Python Graph.simplify方法代码示例

# 需要导入模块: from igraph import Graph [as 别名]
# 或者: from igraph.Graph import simplify [as 别名]
class Physic (BaseInputGraph):
  def __init__(self):
    '''
    @return: Arxiv ASTRO-PH (Astro Physics) collaboration network as iGraph graph instance 
    '''
    edges = []
    weights = []
    f = open("./physic/compact-physic.txt", "r")
    for line in f:
      if line and line[0]!='#':
        seg = line.split()
        edges.append( (int(seg[0]), int(seg[1])) )
        weights.append( 1 )
    maxid = max( edges, key=itemgetter(1) )[1]
    maxid = max( maxid, max(edges,key=itemgetter(0))[0] )
    self.g = Graph()
    self.g.add_vertices(maxid + 1)
    self.g.add_edges(edges)
    self.g.to_undirected()
    self.g.simplify()
    self.g.vs["myID"] = [ str(int(i)) for i in range(maxid+1)]
    print "#nodes=", maxid + 1
    print "#edges=", len(self.g.es)

  def run(self):
    C = BaseInputGraph.unsupervised_logexpand(self)
    BaseInputGraph.run(self, C, p0=np.array([0.04, 0.04]))
    with open("./physic/Physic_weights.pairs", "w+") as txt:
      for e in self.g.es:
        txt.write("%d %d %f\n" %(e.tuple[0], e.tuple[1], e["weight"]) )

# 需要导入模块: from igraph import Graph [as 别名]
# 或者: from igraph.Graph import simplify [as 别名]
def merge(g1,g2):
	""" merges graph g1 and graph g2 into the output graph"""
	g3nslst = list(set(g1.vs['name'][:]) | set(g2.vs['name'][:])) 
	g3 = Graph(0,directed=True)
	g3.add_vertices(g3nslst)
	g3elst = []
	for e in g1.get_edgelist():
		g3elst.append((g1.vs['name'][e[0]],g1.vs['name'][e[1]]))
	for e in g2.get_edgelist():
		g3elst.append((g2.vs['name'][e[0]],g2.vs['name'][e[1]]))
	g3.add_edges(g3elst)
	g3.simplify()
	#add attributes
	g1primlst = [vn for i,vn in enumerate(g1.vs['name'][:]) if int(g1.vs['inprim'][i]) == 1]
	g2primlst = [vn for i,vn in enumerate(g2.vs['name'][:]) if int(g2.vs['inprim'][i]) == 1]
	g3prim = [1 if vn in g1primlst or vn in g2primlst else 0 for vn in g3.vs['name'][:]]
	g3pnamelst = [[] for i in range(len(g3.vs['name'][:]))]
	for i,vn1 in enumerate(g3.vs['name'][:]):
		for j,vn2 in enumerate(g1.vs['name'][:]):
			if vn1 == vn2:
				g3pnamelst[i].extend(g1.vs['pnamelst'][j].strip().split('|'))
		for j,vn2 in enumerate(g2.vs['name'][:]):
			if vn1 == vn2:
				g3pnamelst[i].extend(g2.vs['pnamelst'][j].strip().split('|'))
	g3.vs['pnamelst'] = ['|'.join(map(str,list(set(inp)))) if inp != [] else '' for inp in g3pnamelst]
	#print g1.vs['pnamelst'][:]	
	#print g3.vs['name'][:]
	g3.vs['inprim'] = g3prim
	return g3

