Python networkx.transitivity函数代码示例

def smallWorldness(graph):
	return_values = []
	#Small-worldness criteria
	n = len(nx.nodes(graph))
	e = len(nx.edges(graph))
	#probability of edges: (number of edges in real graph)/possible edges
	p = e/float((n*(n-1)/2.0))	
	##
	#generate random graph using probability
	rand_graph = nx.fast_gnp_random_graph(n, p, seed=1)
	#calculate values for real graph and random graph
	Creal = nx.transitivity(graph) #float
	Crand = nx.transitivity(rand_graph) #float
	Lreal = 0
	Lrand = 0
	real_sum = 0
	rand_sum = 0
	splReal = shortest_path_lengths(graph)
	splRand = shortest_path_lengths(rand_graph)
	for i in range(len(splReal)):
		real_sum += splReal[i]
		rand_sum += splRand[i]
	Lreal = real_sum / len(splReal)
	Lrand = rand_sum / len(splRand)		
	#compare with actual graph
	if(Lreal != 0 and Lrand !=0 and Crand !=0):
		S = (Creal)/(Crand) / (float(Lreal)/(Lrand))
	else:
		S = 0
	return_values.append(S)
	return return_values

def draw_graph(label_flag=True, remove_isolated=True, different_size=True, iso_level=10, node_size=40):
    G=build_graph(fb.get_friends_network())
    betweenness=nx.betweenness_centrality(G)
    degree=nx.degree_centrality(G)
    degree_num=[ degree[v] for v in G]
    maxdegree=max(degree_num);mindegree=min(degree_num);
    print maxdegree,mindegree
    clustering=nx.clustering(G)
    print nx.transitivity(G)
    # Judge whether remove the isolated point from graph
    if remove_isolated is True:
        H = nx.empty_graph()
        for SG in nx.connected_component_subgraphs(G):
            if SG.number_of_nodes() > iso_level:
                H = nx.union(SG, H)
        G = H
    # Ajust graph for better presentation
    if different_size is True:
        L = nx.degree(G)
        G.dot_size = {}
        for k, v in L.items():
            G.dot_size[k] = v
        #node_size = [betweenness[v] *1000 for v in G]
        node_size = [G.dot_size[v] * 10 for v in G]
        node_color= [((degree[v]-mindegree))/(maxdegree-mindegree) for v in G]
        #edge_width = [getcommonfriends(u,v) for u,v in G.edges()]
    pos = nx.spring_layout(G, iterations=15)
    nx.draw_networkx_edges(G, pos, alpha=0.05)
    nx.draw_networkx_nodes(G, pos, node_size=node_size, node_color=node_color, vmin=0.0,vmax=1.0, alpha=0.3)
    # Judge whether shows label
    if label_flag is True:
        nx.draw_networkx_labels(G, pos, font_size=6,alpha=0.1)
    #nx.draw_graphviz(G)
    plt.show()
    return G

def gen_graph_stats (graph):
	G = nx.read_graphml(graph)
	stats = {}

	edges, nodes = 0,0
	for e in G.edges_iter(): edges += 1
	for n in G.nodes_iter(): nodes += 1
	stats['Edges'] = (edges,'The number of edges within the Graph')
	stats['Nodes'] = (nodes, 'The number of nodes within the Graph')
	print "%i edges, %i nodes" % (edges, nodes)


	# Accessing the highest degree node
	center, degree = sorted(G.degree().items(), key=itemgetter(1), reverse=True)[0]
	stats['Center Node'] = ('%s: %0.5f' % (center,degree),'The center most node in the graph. Which has the highest degree')


	hairball = nx.subgraph(G, [x for x in nx.connected_components(G)][0])
	print "Average shortest path: %0.4f" % nx.average_shortest_path_length(hairball)
	stats['Average Shortest Path Length'] = (nx.average_shortest_path_length(hairball), '')
	# print "Center: %s" % G[center]

	# print "Shortest Path to Center: %s" % p


	print "Degree: %0.5f" % degree
	stats['Degree'] = (degree,'The node degree is the number of edges adjacent to that node.')

