def correlation_betweenness_degree_on_ER():
N = 1000
p = 0.004
G = nx.erdos_renyi_graph(N, p)
print nx.info(G)
ND, ND_lambda = ECT.get_number_of_driver_nodes(G)
ND, driverNodes = ECT.get_driver_nodes(G)
degrees = []
betweenness = []
tot_degree = nx.degree_centrality(G)
tot_betweenness = nx.betweenness_centrality(G,weight=None)
for node in driverNodes:
degrees.append(tot_degree[node])
betweenness.append(tot_betweenness[node])
with open("results/driver_degree_ER.txt", "w") as f:
for x in degrees:
print >> f, x
with open("results/driver_betweenness_ER.txt", "w") as f:
for x in betweenness:
print >> f, x
with open("results/tot_degree_ER.txt", "w") as f:
for key, value in tot_degree.iteritems():
print >> f, value
with open("results/tot_betweenness_ER.txt", "w") as f:
for key, value in tot_betweenness.iteritems():
print >> f, value
def get_community_biconnections(commid, df, graph):
print "Find biconnections in the community :", commid
print nx.info(graph)
biconnected_nodes = []
for e in graph.edges():
a, b = e
if graph.has_edge(b,a) and a != b:
# check if already there in the list
if (a,b) in biconnected_nodes or (b,a) in biconnected_nodes:
pass
else:
biconnected_nodes.append((a,b))
print "number of biconnected edges:", len(biconnected_nodes)
source_nodes, target_nodes = zip(*biconnected_nodes)
all_subgraph_nodes = set(source_nodes).union(set(target_nodes))
print "Unique nodes in the biconnections", len(all_subgraph_nodes)
# get the subgraph of all biconnected edges
# plot
dfname = biconnbase+ str(commid) + '_biz_info.csv'
bicon_df = df.loc[all_subgraph_nodes]
print bicon_df.shape
bicon_df.to_csv(dfname)
# subgraph generated from the coordinates
sgname = biconnbase+ str(commid) + '_sg_edgelist.ntx'
sg = graph.subgraph(list(all_subgraph_nodes))
print nx.info(sg)
nx.write_edgelist(sg, sgname, data=False)
def correlation_betweenness_degree_on_ErdosNetwork():
G = nx.read_pajek("dataset/Erdos971.net")
isolated_nodes = nx.isolates(G)
G.remove_nodes_from(isolated_nodes)
print nx.info(G)
ND, ND_lambda = ECT.get_number_of_driver_nodes(G)
print "ND = ", ND
print "ND lambda:", ND_lambda
ND, driverNodes = ECT.get_driver_nodes(G)
print "ND =", ND
degrees = []
betweenness = []
tot_degree = nx.degree_centrality(G)
tot_betweenness = nx.betweenness_centrality(G,weight=None)
for node in driverNodes:
degrees.append(tot_degree[node])
betweenness.append(tot_betweenness[node])
with open("results/driver_degree_Erdos.txt", "w") as f:
for x in degrees:
print >> f, x
with open("results/driver_betweenness_Erdos.txt", "w") as f:
for x in betweenness:
print >> f, x
with open("results/tot_degree_Erdos.txt", "w") as f:
for key, value in tot_degree.iteritems():
print >> f, value
with open("results/tot_betweenness_Erdos.txt", "w") as f:
for key, value in tot_betweenness.iteritems():
print >> f, value
def correlation_betweenness_degree_on_BA():
n = 1000
m = 2
G = nx.barabasi_albert_graph(n, m)
print nx.info(G)
ND, ND_lambda = ECT.get_number_of_driver_nodes(G)
print "ND = ", ND
print "ND lambda:", ND_lambda
ND, driverNodes = ECT.get_driver_nodes(G)
print "ND =", ND
degrees = []
betweenness = []
tot_degree = nx.degree_centrality(G)
tot_betweenness = nx.betweenness_centrality(G,weight=None)
for node in driverNodes:
degrees.append(tot_degree[node])
betweenness.append(tot_betweenness[node])
with open("results/driver_degree_BA.txt", "w") as f:
for x in degrees:
print >> f, x
with open("results/driver_betweenness_BA.txt", "w") as f:
for x in betweenness:
print >> f, x
with open("results/tot_degree_BA.txt", "w") as f:
for key, value in tot_degree.iteritems():
print >> f, value
with open("results/tot_betweenness_BA.txt", "w") as f:
for key, value in tot_betweenness.iteritems():
print >> f, value
def correlation_betweenness_degree_on_WS():
n = 1000
k = 4
p = 0.01
G = nx.watts_strogatz_graph(n, k, p)
print nx.info(G)
ND, ND_lambda = ECT.get_number_of_driver_nodes(G)
ND, driverNodes = ECT.get_driver_nodes(G)
degrees = []
betweenness = []
tot_degree = nx.degree_centrality(G)
tot_betweenness = nx.betweenness_centrality(G,weight=None)
for node in driverNodes:
degrees.append(tot_degree[node])
betweenness.append(tot_betweenness[node])
with open("results/driver_degree_WS.txt", "w") as f:
for x in degrees:
print >> f, x
with open("results/driver_betweenness_WS.txt", "w") as f:
for x in betweenness:
print >> f, x
with open("results/tot_degree_WS.txt", "w") as f:
for key, value in tot_degree.iteritems():
print >> f, value
with open("results/tot_betweenness_WS.txt", "w") as f:
for key, value in tot_betweenness.iteritems():
print >> f, value
def build_graph(self):
'''
Build a networkx graph from WordNet
'''
for synset in list(self.wordnet.all_synsets()):
#for synset in list(self.wordnet.all_synsets('n'))[:10]:
self.G.add_node(synset.name)
self.add_edges(synset, synset.hypernyms())
self.add_edges(synset, synset.hyponyms())
self.add_edges(synset, synset.instance_hypernyms())
self.add_edges(synset, synset.instance_hyponyms())
self.add_edges(synset, synset.member_holonyms())
self.add_edges(synset, synset.substance_holonyms())
self.add_edges(synset, synset.part_holonyms())
self.add_edges(synset, synset.member_meronyms())
self.add_edges(synset, synset.substance_meronyms())
self.add_edges(synset, synset.part_meronyms())
self.add_edges(synset, synset.attributes())
self.add_edges(synset, synset.entailments())
self.add_edges(synset, synset.causes())
self.add_edges(synset, synset.also_sees())
self.add_edges(synset, synset.verb_groups())
self.add_edges(synset, synset.similar_tos())
print nx.info(self.G)
def summary(self):
"""
User friendly wrapping and display of graph properties
"""
print "\n Graph Summary:"
print nx.info(self.g)
pass
def EigenvectorCentralityExperiment(G, min_target, max_target, filename):
print nx.info(G)
print 'average eigenvector centrality: ', UF.average_eigenvector_centrality(G)
X_eigenvector_centrality = []
Y_nD = []
target = min_target
while target <= max_target:
copyG = G.copy()
new_G = SimulatedAnnealing(copyG, target, eigenvector_centrality_cost_function)
eigenvector_centrality = UF.average_eigenvector_centrality(new_G)
nD = SCT.controllability(new_G)
X_eigenvector_centrality.append(eigenvector_centrality)
Y_nD.append(nD)
print "target = ", target, " EC = ", eigenvector_centrality, 'nD = ', nD
target += 0.01
s = 'results/' + filename
with open(s, "w") as f:
for i in range(len(Y_nD)):
print >> f, "%f %f"%(X_eigenvector_centrality[i], Y_nD[i])
return (X_eigenvector_centrality, Y_nD)
def computemaxweight(graph,path,protlist,path_lenght,alone):
elements=[]
nodes=[]
ess=[]
print "------Starting Graph------"
print nx.info(graph)
for i in path:
max=0
for j in path[i]:
count=0
for k in range(0,len(j)-1,1):
count=count+float(graph.edge[j[k]][j[k+1]]["weight"])
if count>max:
max=count
elements=j
ess.extend(elements[1:len(elements)-1])
ess=list(set(ess))
H=graph.subgraph(ess+protlist)
#H.add_nodes_from(protlist)
graphred=check(H,path_lenght,ess,protlist,path)
