SAS Institute. The Power to Know

SAS/GRAPH(R) 9.2: Network Visualization Workshop Help

Main Steps for Visualizing Network Data

SAS/GRAPH Network Visualization Workshop assumes that the network to be investigated is described by two data sets:
  • One data set contains information about the nodes in the network.
  • A second data set contains information about the links that connect the nodes.
For information about these data sets, see About Data Sources . If only link data is available, you can generate a simple node data set from the link data.
There are multiple ways to investigate network data, and your approach can vary from what is described here. In general though, a typical session might consist of the following steps:
  1. Load your node and link data into SAS/GRAPH Network Visualization Workshop.
  2. Use the Edit Data Attributes dialog box to identify the FROM and TO variables in the link data set and the NODE variable in the node data set. When you set data attributes, you can also specify which variables to use for link colors as well as for node colors, shapes, and labels.
  3. Create one or more statistical graphs to see standard relational views of node and link data separately. Each statistical graph is based on node or link data.
  4. Create one or more network graphs to see the network of nodes and links. You choose from several layout patterns when you create a network graph. You might not initially be aware of any underlying structure in your data. It can be helpful to try multiple layout patterns to determine which are the most useful for the network being investigated. After creating the graph, you can later change its layout.
  5. Explore and investigate your data. You can investigate data in the following ways:
    • Explore and manipulate data in the data tables, for example, by sorting the data.
    • Use a combination of statistical graphics, network graphs, and data tables to selectively view and filter your data. To filter the data, select individual observations or groups of observations in a data table or in a graph. The observations are automatically selected in all graphs and data tables. You can also use local selection mode to graphically subset data at multiple levels.
    • Use the tools available to help visualize the graphs. For example, you can zoom in on a portion of a graph or apply a magnifying lens to a network graph. You can also show the labels for particular nodes in a network graph.
  6. You might want to change the appearance and behaviors associated with a graph by changing the graph's properties. For example, the properties of a statistical graph determine the graph's colors, whether and where the graph displays titles or a legend, and more.
  7. Save your data as a project so that you can easily reopen the data tables and associated graphs.