	print "Order: %i" % G.number_of_nodes()
	stats['Order'] = (G.number_of_nodes(),'The number of nodes in the graph.')

	print "Size: %i" % G.number_of_edges()
	stats['Size'] = (G.number_of_edges(),'The number of edges in the graph.')

	print "Clustering: %0.5f" % nx.average_clustering(G)
	stats['Average Clustering'] = (nx.average_clustering(G),'The average clustering coefficient for the graph.')

	print "Transitivity: %0.5f" % nx.transitivity(G)
	stats['Transitivity'] = (nx.transitivity(G),'The fraction of all possible triangles present in the graph.')

	part = community.best_partition(G)
	# values = [part.get(node) for node in G.nodes()]

	# nx.draw_spring(G, cmap = plt.get_cmap('jet'), node_color = values, node_size=30, with_labels=False)
	# plt.show()

	mod = community.modularity(part,G)
	print "modularity: %0.5f" % mod
	stats['Modularity'] = (mod,'The modularity of a partition of a graph.')

	knn = nx.k_nearest_neighbors(G)
	print knn
	stats['K Nearest Neighbors'] = (knn,'the average degree connectivity of graph.\nThe average degree connectivity is the average nearest neighbor degree of nodes with degree k. For weighted graphs, an analogous measure can be computed using the weighted average neighbors degre')


	return G, stats

def get_small_worldness(filename):
  import networkx as nx
  threshold = 0
  f = open(filename[:-4]+'_small_worldness.dat','w')
  for i in range(0,101):
    threshold = float(i)/100
    G = get_threshold_matrix(filename, threshold)
    ER_graph = nx.erdos_renyi_graph(nx.number_of_nodes(G), nx.density(G))

    cluster = nx.average_clustering(G)
    ER_cluster = nx.average_clustering(ER_graph)
    
    transi = nx.transitivity(G)
    ER_transi = nx.transitivity(ER_graph)

    print 'threshold: %f, average cluster coefficient: %f, random nw: %f, transitivity: %f, random nw: %f' %(threshold, cluster, ER_cluster, transi, ER_transi)

    f.write("%f\t%f\t%f" % (threshold, cluster, ER_cluster))
    components = nx.connected_component_subgraphs(G)
    ER_components = nx.connected_component_subgraphs(ER_graph)

    values = []
    ER_values = []
    for i in range(len(components)):
      if nx.number_of_nodes(components[i]) > 1:
        values.append(nx.average_shortest_path_length(components[i]))
    for i in range(len(ER_components)):
      if nx.number_of_nodes(ER_components[i]) > 1:
        ER_values.append(nx.average_shortest_path_length(ER_components[i]))
    if len(values) == 0:
      f.write("\t0.")
    else:
      f.write("\t%f" % (sum(values)/len(values)))

    if len(ER_values) == 0:
      f.write("\t0.")
    else:
      f.write("\t%f" % (sum(ER_values)/len(ER_values)))
    
    f.write("\t%f\t%f" % (transi, ER_transi))  
    
    if (ER_cluster*sum(values)*len(values)*sum(ER_values)*len(ER_values)) >0 :
      S_WS = (cluster/ER_cluster) / ((sum(values)/len(values)) / (sum(ER_values)/len(ER_values)))
    else:
      S_WS = 0.
    if (ER_transi*sum(values)*len(values)*sum(ER_values)*len(ER_values)) >0 :
      S_Delta = (transi/ER_transi) / ((sum(values)/len(values)) / (sum(ER_values)/len(ER_values)))
    else:
      S_Delta = 0.
    