# 需要导入模块: from igraph import Graph [as 别名]
# 或者: from igraph.Graph import simplify [as 别名]
class LFR ( BaseInputGraph ):
  def __init__(self, trialval=1):
    ws = []
    edges = []
    self.trial = trialval
    with open("./binary_networks/mu0.5/network%d.dat" % self.trial, "r") as txt:
      for line in txt:
        seg = line.split()
        edges.append((int(seg[0]), int(seg[1])))
        ws.append(1)
    maxid = max( edges, key=itemgetter(1))[1]
    maxid = max( maxid, max(edges,key=itemgetter(0))[0] )
    self.g = Graph()
    print maxid
    self.g.add_vertices(maxid + 1)
    with open("./binary_networks/mu0.5/community%d.dat" % self.trial, "r") as txt:
      for line in txt:
        seg = line.split()
        #print seg[0]
        self.g.vs[int(seg[0])]["comm"] = seg[1] #note: string is returned
    self.g.add_edges(edges)
    self.g.to_undirected()
    self.g.simplify()
    self.g.delete_vertices(0)
    self.g.es["weight"] = ws
    BaseInputGraph.write_ground_truth(self, "./ground_truth_community%d.groups" % self.trial)
    print "#nodes=", maxid + 1
    print "#edges=", len(self.g.es) 

  def run(self):
    #supervised
    C = []
    for i in range(6):
      commval = str(random.randint(0,100))
      group = [i for i, comm in enumerate(self.g.vs["comm"]) if comm == commval]
      C += BaseInputGraph.get_C(self, group)
    #unsupervised
    C = BaseInputGraph.unsupervised_logexpand(self)
    BaseInputGraph.run(self, C, p0=np.array([1 , 1]))
    BaseInputGraph.results(self, Graph.community_fastgreedy, hasgnc = False,\
     filename="%d" %self.trial)

# 需要导入模块: from igraph import Graph [as 别名]
# 或者: from igraph.Graph import simplify [as 别名]
def graph_from_sparse(data, directed=None):
    from igraph import Graph
    sources, targets = data.nonzero()
    
    if directed==None:
        from numpy import all
        directed = not all(data[sources, targets]==data[targets, sources])
    from numpy import array
    g = Graph(zip(sources, targets), directed=directed, edge_attrs={'weight': array(data[sources, targets])[0]})
    if g.is_directed():
        return g
    else:
        return g.simplify(combine_edges="first")

# 需要导入模块: from igraph import Graph [as 别名]
# 或者: from igraph.Graph import simplify [as 别名]
class Enron (BaseInputGraph):
  def __init__(self):
    '''
    @return: Enron email communication network as iGraph graph instance 
    '''
    edges = []
    weights = []
    f = open("./enron/email-Enron.txt", "r")
    for line in f:
      if line and line[0]!='#':
        seg = line.split()
        edges.append( (int(seg[0]), int(seg[1])) )
        weights.append( 1 )
    maxid = max( edges, key=itemgetter(1) )[1]
    maxid = max( maxid, max(edges,key=itemgetter(0))[0] )
    self.g = Graph()
    self.g.add_vertices(maxid + 1)
    self.g.add_edges(edges)
    self.g.to_undirected()
    self.g.simplify()
    self.g.vs["myID"] = [ str(int(i)) for i in range(maxid+1)]
    print "#nodes=", maxid + 1
    print "#edges=", len(self.g.es)

  def run(self):
    C = BaseInputGraph.unsupervised_logexpand(self)
    BaseInputGraph.run(self, C, p0=np.array([0.04, 0.04]))
    with open("./enron/email-Enron_weights.pairs", "w+") as txt:
      for e in self.g.es:
        txt.write("%d %d %f\n" %(e.tuple[0], e.tuple[1], e["weight"]) )
    with open("./enron/email-Enron_unweights.pairs", "w+") as txt:
      count = 0
      for e in self.g.es:
        txt.write("%d %d\n" %(e.tuple[0], e.tuple[1]) )
        count += 1
      print count , "edges written."

