Python networkx.read_edgelist函数代码示例

def gen_random_graphs(seed, db):
    
    print "generating random graph with seed " + str(seed)
    directory = db.get_rnd_graphs_path()
    if not path.exists(directory):
        makedirs(directory)
    
    filename = db.get_rnd_graph_full_name(str(seed), str(db.get_final_time()))
    if(path.exists(filename)):
        print "random graph with seed " + str(seed) + " already exists! Skipping..."
        return

    
    pathD = db.get_graphs_path()
    filename = pathD + db.get_windowed_graph_name(0)
    G=nx.read_edgelist(filename, nodetype = int, data=(('weight',float),))
    GR = get_random_graph_from(G, seed)
    save_random_graph(GR,1, db)
    
    for i in range(2,db.get_final_time()+1):
        filename = pathD + db.get_windowed_graph_name(str(i))
        if(not path.exists(filename)):
            f = open(filename,'w')
            f.close()
            
        G=nx.read_edgelist(filename, nodetype = int, data=(('weight',float),))
        GRnew = get_random_graph_from(G, seed)
        GR.graph['nmerges'] = i-2
        GR = merge_temporal_graphs(GR, GRnew)
        GR = compute_edge_features(GR)
        save_random_graph(GR,i, db)
    
        print("G_RND[" + str(i)  + "] has " + str(GR.number_of_edges()) + " edges")

def gen_random_graphs(seed):
    
	# create windowed random graphs for each real graph
	# obtain aggreggated graph
	# calculate features of random graph

	print "GENERATING RANDOM GRAPHS"

	day = 1
	final_day = which_day(_maxtime)+1

	filename = str(results_folder) + "Graphs_Data/windowed_graph_" + str(day) + str(".txt")

	print filename 

	G = nx.read_edgelist(filename, nodetype = int, data = (('top',float),))

	# print G 

	GR = get_random_graph_from(G, seed)

	for i in range(2,final_day):
		day = i
		filename = str(results_folder) + "Graphs_Data/windowed_graph_" + str(day) + str(".txt")
		G = nx.read_edgelist(filename, nodetype = int, data = (('top',float),))
		GRnew = get_random_graph_from(G, seed)
		GR.graph['nmerges'] = i - 2
		GR = merge_temporal_graphs(GR, GRnew)
		GR = compute_edge_features(GR)
		save_random_graph(GR,i,seed)

def incorrectness_uncertain_from_file(before_file, after_file, sample_file, n_samples, bins): 
    
    # compute sig_list_b, bucket_list_b ONCE !
    start = time.clock()
    bG = nx.read_edgelist(before_file, '#', '\t', None, nodetype=int)
#    G = nx.read_edgelist(after_file, '#', '\t', None, nodetype=int, data=True)
    print "read bG: DONE, elapsed :", time.clock() - start
    
    h2_list = equivalence_class_H2_open(bG, None)
    cand_size, bin_size, sig_list_b, bucket_list_b = bucket_H2(h2_list, bins)
#    print "len B:", len(sig_list_b), len(bucket_list_b)
    
    # H1 score, H2 score
    start = time.clock()
    score_H1 = 0.0
    score_H2 = 0.0
    count = 0
    for i in range(n_samples):
        file_name = sample_file + str(i)
        aG = nx.read_edgelist(file_name, '#', '\t', create_using=nx.MultiGraph(), nodetype=int, data=False)     # IMPORTANT: MultiGraph
        # H1
        sum_re_prob, re_prob_dict = incorrectness_H1(bG, aG, bins)
        score_H1 += sum_re_prob
        # H2
        sum_re_prob, re_prob_dict = incorrectness_H2_open(aG, sig_list_b, bucket_list_b, bins)
        score_H2 += sum_re_prob
        print "count =", count
        count += 1
    #
    score_H1 = score_H1/n_samples
    score_H2 = score_H2/n_samples
    print "compute score_H1, score_H2: DONE, elapsed :", time.clock() - start
    
    # 
    return score_H1, score_H2

def loadNwU(dsName, path, cd, wccOnly, revEdges, undir):
    print("   Opening " + dsName + " and loading graph... ")
    t1 = time.clock()
    fh = open(path + dsName, "rb")
    if undir:
        if cd:
            prodNet = nx.read_edgelist(fh, delimiter=",")
        else:
            prodNet = nx.read_edgelist(fh)
            # prodNet = prodNet.to_directed()
    else:
        if cd:
            prodNet = nx.read_edgelist(fh, delimiter=",", create_using=nx.DiGraph())
        else:
            prodNet = nx.read_edgelist(fh, create_using=nx.DiGraph())

    fh.close()
    if wccOnly:
        prodNet = nx.algorithms.weakly_connected.weakly_connected_component_subgraphs(prodNet)[0]

    prodNet.remove_edges_from(prodNet.selfloop_edges())

    if revEdges:
        prodNet.reverse(False)

    numNodes = str(prodNet.__len__())
    numEdges = str(prodNet.size())
    t2 = time.clock()
    print("    -> graph loaded: " + numNodes + " nodes, " + numEdges + " edges (" + str(t2 - t1) + " sec).")
    return prodNet

def k_obfuscation_measure(before_file, after_file, n_nodes, k_arr, data=True):
    print "n_nodes =", n_nodes
    