    f.write("\t%f\t%f" % (S_WS, S_Delta))  
    f.write("\n")
    
  f.close()  
  print "1:threshold 2:cluster-coefficient 3:random-cluster-coefficient 4:shortest-pathlength 5:random-shortest-pathlength 6:transitivity 7:random-transitivity 8:S-Watts-Strogatz 9:S-transitivity" 

def get_small_worldness(G, thr):
	f = open(out_prfx + 'small_worldness.dat', 'a')
	g = open(out_prfx + 'cc_trans_ER.dat', 'a')
	#g.write('r(thre.)\t\cc_A\tcc_ER\ttran_A\ttran_ER\n')
	ER_graph = nx.erdos_renyi_graph(nx.number_of_nodes(G), nx.density(G))
	# erdos-renyi, binomial random graph generator ...(N,D:density)	
	cluster = nx.average_clustering(G)   # clustering coef. of whole network
	ER_cluster = nx.average_clustering(ER_graph)	#cc of random graph
	
	transi = nx.transitivity(G)
	ER_transi = nx.transitivity(ER_graph)

	g.write("%f\t%f\t%f\t%f\t%f\n" % (thr, cluster,ER_cluster,transi,ER_transi ))
	
	f.write("%f\t%f\t%f" % (thr, cluster, ER_cluster))
	components = nx.connected_component_subgraphs(G)
	ER_components = nx.connected_component_subgraphs(ER_graph)

	values = []
	ER_values = []
	for i in range(len(components)):
		if nx.number_of_nodes(components[i]) > 1:
			values.append(nx.average_shortest_path_length(components[i]))
	for i in range(len(ER_components)):
		if nx.number_of_nodes(ER_components[i]) > 1:
			ER_values.append(nx.average_shortest_path_length(ER_components[i]))
	if len(values) == 0:
		f.write("\t0.")
	else:
		f.write("\t%f" % (sum(values)/len(values))) # pathlenght

	if len(ER_values) == 0:
		f.write("\t0.")
	else:
		f.write("\t%f" % (sum(ER_values)/len(ER_values)))

	f.write("\t%f\t%f" % (transi, ER_transi))  

	if (ER_cluster*sum(values)*len(values)*sum(ER_values)*len(ER_values)) >0 :
		S_WS = (cluster/ER_cluster) / ((sum(values)/len(values)) / (sum(ER_values)/len(ER_values)))  
	else:
		S_WS = 0.
	if (ER_transi*sum(values)*len(values)*sum(ER_values)*len(ER_values)) >0 :
		S_Delta = (transi/ER_transi) / ((sum(values)/len(values)) / (sum(ER_values)/len(ER_values)))
	else:
		S_Delta = 0.

	f.write("\t%f\t%f" % (S_WS, S_Delta)) # S_WS ~ small worldness 
	f.write("\n")

	f.close() 
	g.close()	 

def printStats(filename):
	'''
	Converts json adjacency list into networkx to calculate and print the
	graphs's 
	  - average clustering coefficient
	  - overall clustering coefficient
	  - maximum diameter
	  - average diameter
	  - number of paritions using community.best_parition
	  - modularity of community.best_partition
	'''
	g = makeGraphFromJSON(filename)
	
	print "Average Clustering Coefficient: %f" % nx.average_clustering(g)
	print "Overall Clustering Coefficient: %f" % nx.transitivity(g)
	
	connected_subgraphs = list(nx.connected_component_subgraphs(g))
	largest = max(nx.connected_component_subgraphs(g), key=len)
	print "# Connected Components: %d" % len(connected_subgraphs)
	print "    Maximal Diameter: %d" % nx.diameter(largest)
	print "    Average Diameter: %f" % nx.average_shortest_path_length(largest)

	# Find partition that maximizes modularity using Louvain's algorithm
	part = community.best_partition(g)	
	print "# Paritions: %d" % (max(part.values()) + 1)
	print "Louvain Modularity: %f" % community.modularity(part, g)

def netstats_simple(graph):
    G = graph
    if nx.is_connected(G): 
        d = nx.diameter(G)
        r = nx.radius(G)
    else: 
        d = 'NA - graph is not connected' #should be calculatable on unconnected graph - see example code for hack
        r = 'NA - graph is not connected'
   
