Hierarchical edge bundling | the R Graph Gallery

What is hierarchical edge bundling?

The following post will guide you through the basics of hierarchical edge bundling. It explains what this kind of chart really is, describing step by step how to build it in R with the graph package.

Start with a hierarchical network

Hierarchical Edge Bundling is based on a hierarchy. An original node gives underlying nodes and so on. Final nodes are called leaves, displayed around the circle.

Draw a connection

The second required level is connection, stored in another dataset. Leaves are connected with curves instead of straight lines.

Most Basic Edge Bundling

This is the most basic hierarchical edge bundling you can build. It displays many connection between leaves.

Input data

You need at least 2 inputs for hierarchical edge bundling:

A hierarchical network structure, also called tree
An adjacency matrix that describes connections between some nodes of the tree

Connections data frame:

Hierarchical network data frame:

Node and Connection color

You can customize node and connection features to add more insight to the chart. For instance, you can change node color to highlight their belonging to a group, or connection color to represent its intensity

Uniform color

You can use one unique color for all connections

Color depending on value or index

Color can also depends on value to represent the strength of the connection, or on the the node index.

Custom nodes

Change node features to display one more level of information on the chart

Add node labels

Last but not least, it is crucial to add labels to chart nodes. This is a bit tricky since label alignment and orientation must be computed by hand. This last example will teach you how to proceed, resulting in the figure below.

Code