    # before_file
    bG = nx.read_edgelist(before_file, '#', '\t', None, nodetype=int)
    print "read bG - DONE"
    
#    if bG.number_of_nodes() < n_nodes:
#        bG.add_nodes_from(range(n_nodes))       # only for er_100k

    # Case 1 - aG = bG
    if after_file == before_file:      # after_file is before_file
        for e in bG.edges_iter():
            bG[e[0]][e[1]]['p'] = 1.0
        return compute_eps_multi(bG, bG, k_arr) 
        
    # Case 2 - aG is a sample
    # after_file
    if data == True:
        aG = nx.read_edgelist(after_file, '#', '\t', None, nodetype=int, data=True)
    else:
        aG = nx.read_edgelist(after_file, '#', '\t', None, nodetype=int, data=False)
#        if aG.number_of_nodes() < n_nodes:
#            aG.add_nodes_from(range(n_nodes))       # only for the cases of KeyError !
        for e in aG.edges_iter():
            aG[e[0]][e[1]]['p'] = 1.0
    print "read aG - DONE"
    
    return compute_eps_multi(bG, aG, k_arr) 

def main():
    """
    Pre-processing: 
        load data, compute centrality measures, write files with node data
    """
    print(nx.__version__)
    # Load network data, create storage dict, and extract main component
    depends=nx.read_edgelist("data/depends.csv",delimiter=",",create_using=nx.DiGraph(),nodetype=str,data=(("weight",time_from_today),))
    depends.name="depends"
    suggests=nx.read_edgelist("data/suggests.csv",delimiter=",",create_using=nx.DiGraph(),nodetype=str,data=(("weight",time_from_today),))
    suggests.name="suggests"
    imports=nx.read_edgelist("data/imports.csv",delimiter=",",create_using=nx.DiGraph(),nodetype=str,data=(("weight",time_from_today),))
    imports.name="imports"
    nets_dict={"depends":depends,"suggests":suggests,"imports":imports}
    for k in nets_dict.keys():
        main_component=nx.connected_component_subgraphs(nets_dict[k].to_undirected())[0].nodes()
        nets_dict[k]=nx.subgraph(nets_dict[k],main_component)
    
    # Run multiple measures on graphs and normalize weights
    measure_list=[nx.in_degree_centrality,nx.betweenness_centrality,nx.pagerank]
    for g in nets_dict.values():
        multiple_measures(g,measure_list)
        normalize_weights(g)
        
    # Output networks in GraphML format (to store node attributes)
    for i in nets_dict.items():
        # print(i[1].edges(data=True))
        nx.write_graphml(i[1],"data/"+i[0]+"_data.graphml")
        print("")
    print("All files written with data")
    
    """Visualization:

def main():
    parser = createParser()
    options = parser.parse_args()

    gtGraphNames = glob.glob("{0}/*.sim.cut".format(options.gtruth))
    gtGraphs = { fn.split("/")[-1][:-8] : nx.read_edgelist(fn) for fn in gtGraphNames }
    print(gtGraphs)
    print(gtGraphNames)

    oGraphNames = [ "{0}/{1}.out.ppi".format(options.other, k) for k in gtGraphs.keys() ]
    oGraphs = { fn.split("/")[-1][:-8] : nx.read_weighted_edgelist(fn) for fn in oGraphNames }
    inputGraphNames = glob.glob("{0}/bZIP*.cut".format(options.other))
    print(inputGraphNames)
    inputGraph = nx.read_edgelist(inputGraphNames[0])
    print(oGraphNames)

    cutoff = 0.99
    paranaGraph = graphWithCutoff(options.parana, 0.0)
    c = findSuggestedCutoff( paranaGraph, inputGraph, cutoff )
    evaluation.printStats( filteredGraph(paranaGraph, inputGraph.nodes(), cutoff=c ), inputGraph )
    print >>sys.stderr, "Parana 2.0    : {0}".format(getCurve(paranaGraph, inputGraph))



    for gtName, gtGraph in gtGraphs.iteritems():
        print(gtName)
        c = findSuggestedCutoff( paranaGraph, gtGraph, cutoff )
        print("Parana cutoff = {0}".format(c))
        print("==================")
        evaluation.printStats( filteredGraph(oGraphs[gtName], gtGraph.nodes()), gtGraph )
        print >>sys.stderr, "Pinney et. al : {0}".format(getCurve(oGraphs[gtName], gtGraph))
        evaluation.printStats( filteredGraph(paranaGraph, gtGraph.nodes(), cutoff=c ), gtGraph )
        print >>sys.stderr, "Parana 2.0    : {0}".format(getCurve(paranaGraph, gtGraph))
        print("\n")
    sys.exit(0)

def graph_properties(filename, directed=False):
  # Read in rec as undirected graph
  if directed:
    G=nx.read_edgelist(filename, nodetype=int, create_using=nx.DiGraph())
  else:
    G=nx.read_edgelist(filename, nodetype=int, create_using=nx.Graph())

  props = {}

  # Calculate number of edges
  props['num_edges'] = G.number_of_edges()

  # Calculate number of nodes
  props['num_nodes'] = len(G)

  # Calculate largest connected component
  largest_component = nx.connected_component_subgraphs(G)[0]
  props['size_largestcc'] = len(largest_component)
  props['proportion_in_largestcc'] = float(len(largest_component)) / len(G)