nx.write_gpickle(graphred,"weightmaxfilter.gpickle")
f1=open("weightproteins.txt","w")
for i in graphred.nodes():
if i in alone:
pass
else:
f1.write(i+"\n")
def main(): test_user = '******' test_graph = buildSocialGraph(test_user, twitter_only=True) print nx.info(test_graph) """
def simpleDisplay(ipaddress = "localhost",port = "9999"):
'''
利用每次处理后保存的图来进行恢复展示
:return:
'''
# client,repo,stargazers,user = getRespond()
# g = addTOGraph(repo,stargazers,user)
# addEdge(stargazers,client,g)
# getPopular(g)
# savaGraph1(g)
# top10(g)
g = nx.read_gpickle("data/github.1")
print nx.info(g)
print
mtsw_users = [n for n in g if g.node[n]['type'] == 'user']
h = g.subgraph(mtsw_users)
print nx.info(h)
print
d = json_graph.node_link_data(h)
json.dump(d, open('data/githubRec.json', 'w'))
cmdstr = "python3 -m http.server %s" % port
webbrowser.open_new_tab("http://%s:%s/%s.html"%(ipaddress,port, "display_githubRec"))
os.system(cmdstr)
def splitGraphs(self,labels):
"""
split the graph into several subgraphs by labels
"""
id_label = []
## load labels
## Node id start from 0
fid = open('labels','r')
for line in fid:
field = line.strip()
id_label.append(int(field))
fid.close()
## calculate the number of different labels
nodup_labels = set(id_label)
K = len(nodup_labels)
for i in range(0,K):
f = open('subgraph_' + str(i) +'.sub','w')
subG = []
for j in range(0,len(id_label)):
if id_label[j] == i:
subG.append(str(j))
G = self.G.subgraph(subG)
print nx.info(G)
nx.write_edgelist(G,f)
def get_distance_dict(filename):
g = nx.read_edgelist(filename)
print "Read in edgelist file ", filename
print nx.info(g)
path_length = nx.all_pairs_shortest_path_length(g)
print len(path_length.keys())
print path_length
def data_prep(infofile, graphfile):
# read in the total biz file
# Preparing the data files
df = pd.read_csv(infofile)
#removing duplicate records
df = df.groupby('pageid').first()
print df.columns
print df.index
print df.shape
print df.isnull().sum()
df = df[df['latitude'] != 'N']
print "Dropping loc, lat = N: ", df.shape
df = df.dropna() #df[df['latitude'] != 'N']
print "Dropping NA", df.shape #df.isnull().sum()
# read in th original edgelist as a directed graph
globalgraph= nx.read_edgelist(graphfile, create_using=nx.DiGraph(), nodetype=int)
print "Original Graph:", nx.info(globalgraph)
print "Keeping it consistent, removing all nodes not in database:"
pageids = list(df.index)
prunedglobalgraph = globalgraph.subgraph(pageids)
print nx.info(prunedglobalgraph)
return df, globalgraph
def check(graph,path_lenght,removable,protlist,path): rem=[] ess=[] for i in removable: count=0 flag=0 rem.append(i) H=graph.copy() H.remove_nodes_from(rem) for j in path: try: lenght=nx.shortest_path_length(H, j[0], j[1]) except: lenght=-1 if lenght==-1 or (lenght+1)!=path_lenght[j]: ess.append(i) flag=1 break else: count=count+1 if count==len(path): rem.append(i) elif flag==1: rem.remove(i) graph.add_nodes_from(protlist) graph.remove_nodes_from(rem) print nx.info(graph) #drawgraph(graph,protlist) return graph
def __init__(
self,
celltypes_file="nx_celltype_graph.edgelist",
cells_file="nx_cell_graph.edgelist",
format="edgelist",
scale=1.0,
):
"""
celltypes_file -- file containing celltype-celltype connectivity graph
cells_file -- file containing cell-cell connectivity graph
format -- string representation of file format of the celltypes_file and cells_file.
"""
self.__celltype_graph = self._read_celltype_graph(celltypes_file, format=format)
if not self.__celltype_graph:
self.__celltype_graph = self._make_celltype_graph("connmatrix.txt", "cells.txt", scale=scale)
self.__cell_graph = self._read_cell_graph(cells_file, format=format)
if not self.__cell_graph:
self.__cell_graph = self._make_cell_graph()
start = datetime.now()
print nx.info(self.__cell_graph)
end = datetime.now()
delta = end - start
config.BENCHMARK_LOGGER.info("Computed Graph info in: %g" % (delta.seconds + 1e-6 * delta.microseconds))
def info(self , verbose = False):
print "--------------Cloud_Reg_graph info:-----------------"
print nx.info(self)
ncloud = 0
nreg = 0
for node in self.nodes_iter():
if isinstance(node, nx.DiGraph):
ncloud += 1
if node.number_of_nodes() == 0:
if verbose: print "cloud ::\n empty cloud\n"
continue
if verbose: print "cloud ::"
for prim in node.nodes_iter():
assert isinstance(prim, cc.circut_module), "cloud type %s " % str(prim.__class__)
if verbose: prim.__print__()
else:
assert isinstance(node ,cc.circut_module) ,"reg type %s " % str(node.__class__)
if verbose:
print "fd ::"
node.__print__()
nreg += 1
assert len(self.big_clouds) == ncloud ,"%d %d"%(len(self.big_clouds),ncloud)
print "Number of cloud:%d " % ncloud
print "Number of register:%d" % nreg
print "--------------------------------------"
def add_partitions_to_digraph(graph, partitiondict): ''' Add the partition numbers to a graph - in this case, using this to update the digraph, with partitions calc'd off the undirected graph. Yes, it's a bad hack. ''' g = graph nx.set_node_attributes(g, 'partition', partitiondict) nx.info(g) return
def main():
### Undirected graph ###
# Initialize model using the Petersen graph
model=gmm.gmm(nx.petersen_graph())
old_graph=model.get_base()
model.set_termination(node_ceiling)
model.set_rule(rand_add)
# Run simualation with tau=4 and Poisson density for motifs
gmm.algorithms.simulate(model,4)
# View results
new_graph=model.get_base()
print(nx.info(new_graph))
# Draw graphs
old_pos=nx.spring_layout(old_graph)
new_pos=nx.spring_layout(new_graph,iterations=2000)
fig1=plt.figure(figsize=(15,7))
fig1.add_subplot(121)
#fig1.text(0.1,0.9,"Base Graph")
nx.draw(old_graph,pos=old_pos,node_size=25,with_labels=False)
fig1.add_subplot(122)
#fig1.text(0.1,0.45,"Simulation Results")
nx.draw(new_graph,pos=new_pos,node_size=20,with_labels=False)
fig1.savefig("undirected_model.png")
### Directed graph ###
# Initialize model using random directed Barabasi-Albert model
directed_base=nx.barabasi_albert_graph(25,2).to_directed()
directed_model=gmm.gmm(directed_base)
directed_model.set_termination(node_ceiling)
directed_model.set_rule(rand_add)
# Run simualation with tau=4 and Poisson density for motifs
gmm.algorithms.simulate(directed_model,4)
# View results
new_directed=directed_model.get_base()
print(nx.info(new_directed))
# Draw directed graphs
old_dir_pos=new_pos=nx.spring_layout(directed_base)
new_dir_pos=new_pos=nx.spring_layout(new_directed,iterations=2000)
fig2=plt.figure(figsize=(7,10))
fig2.add_subplot(211)
fig2.text(0.1,0.9,"Base Directed Graph")
nx.draw(directed_base,pos=old_dir_pos,node_size=25,with_labels=False)
fig2.add_subplot(212)
fig2.text(0.1,0.45, "Simualtion Results")
nx.draw(new_directed,pos=new_dir_pos,node_size=20,with_labels=False)
fig2.savefig("directed_model.png")
# Export files
nx.write_graphml(model.get_base(), "base_model.graphml")
nx.write_graphml(directed_model.get_base(), "directed_model.graphml")
nx.write_graphml(nx.petersen_graph(), "petersen_graph.graphml")