# 需要导入模块: from igraph import Graph [as 别名]
# 或者: from igraph.Graph import simplify [as 别名]
def get_igraph_graph(network):
    print 'load %s users into igraph' % len(network)
    g = Graph(directed=True)
    keys_set = set(network.keys())
    g.add_vertices(network.keys())
    print 'iterative load into igraph'
    edges = []
    for source in network:
        for target in network[source].intersection(keys_set):
            edges.append((source, target))
    g.add_edges(edges)
    g = g.simplify()
    print 'make sure graph is connected'
    connected_clusters = g.clusters()
    connected_cluster_lengths = [len(x) for x in connected_clusters]
    connected_cluster_max_idx = connected_cluster_lengths.index(max(connected_cluster_lengths))
    g = connected_clusters.subgraph(connected_cluster_max_idx)
    if g.is_connected():
        print 'graph is connected'
    else:
        print 'graph is not connected'
    return g

# 需要导入模块: from igraph import Graph [as 别名]
# 或者: from igraph.Graph import simplify [as 别名]
def reduce_and_save_communities(root_user, distance=10, return_graph_for_inspection=False):

    print 'starting reduce_and_save_communities'
    print 'root_user: %s,  following_in_our_db: %s, distance: %s' % (
        root_user.screen_name, len(root_user.following), distance)
    network = TwitterUser.get_rooted_network(root_user, postgres_handle, distance=distance)

    print 'load %s users into igraph' % len(network)
    g = Graph(directed=True)
    keys_set = set(network.keys())
    g.add_vertices(network.keys())
    g.vs["id"] = network.keys() #need this for pajek format
    print 'iterative load into igraph'
    edges = []
    for source in network:
        for target in network[source].intersection(keys_set):
            edges.append((source, target))
    g.add_edges(edges)
    g = g.simplify()
    print 'make sure graph is connected'
    connected_clusters = g.clusters()
    connected_cluster_lengths = [len(x) for x in connected_clusters]
    connected_cluster_max_idx = connected_cluster_lengths.index(max(connected_cluster_lengths))
    g = connected_clusters.subgraph(connected_cluster_max_idx)
    if g.is_connected():
        print 'graph is connected'
    else:
        print 'graph is not connected'

    if return_graph_for_inspection:
        return g

    print 'write to pajek format'
    root_file_name = root_user.screen_name
    f = open('io/%s.net' % root_file_name, 'w')
    g.write(f, format='pajek')

    print 'run infomap'
    #infomap_command = 'infomap_dir/infomap 345234 io/%s.net 10'
    #infomap_command = 'conf-infomap_dir/conf-infomap 344 io/%s.net 10 10 0.50'
    infomap_command = 'infohiermap_dir/infohiermap 345234 io/%s.net 30'
    os.system(infomap_command % root_file_name)

    print 'read into memory'
    f = open('io/%s.smap' % root_file_name)

    section_header = ''
    communities = defaultdict(lambda: ([], [], []))
    for line in f:
        if line.startswith('*Modules'):
            section_header = 'Modules'
            continue
        if line.startswith('*Insignificants'):
            section_header = 'Insignificants'
            continue
        if line.startswith('*Nodes'):
            section_header = 'Nodes'
            continue
        if line.startswith('*Links'):
            section_header = 'Links'
            continue

        if section_header == 'Modules':
            #looks like this:
            #1 "26000689,..." 0.130147 0.0308866
            #The names under *Modules are derived from the node with the highest 
            #flow volume within the module, and 0.25 0.0395432 represent, respectively, 
            #the aggregated flow volume of all nodes within the module and the per 
            #step exit flow from the module.
            continue

        if section_header == 'Nodes':
            #looks like this: 
            #1:10 "2335431" 0.00365772
            #or w/ a semicolon instead, semicolon means not significant
            #see http://www.tp.umu.se/~rosvall/code.html
            if ';' in line:
                continue
            community_idx = line.split(':')[0]
            node_id = line.split('"')[1]
            final_volume = float(line.split(' ')[2])
            communities[community_idx][1].append(node_id)
            communities[community_idx][2].append(final_volume)

        if section_header == 'Links':
            #community_edges
            #looks like this:
            #1 4 0.0395432
            community_idx = line.split(' ')[0]
            target_community_idx = line.split(' ')[1]
            edge_weight = line.split(' ')[2]
            communities[community_idx][0].append('%s:%s' % (target_community_idx, edge_weight))