#using dictionary to pack values and variablesdot, eps, ps, pdf break equally
    result = {#"""single value measures"""  
              'nn': G.number_of_nodes(),
              'ne': G.number_of_edges(),
              'd': d,
              'r': r,
              'conn': nx.number_connected_components(G),
              'asp': nx.average_shortest_path_length(G), 
#              """number of the largest clique"""
              'cn': nx.graph_clique_number(G),
#              """number of maximal cliques"""
              'mcn': nx.graph_number_of_cliques(G),
#              """transitivity - """
              'tr': nx.transitivity(G),
              #cc = nx.clustering(G) """clustering coefficient"""
              'avgcc': nx.average_clustering(G) } 
#    result['d'] = nx.diameter(G)
    print result
    return result

def compute_singlevalued_measures(ntwk, weighted=True, calculate_cliques=False):
    """
    Returns a single value per network
    """
    iflogger.info("Computing single valued measures:")
    measures = {}
    iflogger.info("...Computing degree assortativity (pearson number) ...")
    try:
        measures["degree_pearsonr"] = nx.degree_pearsonr(ntwk)
    except AttributeError:  # For NetworkX 1.6
        measures["degree_pearsonr"] = nx.degree_pearson_correlation_coefficient(ntwk)
    iflogger.info("...Computing degree assortativity...")
    try:
        measures["degree_assortativity"] = nx.degree_assortativity(ntwk)
    except AttributeError:
        measures["degree_assortativity"] = nx.degree_assortativity_coefficient(ntwk)
    iflogger.info("...Computing transitivity...")
    measures["transitivity"] = nx.transitivity(ntwk)
    iflogger.info("...Computing number of connected_components...")
    measures["number_connected_components"] = nx.number_connected_components(ntwk)
    iflogger.info("...Computing average clustering...")
    measures["average_clustering"] = nx.average_clustering(ntwk)
    if nx.is_connected(ntwk):
        iflogger.info("...Calculating average shortest path length...")
        measures["average_shortest_path_length"] = nx.average_shortest_path_length(ntwk, weighted)
    if calculate_cliques:
        iflogger.info("...Computing graph clique number...")
        measures["graph_clique_number"] = nx.graph_clique_number(ntwk)  # out of memory error
    return measures

def get_motifs(filename):
  import networkx as nx
  from math import factorial
  threshold = 0
  f = open(filename[:-4]+'_motifs.dat','w')
  for i in range(0,101):
    threshold = float(i)/100
    G = get_threshold_matrix(filename, threshold)
    tri_dict = nx.triangles(G)
    summe = 0
    for node in tri_dict:
      summe += tri_dict[node]
    
    N = nx.number_of_nodes(G)
    ratio = summe / (3. * binomialCoefficient(N,3))
    
    transi = nx.transitivity(G)
    if transi > 0:
      triads = summe / transi 
      ratio_triads = triads / (3 * binomialCoefficient(N,3))
    else:
      triads = 0.
      ratio_triads = 0.
    
    print 'threshold: %f, number of triangles: %f, ratio: %f, triads: %f, ratio: %f' %(threshold, summe/3, ratio, triads, ratio_triads)
    f.write("%f\t%d\t%f\t%f\t%f\n" % (threshold, summe/3, ratio, triads, ratio_triads))
  f.close()
  print "1:threshold 2:#triangles 3:ratio-to-potential-triangles 4:triads 5:ratio-to-potential-triads"

    def connected_components(self):
        """
        Returns basic statistics about the connected components of the
        graph. This includes their number, order, size, diameter, radius,
        average clusttering coefficient, transitivity, in addition to basic
        info about the largest and smallest connected components.
        """
        cc_stats = {}
        cc = nx.connected_components(self.graph.structure)

        for index, component in enumerate(cc):
            cc_stats[index] = {}
            this_cc = cc_stats[index]

            this_cc["order"] = len(component)
            this_cc["size"] = len(self.graph.structure.edges(component))

            subgraph = self.graph.structure.subgraph(component)
            this_cc["avg_cluster"] = nx.average_clustering(subgraph)
            this_cc["transitivity"] = nx.transitivity(subgraph)

            eccentricity = nx.eccentricity(subgraph)
            ecc_values = eccentricity.values()
            this_cc["diameter"] = max(ecc_values)
            this_cc["radius"] = min(ecc_values)