def main111():
if 1:
G = nx.read_edgelist(infname)
print nx.info(G)
# Graph adj matix
A = nx.to_scipy_sparse_matrix(G)
print type(A)
from scipy import sparse, io
io.mmwrite("Results/test.mtx", A)
exit()
# write to disk clustering coeffs for this graph
snm.get_clust_coeff([G], 'orig', 'mmonth')
# write to disk egienvalue
snm.network_value_distribution([G], [], 'origMmonth')
if 0:
edgelist = np.loadtxt(infname, dtype=str, delimiter='\t')
print edgelist[:4]
idx = np.arange(len(edgelist))
np.random.shuffle(idx)
subsamp_edgelist = edgelist[idx[:100]]
G = nx.Graph()
G.add_edges_from([(long(x), long(y)) for x, y in subsamp_edgelist])
# visualize this graph
# visualize_graph(G)
exit()
G = nx.Graph()
G.add_edges_from([(long(x), long(y)) for x, y in edgelist])
print nx.info(G)
print 'Done'
def draw_citing_users_follower_count():
df = pd.read_csv('Results/twtrs_follower_network.tsv', sep='\t', header=None)
df.columns = ['src', 'followers']
count_followers = lambda row: len(row[1].split(','))
df['fCnt'] = df.apply(count_followers, axis=1)
edglstdf = pd.read_csv('Results/clustered_relevant_users.tsv', sep='\t', header=None)
eldf = edglstdf.apply(lambda row: [x.lstrip('[').rstrip(']') for x in row])
eldf.columns = ['src','trg']
eldf[['src']] = eldf[['src']].apply(pd.to_numeric)
df = pd.merge(eldf,df, on='src')
df[['src','trg','fCnt']].to_csv('Results/procjson_edglst.tsv', sep='\t', header=False, index=False)
g=nx.Graph()
g.add_edges_from(df[['src','trg']].values)
print nx.info(g)
f, axs = plt.subplots(1, 1, figsize=(1.6*6., 1*6.))
# nx.draw_networkx(g, pos=nx.spring_layout(g), ax=axs, with_labels=False, node_size=df[['fCnt']]/float(len(df)), alpha=.5)
pos=nx.spring_layout(g)
# nx.draw_networkx(g, pos=pos, ax=axs, with_labels=False, alpha=.5, node_size=30)
nx.draw_networkx_edges(g, pos=pos, ax=axs, alpha=0.5, width=0.8)
nx.draw_networkx_nodes(g, pos=pos, ax=axs, nodelist=list(df['src'].values), node_color='#7A83AC', node_size=30, alpha=0.5)
nx.draw_networkx_nodes(g, pos=pos, ax=axs, nodelist=list(df['trg'].values), node_color='k', node_size=20, alpha=0.8)
axs.patch.set_facecolor('None')
axs.set_xticks([]) #[None]# grid(True, which='both')
axs.set_yticks([]) #[None]# grid(True, which='both')
plt.savefig('figures/outfig', bbox_inches='tight', pad_inches=0)
return
def phone_or_postid_pruning_network_construction(edge_list=
path+'connected-component-analysis/network-profiling-data/cid6_analysis/cid6-edge-list',
edge_phone_count=path+'connected-component-analysis/network-profiling-data/cid6_analysis/edge-count-phone.jl',
phone_edge_list=path+'connected-component-analysis/network-profiling-data/cid6_analysis/cid6-edge-list-tagged-phone'):
G = nx.read_edgelist(edge_list, delimiter='\t')
print nx.info(G)
threshold = 50
count = 0
forbidden_phones = set()
with codecs.open(edge_phone_count, 'r', 'utf-8') as f:
for line in f:
obj = json.loads(line[0:-1])
if int(obj.keys()[0]) >= threshold:
forbidden_phones = forbidden_phones.union(set(obj[obj.keys()[0]]))
with codecs.open(phone_edge_list, 'r', 'utf-8') as f:
for line in f:
fields = re.split('\t', line[0:-1])
phones = set(fields[2:])
if len(phones.intersection(forbidden_phones)) != 0:
count += 1
G.remove_edge(fields[0], fields[1])
print str(count),' edges pruned from graph'
ccs = sorted(nx.connected_components(G), key=len, reverse=True)
print len(ccs)
print len(ccs[0])
def simplify_edges(G):
nodes = []
print "Compacting nodes of degree 2"
for n in G.nodes():
if G.degree(n) == 2:
nodes.append(n)
G.node[n]['pos'] = n
nodes = list(set(nodes))
print "Simplifying an estimated %i nodes...."%len(nodes)
while nodes:
while nodes:
nodes = list(set(nodes))
n = nodes.pop()
neighbors = G.neighbors(n)
G.remove_node(n)
G.add_path(neighbors)
for nn in neighbors:
if G.degree(n) == 2:
nodes.append(nn)
for n in G.nodes():
if G.degree(n) == 2:
nodes.append(n)
nodes = list(set(nodes))
G = max(nx.connected_component_subgraphs(G), key=len)
print nx.info(G)
#return G
for n in G.nodes():
G.node[n]['pos'] = n
def Gephi_Graph(r_serv, graphpath, mincard, maxcard, insert_type):
"""Create Gephi Graph by calling a "Sub function": Create_Graph
:param r_serv: -- connexion to redis database
:param graphpath: -- the absolute path of the .gephi graph created.
:param mincard: -- the minimum links between 2 nodes to be created
:param maxcard: -- the maximum links between 2 nodes to be created
:param insert_type: -- the type of datastructure used to create the graph.
In fact this function is juste here to be able to choose between two kind of
Redis database structure: One which is a Sorted set and the other a simple
set.
"""
g = nx.Graph()
if (insert_type == 0):
for h in r_serv.smembers("hash"):
Create_Graph(r_serv, g, h, graphpath, mincard, maxcard)
elif (insert_type == 2):
for h in r_serv.zrange("hash", 0, -1):
Create_Graph(r_serv, g, h, graphpath, mincard, maxcard)
nx.write_gexf(g,graphpath)
print nx.info(g)
def cid6_phone_edges_not_in_postid(tagged_phone_edge_list=path + 'connected-component-analysis/network-profiling-data/cid6_analysis/cid6-edge-list-tagged-phone',
tagged_postid_edge_list=path + 'connected-component-analysis/network-profiling-data/cid6_analysis/cid6-edge-list-tagged-postid',
out_file=path + 'connected-component-analysis/network-profiling-data/cid6_analysis/cid6-edge-list-tagged-phone-minus-postid'
):
postid_edges = set()
G = nx.Graph()
with codecs.open(tagged_postid_edge_list, 'r', 'utf-8') as f:
for line in f:
fields = re.split('\t', line[0:-1])
postid_edges.add(tuple(sorted([fields[0], fields[1]])))
# ccs = sorted(nx.connected_components(G), key=len, reverse=True)
# print len(ccs)
# print len(ccs[0])
# print nx.info(G)
out = codecs.open(out_file, 'w', 'utf-8')
with codecs.open(tagged_phone_edge_list, 'r', 'utf-8') as f:
for line in f:
fields = re.split('\t', line[0:-1])
edge = sorted([fields[0], fields[1]])
if tuple(edge) not in postid_edges:
out.write(line)
G.add_edge(fields[0], fields[1])
out.close()
print nx.info(G)
ccs = sorted(nx.connected_components(G), key=len, reverse=True)
print len(ccs)
print len(ccs[0])
def get_k_core(reviews_path,k_val):
# Report start of process
print "=================================="
print "EXTRACTING K-CORE OF PID GRAPH "
print "=================================="
print "AT STEP #1: Determine which reviewer reviewed which products"
# with ufora.remotely.downloadAll():
(PID_to_lines,PID_to_reviewerID) = get_PID_facts(reviews_path)
print "At STEP #2: Created weighted edges"
# with ufora.remotely.downloadAll():
weighted_edges = get_weighted_edges(PID_to_reviewerID)
print "AT STEP #3: Create PID graph structure"
# with ufora.remotely.downloadAll():
PID_graph = create_graph(PID_to_reviewerID,weighted_edges)
print nx.info(PID_graph)
print "AT STEP #4: Extracting K-core"
# with ufora.remotely.downloadAll():
k_core_graph = nx.k_core(PID_graph,k_val)
print nx.info(k_core_graph)
pickle.dump(graph,open("graph",'w'))
print "DONE!"
