digraph.create_indices()
graph = BigGraph(graphfile + '.disconnected')
print 'digraph.add_only_symmetric_edgelist(graph) ...'
digraph.add_only_symmetric_edgelist(graph)
print 'graph.create_indices() ...'
graph.create_indices()
number_of_nodes = graph.number_of_nodes()
comps = [
len(comp) / float(number_of_nodes)
for comp in graph.connected_components()
]
if comps[0] < 0.5:
print 'ERROR: biggest connected componnet not found!'
exit(-1)
print 'input DiGraph:'
print 'nodes = %d' % digraph.number_of_nodes()
print 'edges = %d' % digraph.number_of_edges()
print 'output Graph (possibly disconnected):'
print 'nodes = %d' % graph.number_of_nodes()
print 'edges = %d' % graph.number_of_edges()
print 'connected components fractions: %s' % str(comps)
digraph.erase_from_disk()
filename = len(sys.argv) > 1 and sys.argv[1] or None
if not filename:
#filename = 'orkut-links-fst.txt.toundirected.30mill'
print 'Error: first argument missing, input filename with space separated graph!'
exit(-1)
outname = len(sys.argv) > 2 and sys.argv[2] or None
if not outname:
#outname = 'orkut-2k_sym.big_graph'
print 'Error: second argument missing, output filename!'
exit(-1)
graphfile = filename
graph = BigGraph(graphfile)
graph.debug = True
graph.input_debug_links = 200000
graph.output_debug_nodes = 10000
print 'NODES:'
print graph.number_of_nodes()
print 'EDGES:'
print graph.number_of_edges()
print 'dumping Graph to edge list file ...'
graph.save_edgelist(outname)
print 'done.'
if not outname:
print 'Error: second argument missing, output filename for BigGraph!'
exit(-1)
graph = BigGraph(filename)
#graph = BigGraph()
#graph.add_edge(1,2)
#graph.add_edge(2,3)
#graph.add_edge(3,1)
#graph.add_edge(4,5)
aux_graph = Graph()
connected_graph = BigGraph(outname)
graph.add_random_component(aux_graph)
for src, dst in aux_graph.edges_iter():
connected_graph.add_edge(src, dst)
connected_graph.create_indices()
print 'input Graph:'
print 'nodes = %d' % graph.number_of_nodes()
print 'edges = %d' % graph.number_of_edges()
print 'output connected Graph:'
print 'nodes = %d' % connected_graph.number_of_nodes()
print 'edges = %d' % connected_graph.number_of_edges()
