Plot the evolution of dynamic clusters as an alluvial

plot_alluvial() draws the table created by networks_to_alluv() with ggalluvial: one column per time window, one block per dynamic cluster, with a height proportional to its share of the window, and flows that follow the nodes from one window to the next. It can colour the clusters (color_alluvial()), reorder them to limit crossings (minimize_crossing_alluvial()) and position their labels (prepare_label_alluvial()) on the way.

Usage

plot_alluvial(
  alluv_dt,
  cluster_id,
  node_id,
  window_column = "window",
  color_column = "color",
  color_alluvial = FALSE,
  color = NULL,
  minimize_crossing = FALSE,
  prepare_label = FALSE,
  cluster_label_column = "cluster_label",
  min_share_cluster = NULL,
  min_windows_cluster = NULL,
  print_plot_code = FALSE
)

Arguments

alluv_dt

A data frame created with networks_to_alluv(), or directly the list of tbl_graphs with dynamic clusters (see merge_dynamic_clusters()), which is then converted with networks_to_alluv() (color_column and cluster_label_column are the columns kept).

cluster_id

Character scalar, the column with the dynamic clusters (e.g. "dynamic_cluster_leiden").

node_id

Character scalar, the column with the node identifiers.

window_column

Character scalar, the column with the time windows ("window" by default).

color_column

Character scalar, the column with the colours of the clusters ("color" by default). If absent or NULL, ggplot2 chooses the colours.

color_alluvial

Logical. If TRUE, runs color_alluvial() first.

color

With color_alluvial = TRUE, the colours passed to color_alluvial().

minimize_crossing

Logical. If TRUE, runs minimize_crossing_alluvial() first. Clusters are also reordered when alluv_dt already has a minimize_crossing_order column.

prepare_label

Logical. If TRUE, runs prepare_label_alluvial() first, which adds a label_x column with one label per cluster.

cluster_label_column

Character scalar, the column with the labels used by prepare_label_alluvial() ("cluster_label" by default).

min_share_cluster, min_windows_cluster

Optional numbers to keep the main clusters only: the clusters whose largest share of a window (share_cluster_max, in per cent) is at least min_share_cluster, and which exist in at least min_windows_cluster windows (length_cluster). NULL (default) keeps all the clusters.

print_plot_code

Logical. If TRUE, prints the ggplot2 code of the plot.

Value

A ggplot object.

Details

Labels are drawn with ggrepel, which must be installed, when alluv_dt has a label_x column. Small clusters clutter alluvials: filtering the table on share_cluster_max or length_cluster (see networks_to_alluv()) before plotting keeps the main ones.

The alluvial method was initiated by Alexandre Truc.

Examples

# \donttest{
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,
  method = "similarity",
  edges_threshold = 1,
  verbose = FALSE
)
#> Warning: The last window is shorter than the others.
#> ℹ The data end in "2013", but the last window ends in "2014".
networks <- add_clusters(
  networks,
  clustering_method = "leiden",
  objective_function = "modularity",
  seed = 123,
  verbose = FALSE
)
networks <- merge_dynamic_clusters(
  networks,
  cluster_id = "cluster_leiden",
  node_id = "source_id",
  method = "majority", threshold_similarity = 0.51,
  similarity_type = "partial"
)
#> ℹ Linking clusters across windows with the "majority" rule: a cluster inherits
#>   the identifier of a past cluster when more than 0.51 of the nodes of each go
#>   to / come from the other (double majority). The comparison counts the nodes
#>   present in both windows only (`similarity_type` = "partial").
#> Warning: 3 pairs of consecutive windows share no node: their clusters cannot be matched.
#> ℹ Clusters are matched through the nodes they share. In a network of documents
#>   (coupling), each node has one date: the windows must overlap (`window_step`
#>   smaller than `time_window` in `build_dynamic_networks()`). If windows already
#>   overlap, the nodes may have changed completely, or the threshold may leave a
#>   window without edges.
alluv_dt <- networks_to_alluv(
  networks,
  cluster_id = "dynamic_cluster_leiden",
  node_id = "source_id"
)
#> ℹ No color column in the graphs: no colour kept (see `color_alluvial()`).
#> ℹ No cluster_label column in the graphs: no label kept (see `name_clusters()`).
if (requireNamespace("ggalluvial", quietly = TRUE)) {
  plot_alluvial(
    alluv_dt,
    cluster_id = "dynamic_cluster_leiden",
    node_id = "source_id",
    color_alluvial = TRUE,
    minimize_crossing = TRUE
  )
}
#> Warning: 15 categories but 14 default colours: colours are recycled.
#> ℹ Give a palette in `color` (e.g. `scico::scico(15, palette = "batlow")`).
#> Warning: no non-missing arguments to max; returning -Inf

# }