def test_traversals():
name = 'ca-CondMat.edges.gz'
G = nx.read_edgelist(name, comments='#', create_using=nx.Graph(), nodetype=int, data=False, edgetype=None)
G.name = name
print nx.info(G)
N = G.number_of_nodes()
f = 0.1
pk_real = degrees2pk([G.degree(v) for v in G]) # real node degree distribution
qk_expected = qk_f(pk_real, f) # expected node degree distribution in a BFS sample of fraction f
start_node = random.choice(G.nodes())
S = bfs(G, start_node, int(N*f))
qk_sampled = degrees2pk([G.degree(v) for v in S])
pk_corrected = estimate_pk(qk_sampled, f)
print """
%2.1f - mean degree in raw BFS, actually sampled
%2.1f - mean degree in raw BFS, expected by the RG(pk) model.
----
%2.1f - mean degree in G, calculated from the BFS sample according to the RG(pk) model.
%2.1f - real mean degree in G
""" % (mean_degree(qk_sampled), mean_degree(qk_expected), mean_degree(pk_corrected), mean_degree(pk_real))
def main():
# Load Zachary data, randomly delete nodes, and report
zachary=nx.Graph(nx.read_pajek("karate.net")) # Do not want graph in default MultiGraph format
zachary.name="Original Zachary Data"
print(nx.info(zachary))
zachary_subset=rand_delete(zachary, 15) # Remove half of the structure
zachary_subset.name="Randomly Deleted Zachary Data"
print(nx.info(zachary_subset))
# Create model, and simulate
zachary_model=gmm.gmm(zachary_subset,R=karate_rule,T=node_ceiling_34)
gmm.algorithms.simulate(zachary_model,4,poisson=False,new_name="Simulation from sample") # Use tau=4 because data is so small (it's fun!)
# Report and visualize
print(nx.info(zachary_model.get_base()))
fig=plt.figure(figsize=(30,10))
fig.add_subplot(131)
nx.draw_spring(zachary,with_labels=False,node_size=45,iterations=5000)
plt.text(0.01,-0.1,"Original Karate Club",color="darkblue",size=20)
fig.add_subplot(132)
nx.draw_spring(zachary_subset,with_labels=False,node_size=45,iterations=5000)
plt.text(0.01,-0.1,"Random sample of Karate Club",color="darkblue",size=20)
fig.add_subplot(133)
nx.draw_spring(zachary_model.get_base(),with_labels=False,node_size=45,iterations=5000)
plt.text(0.01,-0.1,"Simulation from random sample",color="darkblue",size=20)
plt.savefig("zachary_simulation.png")
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 kinetic(fileName='P2_1_9_p07', M=None, N=None, axis=None):
#FILE = "/home/xingzhong/MicrosoftGestureDataset-RC/data/%s"%fileName
FILE = "/Users/xingzhong/Downloads/MicrosoftGestureDataset-RC/data/%s"%fileName
truth = np.genfromtxt(FILE+'.tagstream', delimiter=';', skiprows=1, dtype=None, converters={0: lambda x: (int(x) *1000 + 49875/2)/49875})
nd = np.loadtxt(FILE+'.csv')
nd = nd[np.where(nd[:,80]!=0)]# remove empty rows
idx, ndd = map(int, nd[:,0]), nd[:, 1:] # unpack index and data
m, n = ndd.shape
panel = pd.Panel( ndd.reshape((m, 20, 4)), items=idx, major_axis=AGENTS, minor_axis=['x','y','z','v'] ).transpose(2, 0, 1)
panel['dx'] = 1000* panel['x'].diff().fillna(0)
panel['dy'] = 1000* panel['y'].diff().fillna(0)
panel['dz'] = 1000* panel['z'].diff().fillna(0)
panel = panel.transpose(2, 1, 0)
samples = [s for s in instance_generator(panel, truth)]
g = EventGraph()
X = [np.array([0])]
for aid, seq in enumerate (samples[0]):
if M is not None and aid > M :
break
for t, atom in enumerate (seq):
if N is not None and t > N:
break
elif not atom is None and t!=0:
if axis:
g.addEvent( Event(t, aid, atom ))
X.append(atom)
else:
g.addEvent( Event(t, aid, np.array([atom[axis]]) ))
X.append( np.array([atom[axis]]) )
g.buildEdges(delta = 1)
print nx.info(g)
return g, X
def query(self,
topic,
max_depth=4,
config=None,
pivot_on=list(),
dont_pivot_on=list(['enrichment', 'classification']),
direction='successors'):
"""
:param topic: a graph to return the context of. At least one node ID in topic \
must be in full graph g to return any context.
:param max_depth: The maximum distance from the topic to search
:param config: The titanDB configuration to use if not using the one configured with the plugin
:param pivot_on: A list of attribute types to pivot on.
:param dont_pivot_on: A list of attribute types to not pivot on.
:param direction: The direction to transverse the graph
:return: subgraph in networkx format
NOTE: If an attribute is in both pivot_on and dont_pivot_on it will not be pivoted on
"""
if config is None:
config = self.titandb_config
# Connect to TitanDB Database
titan_graph = TITAN_Graph(config)
# Convert the topic nodes into titanDB eids
current_nodes = set()
eid_uri_map = {}
# Validate the node URI
for node in topic.nodes():
titan_node = titan_graph.vertices.index.get_unique(
"uri", topic.node[node]["uri"])
if titan_node:
current_nodes.add(titan_node.eid)
eid_uri_map[titan_node.eid] = node
topic_nodes = frozenset(current_nodes)
subgraph_nodes = current_nodes
#sg = copy.deepcopy(topic)
sg = nx.MultiDiGraph()
sg.add_nodes_from(topic.nodes(data=True))
sg.add_edges_from(topic.edges(data=True))
distances = {node: 0 for node in topic.nodes()}
# Below 1 line is probably not necessary
# pivot_edges = list()
# print "Initial current Nodes: {0}".format(current_nodes) # DEBUG
for i in range(1, max_depth + 1):
new_nodes = set()
new_out_edges = set()
new_in_edges = set()
for eid in current_nodes:
# properties = og.node[node]
node = titan_graph.vertices.get(eid)
# If all directions, get all neighbors
if direction == 'all' or eid in topic_nodes:
try:
new_nodes = new_nodes.union({
n.eid
for n in titan_graph.gremlin.query(
"g.v({0}).both".format(eid))
})
except:
pass
try:
new_out_edges = new_out_edges.union({
n.eid
for n in titan_graph.gremlin.query(
"g.v({0}).outE".format(eid))
})
except:
pass
try:
new_in_edges = new_in_edges.union({
n.eid
for n in titan_graph.gremlin.query(
"g.v({0}).inE".format(eid))
})
except:
pass
# If there is a list of things to NOT pivot on, pivot on everything else
elif dont_pivot_on and 'attribute' in node and node.map(
)['attribute'] not in dont_pivot_on:
try:
new_nodes = new_nodes.union({
n.eid
for n in titan_graph.gremlin.query(
"g.v({0}).both".format(eid))
})
except:
pass
try:
new_out_edges = new_out_edges.union({
n.eid
for n in titan_graph.gremlin.query(
"g.v({0}).outE".format(eid))
})
except:
pass
try:
new_in_edges = new_in_edges.union({
n.eid
for n in titan_graph.gremlin.query(
"g.v({0}).inE".format(eid))
})
except:
