Skip to contents

Plot the diagnostics of the matching of clusters across windows

Source: R/merge_diagnostics.R
plot_merge_diagnostics.Rd

[Experimental]

Draws the result of merge_diagnostics(). Two views are available:

  • "summary" (default): one panel per indicator (number of dynamic clusters, share of window clusters that find a predecessor, median lifespan, share of nodes in persistent clusters...), against the threshold, with one line per type of similarity. Look for plateaus: thresholds around which the indicators barely move.

  • "lifespans": for each threshold, the share of the nodes (of all windows) that belong to dynamic clusters of a given lifespan (1 window, 2, 3 to 5, 6 to 10, more than 10), one panel per type of similarity. It shows how the weight of short-lived and long-lived clusters changes with the threshold.

Usage

plot_merge_diagnostics(
  diagnostics,
  view = c("summary", "lifespans"),
  metrics = c("n_dynamic_clusters", "share_continued", "median_lifespan",
    "share_nodes_persistent"),
  base_size = 16
)

Arguments

diagnostics

The result of merge_diagnostics().

view

"summary" or "lifespans".

metrics

For the summary, the columns of diagnostics to draw.

base_size

Base font size of the plot.

Value

A ggplot object.

See also

merge_diagnostics().

Examples

networks <- build_dynamic_networks(
  nodes = subset(Nodes_stagflation, source_type == "Stagflation"),
  directed_edges = Ref_stagflation,
  source_id = "source_id",
  target_id = "target_id",
  time_variable = "source_year",
  time_window = 10,
  window_step = 4,
  method = "angle",
  edges_threshold = 2,
  verbose = FALSE
)
#> Warning: The last window is shorter than the others.
#> ℹ The data end in "2013", but the last window ends in "2016".
networks <- add_clusters(
  networks,
  clustering_method = "leiden",
  objective_function = "modularity",
  seed = 123,
  verbose = FALSE
)
diagnostics <- merge_diagnostics(
  networks, "cluster_leiden", "source_id", method = "majority",
  thresholds = c(0.51, 0.6, 0.75), similarity_types = "partial", verbose = FALSE
)
#> Warning: 1 pair of consecutive windows share no node: its clusters cannot be matched,
#> whatever the threshold.
plot_merge_diagnostics(diagnostics)

plot_merge_diagnostics(diagnostics, view = "lifespans")