When applying network analysis methods, many types of data can naturally be represented as a bipartite network. That is, a network that has two sets of nodes, such that edges can only connect nodes in opposite sets, and nodes from the same set cannot be connected.
For example, we could construct a network representation from the Rugby World Cup 2019 squad data, as extracted from Wikipedia. Specifically, we could look at the relationship between countries and club teams, which has often been a source of tension in the sport. In this network, each node either represents a country or a club team. An edge connects a country to a club if one or more players in that country's squad plays their club rugby for that team. The weight on that edge indicates the number of players in question.
This network is shown in the visualisation below, which was generated using the webweb tool and the Python NetworkX package. There are 166 nodes, corresponding to 20 countries with players distributed among 146 clubs - these are connected by 237 edges. As we can see in the network, the lower tier countries tend have players spread among many clubs, sometimes spread across multiple countries. Many of the club teams from the English Premiership and the French Top 14 have players from a diverse range of countries. Also, we clearly see that there are only two connected components in the network. The large component represents 19 of the 20 countries participating in the tournament. The second component contains only Ireland, connected to the four provincial teams - this separation reflects the IRFU's policy on foreign-based players. A labelled static visualisation of the network, produced with Gephi, is available here.