pass
# Otherwise, only get all neighbors if the node is to be pivoted on.
elif 'attribute' in node and \
node['attribute'] in pivot_on and \
node['attribute'] not in dont_pivot_on:
try:
new_nodes = new_nodes.union({
n.eid
for n in titan_graph.gremlin.query(
"g.v({0}).both".format(eid))
})
except:
pass
try:
new_out_edges = new_out_edges.union({
n.eid
for n in titan_graph.gremlin.query(
"g.v({0}).outE".format(eid))
})
except:
pass
try:
new_in_edges = new_in_edges.union({
n.eid
for n in titan_graph.gremlin.query(
"g.v({0}).inE".format(eid))
})
except:
pass
# If not all neighbors and not in pivot, if we are transversing up, get predecessors
elif direction == 'predecessors':
# add edges to make predecessors successors for later probability calculation
try:
new_nodes = new_nodes.union({
n.eid
for n in titan_graph.gremlin.query(
"g.v({0}).out".format(eid))
})
except:
pass
# add the reverse edges. These opposite of these edges will get placed in the subgraph
try:
new_in_edges = new_in_edges.union({
n.eid
for n in titan_graph.gremlin.query(
"g.v({0}).inE".format(eid))
})
except:
pass
# Otherwise assume we are transversing down and get all successors
else: # default to successors
try:
new_nodes = new_nodes.union({
n.eid
for n in titan_graph.gremlin.query(
"g.v({0}).both".format(eid))
})
except:
pass
try:
new_out_edges = new_out_edges.union({
n.eid
for n in titan_graph.gremlin.query(
"g.v({0}).outE".format(eid))
})
except:
pass
# Remove nodes from new_nodes that are already in the subgraph so we don't overwrite their topic distance
current_nodes = new_nodes - subgraph_nodes
# combine the new nodes into the subgraph nodes set
subgraph_nodes = subgraph_nodes.union(current_nodes)
# Copy nodes, out-edges, in-edges, and reverse in-edges into subgraph
# Add nodes
for neighbor_eid in new_nodes:
attr = titan_graph.vertices.get(neighbor_eid).map()
sg.add_node(attr['uri'], attr)
eid_uri_map[neighbor_eid] = attr['uri']
# Add predecessor edges
for out_eid in new_out_edges:
out_edge = titan_graph.edges.get(out_eid)
attr = out_edge.map()
sg.add_edge(eid_uri_map[out_edge._outV],
eid_uri_map[out_edge._inV], out_eid, attr)
# Add successor edges & reverse pivot edges
for in_eid in new_in_edges:
in_edge = titan_graph.edges.get(in_eid)
attr = in_edge.map()
attr['origin'] = "subgraph_creation_pivot"
sg.add_edge(eid_uri_map[in_edge._inV],
eid_uri_map[in_edge._outV], in_eid, attr)
# Set the distance from the topic on the nodes in the graph
for eid in current_nodes:
if eid_uri_map[eid] not in distances:
distances[eid_uri_map[eid]] = i
# logging.debug("Current nodes: {0}".format(current_nodes)) # DEBUG
# add the distances to the subgraph
nx.set_node_attributes(sg, "topic_distance", distances)
logging.debug(nx.info(sg)) # DEBUG
# Return the subgraph
return sg
import csv
import networkx as nx
from operator import itemgetter
import community
# Read in the nodelist file
with open('edge_graph.csv', 'r') as nodecsv:
nodereader = csv.reader(nodecsv)
nodes = [n for n in nodereader][1:]
# Get a list of just the node names (the first item in each row)
node_names = [n[0] for n in nodes]
# Read in the edgelist file
with open('edge_graph.csv', 'r') as edgecsv:
edgereader = csv.reader(edgecsv)
edges = [tuple(e) for e in edgereader][1:]
# Print the number of nodes and edges in our two lists
print(len(node_names))
print(len(edges))
G = nx.Graph() # Initialize a Graph object
G.add_nodes_from(node_names) # Add nodes to the Graph
G.add_edges_from(edges) # Add edges to the Graph
print(nx.info(G)) # Print information about the Graph
print(G)
nx.draw(G)
def load_network(self):
# read METIS file
self.G = utils.read_metis(self.DATA_FILENAME)
self.initial_number_of_nodes = self.G.number_of_nodes(
) # used for computing metrics
# Alpha value used in prediction model
self.prediction_model_alpha = self.G.number_of_edges() * (
self.num_partitions / self.G.number_of_nodes()**2)
if self.use_one_shot_alpha:
self.prediction_model_alpha = self.one_shot_alpha
# Order of nodes arriving
self.arrival_order = list(range(0, self.G.number_of_nodes()))
if self.SIMULATED_ARRIVAL_FILE == "":
# mark all nodes as needing a shelter
self.simulated_arrival_list = [1] * self.G.number_of_nodes()
else:
with open(self.SIMULATED_ARRIVAL_FILE, "r") as ar:
self.simulated_arrival_list = [
int(line.rstrip('\n')) for line in ar
]
# count the number of people arriving in the simulation
self.number_simulated_arrivals = 0
for arrival in self.simulated_arrival_list:
self.number_simulated_arrivals += arrival
if self.verbose > 0:
print("Graph loaded...")
