Relationship

Force-directed network

Arranges a node-link network using attractive and repulsive layout forces.

Diagram
Relationship
Clustering

What it answers

What clusters or hubs appear in a network layout?

Shape: Nodes positioned by simulated forces
What it shows: Connectivity patterns and candidate communities.

Example

The question

Which groups form naturally among our customers who buy together?

Customers linked by shared purchases (force-directed layout)

Points pulled together by their links settle into three clusters of eight customers, coloured by group, with only three links between groups. Position has no scale; only closeness matters.

Illustrative data. It belongs to no company.

When to use it

Use it when

Exploratory network browsing.

Avoid it when

When a stable metric coordinate system is needed.

How to read it

Inspect links and highlighted neighbourhoods rather than absolute node distances.

Note

Layout distance is not automatically a measured relationship strength.

The data you need

Layout: Edge list plus node table
Fields: Source: text ID; Target: text ID; optional Weight: number
One row is: One relationship between two nodes. What is the grain?
Rules: Declare directed or undirected links. Handle duplicate edges and self-loops intentionally.
Optional: Separate Nodes table: NodeID,Label,Type. Include isolated nodes there.
Preparation: Resolve node identities and endpoint joins; define direction and duplicate/self-link handling. Aggregate weights only under a stated relationship or flow definition.
Units: Unweighted links encode presence. Weights need a unit; flow shares divide by stated source, destination or network totals, not an assumed common denominator.

An edge list: one row per link, from one node to another, often with a node table beside it.

Worked example

Edges A-B, A-C, B-C form a tight linked group under a force layout. The layout alone does not prove a statistical cluster.

Source	Target
A	B
A	C
B	C

All charts in the library