Used for selecting "the most important" part of the network. This is based on the graph algorithms. Network generalization is applied if method=network. The algorithm calculates three centrality measures for each line in the network and only the lines with the values greater than thresholds are selected.

The behaviour of algorithm can be altered by the following parameters: * degree_thresh - algorithm selects only the lines which share a point with at least degree_thresh different lines. * closeness_thresh - is always in the range (0, 1]. Only the lines with the closeness centrality value at least closeness_thresh apart are selected. The lines in the centre of a network have greater values of this measure than the lines near the border of a network. This means that this parameter can be used for selecting the centre(s) of a network. Note that if closeness_thresh=0 then everything is selected. * betweeness_thresh - Again, only the lines with a betweeness centrality measure at least betweeness_thresh are selected. This value is always positive and is larger for large networks. It denotes to what extent a line is in between the other lines in the network. This value is large for the lines which lie between other lines and lie on the paths between two parts of a network. In the terminology of road networks, these are highways, bypasses, main roads/streets, etc.

All three parameters above can be presented at the same time. In that case, the algorithm selects only the lines which meet each criterion. Also, the outputed network may not be connected if the value of betweeness_thresh is too large.