print(nx.info(self.G))
if nx.is_directed(self.G):
print("Graph is directed")
else:
print("Graph is undirected")
self.reset()
# load displacement prediction weights
if (self.PREDICTION_LIST_FILE == ""):
self.predicted_displacement_weights = [
1
] * self.G.number_of_nodes()
else:
with open(self.PREDICTION_LIST_FILE, 'r') as plf:
self.predicted_displacement_weights = [
float(line.rstrip('\n')) for line in plf
]
# preserve original node/edge weight when modification functions are applied
if self.graph_modification_functions:
node_weights = {
n[0]: n[1]['weight']
for n in self.G.nodes_iter(data=True)
}
nx.set_node_attributes(self.G, 'weight_orig', node_weights)
edge_weights = {(e[0], e[1]): e[2]['weight']
for e in self.G.edges_iter(data=True)}
nx.set_edge_attributes(self.G, 'weight_orig', edge_weights)
# make a copy of the original graph since we may alter the graph later on
# and may want to refer to information from the original graph
self.originalG = self.G.copy()
def label_prop():
G = nx.read_edgelist("facebook_combined.txt",
create_using=nx.Graph(),
nodetype=int)
print nx.info(G)
for i in G.nodes():
G.node[i]['label'] = i
G.node[i]['ID'] = i
G.node[i]['l_1'] = 0
G.node[i]['l_2'] = 0
G.node[i]['l_next'] = 0
'''
for n,nbrs in G.adjacency_iter():
for nbr,edict in nbrs.items():
if nbr==200:
print n, nbrs, G.node[nbr]['label']
'''
mainStop = False
i = 0
while (i < 100):
if i == 99:
set_communities = set()
for n in G.nodes():
set_communities.add(G.node[n]['label'])
print "the number of communities after 100 iterations==", len(
set_communities)
i += 1
mainStop = False
l1_stop = True
l2_stop = True
for n in G.nodes():
if (not (G.node[n]['label'] == G.node[n]['l_1'])):
l1_stop = False
for n in G.nodes():
if (not (G.node[n]['label'] == G.node[n]['l_2'])):
l2_stop = False
#print l1_stop, l2_stop
if (not (l1_stop or l2_stop)):
#print "in not loop"
for n, nbrs in G.adjacency_iter():
dict = {}
dict.clear()
for nbr, d in nbrs.items():
temp = G.node[nbr]['label']
if not dict.has_key(temp):
dict = {temp: 1}
else:
dict[temp] += 1
max_key = 0
max_key = max(dict, key=dict.get)
G.node[n]['l_next'] = max_key
G.node[n]['l_2'] = G.node[n]['l_1']
G.node[n]['l_1'] = G.node[n]['label']
G.node[n]['label'] = max_key
'''
for n in G.nodes():
G.node[n]['l_2']=G.node[n]['l_1']
G.node[n]['l_1']=G.node[n]['label']
G.node[n]['label']=G.node[n]['l_next']
'''
else:
print "The Community converges"
mainStop = True
print i
return i
def main(adminIsPoint=False):
path = os.path.realpath(
os.path.abspath(
os.path.split(inspect.getfile(inspect.currentframe()))[0]))
path = os.path.split(path)[0]
dash = os.path.join(path, r'dashboard.xlsm')
ctrl = pd.read_excel(dash, sheetname="AGGREGATE", index_col=0)
district = ctrl['Weight'].loc['DISTRICT']
logging.basicConfig(filename=os.path.join(path, 'runtime', district,
"PCS_Criticality_log.log"),
level=logging.INFO,
format="%(asctime)s-%(levelname)s: %(message)s")
logging.info("Starting Criticality Process")
print "Running: Criticality Analysis on %s. Do not interrupt" % district
# Path Settings
outpath = os.path.join(path, 'Outputs', '%s' % district)
runtime = os.path.join(path, r'PCS\Criticality\runtime\%s\\' % district)
for d in [outpath, runtime]:
if not os.path.isdir(d):
os.mkdir(d)
NETWORK_IN = os.path.join(path, r'runtime\%s\\' % district)
OD_IN = os.path.join(path, 'PCS\Criticality\input', '%s' % district)
DATA_IN = os.path.join(path, 'PCS\Criticality\Vietnam_Data_Layers')
inAdmin = os.path.join(DATA_IN, 'Poverty_Communes_2009.shp')
inNetworkFile = os.path.join(NETWORK_IN, 'Network.csv')
crs_in = {'init': 'epsg:4326'} #WGS 84
#Create folders for analysis
for d in [outpath, runtime, OD_IN]:
if not os.path.isdir(d):
os.mkdir(d)
#Error checking - Check input data
for curFile in [dash, inNetworkFile, inAdmin, DATA_IN, OD_IN, NETWORK_IN]:
if not os.path.exists(curFile):
logging.error("No input found: %s" % curFile)
raise ValueError("No input found: %s" % curFile)
inNetwork = pd.read_csv(inNetworkFile)
ctrldf = pd.read_excel(dash, sheetname="CRITICALITY", index_col='COL_ID')
#Inputs
network = os.path.join(runtime, 'Network.shp')
#Network Prep
fillvalue = inNetwork['iri_med'].mean()
inNetwork['TC_iri_med'] = inNetwork['iri_med'].fillna(fillvalue)
inNetwork['total_cost'] = inNetwork['length'] * (
ctrldf['Base_cost_km'][0] +
(ctrldf['IRI_Coeff'][0] * inNetwork['TC_iri_med']))
ginNetwork = gpd.GeoDataFrame(inNetwork,
crs=crs_in,
geometry=inNetwork['Line_Geometry'].map(
shapely.wkt.loads))
ginNetwork.to_file(network, driver='ESRI Shapefile')
logging.info("Successfully loaded data")
if not adminIsPoint:
prepareAdminCentroids(ginNetwork, inAdmin, crs_in,
os.path.join(OD_IN, 'adm_centroids.shp'))
logging.info("Created admin centroids")
def makeOrigin(n, ctrldf):
origindict = {
'name':
ctrldf['OName'][n],
'file':
os.path.join(path, 'PCS', 'Criticality', 'input', district,
'%s.shp' % ctrldf['OName'][n]),
'scalar_column':
ctrldf['OScalar'][n]
}
return origindict
def makeDestination(n, ctrldf):
destdict = {
'name':
ctrldf['DName'][n],
'file':
os.path.join(path, 'PCS', 'Criticality', 'input', district,
'%s.shp' % ctrldf['DName'][n]),
'penalty':
ctrldf['DPenalty'][n],
'importance':
ctrldf['DImportance'][n],
'annual':
ctrldf['DAnnual'][n],
'scalar_column':
ctrldf['DScalar'][n]
}
return destdict
origin_1, origin_2, origin_3, origin_4, origin_5 = makeOrigin(
0, ctrldf), makeOrigin(1, ctrldf), makeOrigin(2, ctrldf), makeOrigin(
3, ctrldf), makeOrigin(4, ctrldf)
originlist = {
'%s' % ctrldf['OName'][0]: origin_1,
'%s' % ctrldf['OName'][1]: origin_2,
'%s' % ctrldf['OName'][2]: origin_3,
'%s' % ctrldf['OName'][3]: origin_4,
'%s' % ctrldf['OName'][4]: origin_5,
}
destination_1, destination_2, destination_3, destination_4, destination_5 = makeDestination(
0, ctrldf), makeDestination(1, ctrldf), makeDestination(
2, ctrldf), makeDestination(3, ctrldf), makeDestination(4, ctrldf)
destinationlist = {
'%s' % ctrldf['DName'][0]: destination_1,
'%s' % ctrldf['DName'][1]: destination_2,
'%s' % ctrldf['DName'][2]: destination_3,
'%s' % ctrldf['DName'][3]: destination_4,
'%s' % ctrldf['DName'][4]: destination_5,
}
logging.debug("Opened origins and destinations")
# Prepation of network
gdf_points, gdf_node_pos, gdf = net_p.prepare_centroids_network(
origin_1['file'], network)
# Create Networkx MultiGraph object from the GeoDataFrame
G = net_p.gdf_to_simplified_multidigraph(gdf_node_pos, gdf, simplify=False)
# Change the MultiGraph object to Graph object to reduce computation cost
G_tograph = net_p.multigraph_to_graph(G)
logging.debug(
'Loaded road network: number of disconnected components is: %d' %
nx.number_connected_components(G_tograph))
# Observe the properties of the Graph object
nx.info(G_tograph)
# Take only the largest subgraph with all connected links
len_old = 0
for g in nx.connected_component_subgraphs(G_tograph):
if len(list(g.edges())) > len_old:
G1 = g
len_old = len(list(g.edges()))
G_sub = G1.copy()
nx.info(G_sub)
# Save the simplified transport network into a GeoDataFrame
gdf_sub = net_p.graph_to_df(G_sub)
blank, gdf_node_pos2, gdf_new = net_p.prepare_newOD(
origin_1['file'], gdf_sub)
