DOCUMENTATION
Sign In

Get access to My SAS, trials, communities and more.

Data Mining and Machine Learning: The NETWORK Procedure
 

The NETWORK Procedure

CONNECTEDCOMPONENTS Statement

  • CONNECTEDCOMPONENTS < options >;

The CONNECTEDCOMPONENTS statement invokes an algorithm that finds the connected components of the input graph. For more information about connected components, see the section Connected Components. You can specify the following options:

ALGORITHM=AUTOMATIC | DFS | PARALLEL | UNIONFIND

specifies the algorithm to use for calculating connected components. You can specify the following values:

AUTOMATIC

uses the union-find algorithm for undirected graphs and the depth-first search algorithm for directed graphs.

DFS

uses the depth-first search algorithm for connected components.

PARALLEL

uses the distributed parallel union-find algorithm for connected components. You can specify this value when the number of machines in your session is greater than 1. You can use this algorithm only with undirected graphs. You can also enable this functionality by specifying DISTRIBUTED=TRUE in the PROC NETWORK statement.

UNIONFIND

uses the union-find algorithm for connected components. You can use this algorithm only with undirected graphs.

By default, ALGORITHM=UNIONFIND for undirected graphs, and ALGORITHM=DFS for directed graphs.

OUT=CAS-libref.data-table

specifies the output data table to contain the connected components summary results. CAS-libref.data-table is a two-level name, where CAS-libref refers to the caslib and session identifier, and data-table specifies the name of the output data table. For more information about this two-level name, see the section Using CAS Sessions and CAS Engine Librefs in Chapter 1, Introduction.

Last updated: June 11, 2021