        return cc_stats

def plot_distribution(distribution_type,legend,graph,list_communities,out=None):
	x = [i for i in range(0,len(list_communities[0]))]
	for communities in list_communities:
		if distribution_type.lower() == "nodes":
			y = list(map(len,communities))
		else:
			y = []
			for l in communities:
				H = graph.subgraph(l)
				if distribution_type.lower() == "density":
					y.append(nx.density(H))
				elif distribution_type.lower() == "transitivity":
					y.append(nx.transitivity(H))
				else:
					return None
		plt.plot(x,y,linewidth=2,alpha=0.8)
		#plt.yscale("log")

	plt.legend(legend, loc='upper left')
	plt.xlabel("Comunity ID")
	plt.ylabel(distribution_type)

	if out == None:
		plt.show()
	else:
		plt.savefig(out+".svg",bbox_inches="tight")
	plt.close()

def get_network_property(graph):
    """Returns various property of the graph.

    It calculates the richness coefficient, triangles and transitivity
    coefficient. To do so, it removes self-loops *in-place*. So, there
    is a possibility that the graph passed as parameter has been
    changed.
    """

    remove_self_loop(graph)

    # If number of nodes is less than three
    # no point in calculating these property.
    if len(graph.nodes()) < 3:
        return ({0: 0.0}, 0, 0)

    try:
        richness = nx.rich_club_coefficient(graph)
    except nx.NetworkXAlgorithmError:
        # NetworkXAlgorithmError is raised when
        # it fails achieve desired swaps after
        # maximum number of attempts. It happened
        # for a really small graph. But, just to
        # guard against those cases.
        richness = nx.rich_club_coefficient(graph, False)

    triangle = nx.triangles(graph)
    transitivity = nx.transitivity(graph)

    return (richness, triangle, transitivity)

def degree_statistics(G):
    n_nodes = G.number_of_nodes()
    
    start = time.clock()
    # list of sampled graphs
    g_list[:] = []
    for i in range(N_SAMPLES):
        g_list.append(generate_sample(G))
    print "Sampling graphs - Elapsed ", (time.clock() - start)
    
    #####
    # number of edges s_NE
    s_NE = sum(e[2]['p'] for e in G.edges_iter(data=True))
    
    # average degree s_AD
    s_AD = 2*s_NE /n_nodes
    
    # maximal degree s_MD
    sum_MD = 0.0
    for aG in g_list:
        max_deg = max(aG.degree().itervalues())
        sum_MD += max_deg
        
    s_MD = sum_MD/N_SAMPLES
    
    # degree variance s_DV
    sum_DV = 0.0
    for aG in g_list:
        deg_var = 1.0/n_nodes * sum((d - s_AD)*(d-s_AD) for d in aG.degree().itervalues())
        sum_DV += deg_var
    
    s_DV = sum_DV/N_SAMPLES
    
    # clustering coefficient s_CC
    sum_CC = 0.0
    for aG in g_list:
        cc = nx.transitivity(aG)
        sum_CC += cc
    
    s_CC = sum_CC/N_SAMPLES
    
    # degree distribution
    deg_list = [0 for i in range(MAX_DEG)]
    for aG in g_list:
        for d in aG.degree().itervalues():
            deg_list[d] += 1
            
    i = MAX_DEG-1
    while deg_list[i] == 0:
        i = i-1
    deg_list = deg_list[:i+1]
    print "len(deg_list) =", len(deg_list)
    print deg_list
    
    for i in range(len(deg_list)):
        deg_list[i] = float(deg_list[i])/N_SAMPLES
    
    #
    return s_NE, s_AD, s_MD, s_DV, s_CC, deg_list

def cluster():
	if created == 0:
		print 'No graph created!'
	elif created == 1:
		try:
			print 'The clustering coefficient for the whole graph is %0.4f.'%(nx.transitivity(G))
		except nx.NetworkXError, e:
			print e

def preferentialAttachment(G):
    n = G.number_of_nodes()
    m =  random.randrange(15,20)
    PG = nx.barabasi_albert_graph(n,m)
    plot(PG)
    l =  math.log(n)/math.log(math.log(n))
    print 'Global Clustering: {0}\t'.format(str(nx.transitivity(PG))),
    print 'Average path length : {0}\n'.format(str(l))