#Road Network Graph prep
G2_multi = net_p.gdf_to_simplified_multidigraph(gdf_node_pos2,
gdf_new,
simplify=False)
Filedump(gdf_new, 'Road_Lines', runtime)
Filedump(gdf_node_pos2, 'Road_Nodes', runtime)
G2 = net_p.multigraph_to_graph(G2_multi)
gdf2 = net_p.graph_to_df(G2)
nLink = len(G2.edges())
Outputs, cost_list, iso_list = [], [], []
for z in ctrldf.index:
if (((ctrldf['ComboO'][z]) != 0) & ((ctrldf['ComboD'][z]) != 0) &
(pd.notnull(ctrldf['ComboO'][z])) &
(pd.notnull(ctrldf['ComboO'][z]))):
Q = int(ctrldf['ComboNumber'][z])
logging.info(
'Computing | combination %s as origin and %s as destination ' %
(ctrldf['ComboO'][z], ctrldf['ComboD'][z]))
xx = calculateOD(originlist['%s' % ctrldf['ComboO'][z]],
destinationlist['%s' % ctrldf['ComboD'][z]], Q,
gdf_sub, G2, nLink, gdf2, runtime, ctrldf)
Outputs.append(xx)
cost_list.append("Social_Cost_%s" % Q)
iso_list.append("Isolated_Trips_%s" % Q)
Output = inNetwork.drop(["geometry", 'TC_iri_med', 'total_cost'], axis=1)
for o_d_calc in range(0, len(Outputs)):
Output = Output.merge(Outputs[o_d_calc]['summary'],
how='left',
on='ID')
Output['Cost_total'] = Output[cost_list].sum(axis=1)
Output['Iso_total'] = Output[iso_list].sum(axis=1)
Output['CRIT_SCORE'] = (
ctrldf['Disrupt_Weight'][0] * Output['Cost_total'] +
ctrldf['Isolate_Weight'][0] * Output['Iso_total'])
Output['CRIT_SCORE'] = (
(Output['CRIT_SCORE'] - Output['CRIT_SCORE'].min()) /
(Output['CRIT_SCORE'].max() - Output['CRIT_SCORE'].min()))
logging.info("Calculated PCS Criticality")
FileOut(Output, 'criticality_output', outpath)
pSelection = 0.5
# When do add-ons start
groupPercent = 0.5
#Intervals
intervalPrimary = 10
intervalSecondary = 10
#Percentage to decide about Hubs
percentageP = 0.07
percentageS = 0.15
#Get Node Lists
nodeList = readNodes(nodeList, fileName)
#Create the graph
generateHInGBg(G_hybrid_btG, nodeList, kAverage, pSelection, groupPercent,
intervalPrimary, intervalSecondary, percentageP, percentageS)
print nx.info(G_hybrid_btG)
#Hubs
percentage = 0.07
print getHubsAndDegrees(G_hybrid_btG, percentage)
print getHubs(G_hybrid_btG, percentage)
#Degree
PlotDegreeDistribution(G_hybrid_btG, loglogplot=False)
print 'Average Network Degree', np.average(G_hybrid_btG.degree().values())
#Clusters
PlotClusteringDistribution(G_hybrid_btG, loglogplot=False)
print nx.average_clustering(G_hybrid_btG)
print nx.clustering(G_hybrid_btG)
def get_basic_info(graph_dict_list):
for item in graph_dict_list:
print(item["name"])
print(nx.info(item["graph"]))
def n2v_embedding(G,
targets,
verbose=False,
sample_size=0.5,
outfile_name="test.emb",
p=-100,
q=-100,
binary_path="./node2vec",
parameter_range=[0.25, 0.50, 1, 2, 4],
embedding_dimension=128):
## construct the embedding and return the binary..
#./node2vec -i:graph/karate.edgelist -o:emb/karate.emb -l:3 -d:24 -p:0.3 -dr -v
clf = OneVsRestClassifier(linear_model.LogisticRegression(),
n_jobs=mp.cpu_count())
if verbose:
print(nx.info(G))
N = len(G.nodes())
## get the graph..
if not os.path.exists("tmp"):
os.makedirs("tmp")
tmp_graph = "tmp/tmpgraph.edges"
out_graph = "tmp/tmpgraph.emb"
number_of_nodes = len(G.nodes())
number_of_edges = len(G.edges())
if verbose:
print("Graph has {} edges and {} nodes.".format(
number_of_edges, number_of_nodes))
f = open(tmp_graph, "w+")
#f.write(str(number_of_nodes)+" "+str(number_of_edges)+"\n")
for e in G.edges(data=True):
f.write(
str(e[0]) + " " + str(e[1]) + " " + str(float(e[2]['weight'])) +
"\n")
f.close()
if verbose:
print("N2V training phase..")
vals = parameter_range
copt = 0
cset = [0, 0]
dim = embedding_dimension
if float(p) > -100 and float(q) > -100:
print("Runing specific config of N2V.")
call_node2vec_binary(tmp_graph,
outfile_name,
p=p,
q=q,
directed=False,
weighted=True)
else:
## commence the grid search
for x in vals:
for y in vals:
call_node2vec_binary(tmp_graph,
outfile_name,
p=x,
q=y,
directed=False,
weighted=True,
binary=binary_path)
print("parsing {}".format(outfile_name))
rdict = benchmark_node_classification(
outfile_name, graph, targets, percent=float(sample_size))
mi, ma, misd, masd = rdict[float(sample_size)]
if ma > copt:
if verbose:
print("Updating the parameters: {} {}".format(
ma, cset))
cset = [x, y]
copt = ma
else:
print("Current optimum {}".format(ma))
call(["rm", "-rf",
outfile_name]) ## when updatedin delete the file
print("Final iteration phase..")
call_node2vec_binary(tmp_graph,
outfile_name,
p=cset[0],
q=cset[1],
directed=False,
weighted=True,
binary="./node2vec")
with open(outfile_name, 'r') as f:
fl = f.readline()
print("Resulting dimensions:{}".format(fl))
call(["rm", "-rf", "tmp"])
def topographic_metrics(wn):
# Get a copy of the graph
G = wn.get_graph()
# Print general topographic information
print(nx.info(G))
# Plot node and edge attributes.
junction_attr = wn.query_node_attribute('elevation',
node_type=wntr.network.Junction)
pipe_attr = wn.query_link_attribute('length', link_type=wntr.network.Pipe)
wntr.graphics.plot_network(wn,
node_attribute=junction_attr,
link_attribute=pipe_attr,
title='Node elevation and pipe length',
node_size=40,
link_width=2)
# Compute link density
print("Link density: " + str(nx.density(G)))
# Compute node degree
node_degree = dict(G.degree())
wntr.graphics.plot_network(wn,
node_attribute=node_degree,
title='Node Degree',
node_size=40,
node_range=[1, 5])
# Compute number of terminal nodes
terminal_nodes = G.terminal_nodes()
wntr.graphics.plot_network(wn,
node_attribute=terminal_nodes,
title='Terminal nodes',
node_size=40,
node_range=[0, 1])
print("Number of terminal nodes: " + str(len(terminal_nodes)))
print(" " + str(terminal_nodes))
# Compute pipes with diameter > threshold
diameter = 0.508 # m (20 inches)
pipes = wn.query_link_attribute('diameter', np.greater, diameter)
wntr.graphics.plot_network(wn,
link_attribute=list(pipes.keys()),
title='Pipes > 20 inches',
link_width=2,
link_range=[0, 1])
print("Number of pipes > 20 inches: " + str(len(pipes)))
print(" " + str(pipes))
# Compute nodes with elevation <= treshold
elevation = 1.524 # m (5 feet)
nodes = wn.query_node_attribute('elevation', np.less_equal, elevation)
wntr.graphics.plot_network(wn,
node_attribute=list(nodes.keys()),
title='Nodes <= 5 ft elevation',
node_size=40,
node_range=[0, 1])
print("Number of nodes <= 5 ft elevation: " + str(len(nodes)))
print(" " + str(nodes))
# Compute eccentricity, diameter, and average shortest path length
# These all use an undirected graph
uG = G.to_undirected() # undirected graph
if nx.is_connected(uG):
ecc = nx.eccentricity(uG)
wntr.graphics.plot_network(wn,
node_attribute=ecc,
title='Eccentricity',
node_size=40,
node_range=[15, 30])
print("Diameter: " + str(nx.diameter(uG)))
ASPL = nx.average_shortest_path_length(uG)
print("Average shortest path length: " + str(ASPL))
# Compute cluster coefficient
clust_coefficients = nx.clustering(nx.Graph(G))
wntr.graphics.plot_network(wn,
node_attribute=clust_coefficients,
title='Clustering Coefficient',
node_size=40)
# Compute betweenness centrality
bet_cen = nx.betweenness_centrality(G)
wntr.graphics.plot_network(wn,
node_attribute=bet_cen,
title='Betweenness Centrality',
