns

Invisibly returns the input model.

Examples

# Loading a test dataset into the global environment
x <- stackloss

# Quick low dimensional clustering with K = 3 clusters and S = 1 dimensions
clust <- adproclus_low_dim(x, 3, 1)

# Plot the overlapping the clusters
plot_cluster_network(clust)