  # Calculate clustering coefficient
  props['average_clustering'] = nx.average_clustering(G)

  # Calculate diameter of largest connected component
  # props['diameter'] = nx.diameter(largest_component)
  
  return props

def calGraph(infile, mode = 1):
	#init Parameter
	inputpath = 'edge_list/'
	outputpath = 'network_output/'
	n = mode
	Data_G = inputpath+infile+'_'+str(n)+'.edgelist'
	
	#init Graph
	G = nx.read_edgelist(Data_G, create_using=nx.DiGraph())
	GU = nx.read_edgelist(Data_G)
	#basci info
	print nx.info(G),'\n', nx.info(GU) 
	average_degree = float(sum(nx.degree(G).values()))/len(G.nodes())
	print 'average degree :', average_degree 
	degree_histogram = nx.degree_histogram(G)
	print 'degree histogram max :', degree_histogram[1]
	desity = nx.density(G)
	print 'desity :', desity

	#Approximation
	#Centrality
	degree_centrality = nx.degree_centrality(G)
	print 'degree centrality top 10 !', sorted_dict(degree_centrality)[:2]
	out_degree_centrality = nx.out_degree_centrality(G)
	print 'out degree centrality top 10 !', sorted_dict(out_degree_centrality)[:2]

    def load(self,fname):
        fext = (str(fname).split("."))[1]
        self.fname = (str(fname).split("."))[0]

        if self.directed_graph == False:
            self.G = nx.read_edgelist(path=fname)
        else:
            self.G = nx.read_edgelist(path=fname,create_using=nx.DiGraph())

 def test_edgelist_integers(self):
     G=nx.convert_node_labels_to_integers(self.G)
     (fd,fname)=tempfile.mkstemp()
     nx.write_edgelist(G,fname)  
     H=nx.read_edgelist(fname,nodetype=int)
     H2=nx.read_edgelist(fname,nodetype=int)
     G.remove_node(5) # isolated nodes are not written in edgelist
     assert_equal(sorted(H.nodes()),sorted(G.nodes()))
     assert_equal(sorted(H.edges()),sorted(G.edges()))
     os.close(fd)
     os.unlink(fname)

 def test_edgelist_multidigraph(self):
     G = self.XDG
     (fd, fname) = tempfile.mkstemp()
     nx.write_edgelist(G, fname)
     H = nx.read_edgelist(fname, nodetype=int, create_using=nx.MultiDiGraph())
     H2 = nx.read_edgelist(fname, nodetype=int, create_using=nx.MultiDiGraph())
     assert_not_equal(H, H2)  # they should be different graphs
     assert_nodes_equal(list(H), list(G))
     assert_edges_equal(list(H.edges()), list(G.edges()))
     os.close(fd)
     os.unlink(fname)

 def test_edgelist_digraph(self):
     G = self.DG
     (fd, fname) = tempfile.mkstemp()
     nx.write_edgelist(G, fname)
     H = nx.read_edgelist(fname, create_using=nx.DiGraph())
     G.remove_node('g')  # isolated nodes are not written in edgelist
     H2 = nx.read_edgelist(fname, create_using=nx.DiGraph())
     assert_not_equal(H, H2)  # they should be different graphs
     assert_nodes_equal(list(H), list(G))
     assert_edges_equal(list(H.edges()), list(G.edges()))
     os.close(fd)
     os.unlink(fname)

 def test_edgelist_graph(self):
     G=self.G
     (fd,fname)=tempfile.mkstemp()
     nx.write_edgelist(G,fname)  
     H=nx.read_edgelist(fname)
     H2=nx.read_edgelist(fname)
     assert_not_equal(H,H2) # they should be different graphs
     G.remove_node('g') # isolated nodes are not written in edgelist
     assert_equal(sorted(H.nodes()),sorted(G.nodes()))
     assert_equal(sorted(H.edges()),sorted(G.edges()))
     os.close(fd)
     os.unlink(fname)

def calGraph(infile, mode = 1):
	#init Parameter
	inputpath = 'edge_list/'
	n = mode
	Data_G = inputpath+infile+'_'+str(n)+'.edgelist'
	
	#init Graph
	G = nx.read_edgelist(Data_G, create_using=nx.DiGraph())
	GU = nx.read_edgelist(Data_G)
	average_clustering = nx.average_clustering(GU)
	transitivity = nx.transitivity(G)
	return [average_clustering, transitivity]