node_size=40,
node_range=[0, 0.4])
central_pt_dom = G.central_point_dominance()
print("Central point dominance: " + str(central_pt_dom))
# Compute articulation points
Nap = list(nx.articulation_points(uG))
Nap = list(set(Nap)) # get the unique nodes in Nap
Nap_density = float(len(Nap)) / uG.number_of_nodes()
print("Density of articulation points: " + str(Nap_density))
wntr.graphics.plot_network(wn,
node_attribute=Nap,
title='Articulation Point',
node_size=40,
node_range=[0, 1])
# Compute bridges
bridges = G.bridges()
wntr.graphics.plot_network(wn,
link_attribute=bridges,
title='Bridges',
link_width=2,
link_range=[0, 1])
Nbr_density = float(len(bridges)) / G.number_of_edges()
print("Density of bridges: " + str(Nbr_density))
# Compute spectal gap
spectral_gap = G.spectral_gap()
print("Spectal gap: " + str(spectral_gap))
# Compute algebraic connectivity
alg_con = G.algebraic_connectivity()
print("Algebraic connectivity: " + str(alg_con))
# Critical ratio of defragmentation
fc = G.critical_ratio_defrag()
print("Critical ratio of defragmentation: " + str(fc))
# Compute closeness centrality
clo_cen = nx.closeness_centrality(G)
wntr.graphics.plot_network(wn,
node_attribute=clo_cen,
title='Closeness Centrality',
node_size=40)
import networkx as nx
g = nx.read_gpickle("data/github.gpickle.1")
print(nx.info(g))
edgelist_format = []
for index, row in edgelist.iterrows(): # to get row indices of the data frame
inside = []
inside.append(edgelist.at[index, 'V1'])
inside.append(edgelist.at[index, 'V2'])
edgelist_format.append(inside) # appending pairs to main list iteratively
edgelist_format[:10]
# inside only gets stored for the most recent iteration
len(edgelist_format)
# length is corect and last entry is correct - verified with data frame/csv file
# Adding edges to the graph
G.add_edges_from(edgelist_format)
nx.info(
G
) # getting the correct number of edges in the graph object (number of nodes also coresponds to the max value
# from the csv file)
# degree sequence sorted in descending order
degree_sequence = sorted([d for n, d in G.degree()], reverse=True)
degree_sequence[:50]
# Sampling 1000 nodes from the degree sequence
degree_sequence_sample = random.sample(degree_sequence, 1000)
degree_sequence_sample.sort(reverse=True)
# degree distribution for the true network
degreeCount1 = collections.Counter(degree_sequence)
degr, cont = zip(*degreeCount1.items())
plt.bar(degr, cont, width=0.80, color='b')
import numpy as np
import networkx as nx
import matplotlib.pyplot as plt
import sys
sys.path.append('./src')
from dijkstra2 import dijkstra_2_src
A = np.loadtxt('./WG59/wg59_dist.txt')
G = nx.from_numpy_matrix(A)
T = dijkstra_2_src(G, 1, 5)
#a = np.array([v for v in G.nodes()])
print(nx.info(T))
nx.draw(G)
nx.draw(T)
plt.show()
def isomorphic_test_on_prod_rules(orig, tdfname, gname=""):
""""
orig: path to original/refernce input graph
tdfname: path fragment for a set of td pro rules
gname: graph name (str)
returns:
"""
# if whole tree path
# else, assume a path fragment
print '... input graph :', os.path.basename(orig)
print '... prod rules path frag :', tdfname
G = load_edgelist(orig) # load edgelist into a graph obj
N = G.number_of_nodes()
M = G.number_of_edges()
# +++ Graph Checks
if G is None: sys.exit(1)
G.remove_edges_from(G.selfloop_edges())
giant_nodes = max(nx.connected_component_subgraphs(G), key=len)
G = nx.subgraph(G, giant_nodes)
graph_checks(G)
# --- graph checks
G.name = gname
print "\t", nx.info(G)
files = glob(tdfname + "*.prs")
stacked_df = pd.DataFrame()
# mat_dict = {}
# for i, x in enumerate(sorted(files)):
# mat_dict[os.path.basename(x).split(".")[0].split("_")[-1]] = i
# if DBG: print os.path.basename(x).split(".")[0].split("_")[-1]
for prs in sorted(files):
tname = os.path.basename(prs).split(".")
tname = "_".join(tname[:2])
# print prs
# with open(prs, 'r') as f: # read tree decomp from inddgo
# lines = f.readlines()
# lines = [x.rstrip('\r\n') for x in lines]
df = pd.read_csv(prs, sep="\t", header=None)
print tname
df['cate'] = tname
stacked_df = pd.concat([df, stacked_df])
# print df.shape
print "\nStacked prod rules\n", "~" * 20
print " ", stacked_df.shape
if args['verb']: print stacked_df.to_string()
stacked_df.to_csv("../Results/{}_stacked_df.tsv".format(gname), sep="\t")
if os.path.exists(
"../Results/{}_stacked_df.tsv".format(gname)): print 'Wrote:', "../Results/{}_stacked_df.tsv".format(gname)
print "\nisomorphic union of the rules (_mod probs)\n", "~" * 20
stacked_df.columns = ['rnbr', 'lhs', 'rhs', 'pr', df['cate'].name]
iso_union, iso_interx = isomorph_intersection_2dfstacked(stacked_df)
print " ", iso_union.shape
if args['verb']: print iso_union.to_string()
print "\nIsomorphic intersection of the prod rules\n", "~" * 20
iso_interx = iso_interx[[1,2,3,4]]
# print iso_interx.head(); exit()
iso_interx.to_csv('../Results/{}_isom_interxn.tsv'.format(gname), header=False, index=False, sep="\t")
if os.path.exists('../Results/{}_isom_interxn.tsv'.format(gname)):
print 'Wrote:', '../Results/{}_isom_interxn.tsv'.format(gname)
def build_directed_graph(df,
path=work_david,
year=2000,
level='district',
graph_type='directed',
return_json=False):
import networkx as nx
import numpy as np
from networkx import NetworkXNotImplemented
"""Build a directed graph with a specific level hierarchy and year/s.
Input: df: original pandas DataFrame
year: selected year/s
level: district, county or city
return_json: convert networkx DiGraph object toJSON object and
return it.
Output: G: networkx DiGraph object or JSON object"""
print('Building {} graph with {} hierarchy level'.format(
graph_type, level))
# source = level_dict.get(level)['source']
# target = level_dict.get(level)['target']
df_sliced = choose_year(df, year=year, dropna=True)
node_sizes = node_sizes_source_target(df, year=year, level=level)
# node_geo = get_lat_lon_from_df_per_year(df, year=year, level=level)
# if weight_col is not None:
# df['weights'] = normalize(df[weight_col], 1, 10)
# else:
# df['weights'] = np.ones(len(df))
# df = df[df['Percent-migrants'] != 0]
G = create_G_with_df(df_sliced, level=level, graph_type=graph_type)
# G = nx.from_pandas_edgelist(
# df_sliced,
# source=source,
# target=target,
# edge_attr=[
# source,
# 'Percent-migrants',
# 'Direction',
# 'Number',
# 'Total',
# 'Distance',
# 'Angle'],
# create_using=Graph)
# enter geographical coords as node attrs:
geo = read_geo_name_cities(path=path)
for col in geo.columns:
dict_like = dict(
zip([x for x in G.nodes()], [geo.loc[x, col] for x in G.nodes()]))
nx.set_node_attributes(G, dict_like, name=col)
# slice df for just inflow:
df_in = df_sliced[df_sliced['Direction'] == 'inflow']
# calculate popularity index:
pi_dict = calculate_poplarity_index_for_InID(df_in)
total_dict_in = get_total_number_of_migrants(G, df_in, direction='In')
total_dict_out = get_total_number_of_migrants(G, df_in, direction='Out')
# set some node attrs:
nx.set_node_attributes(G, total_dict_in, 'total_in')
nx.set_node_attributes(G, total_dict_out, 'total_out')
total_net = {}
for (key1, val1), (key2, val2) in zip(total_dict_in.items(),
total_dict_out.items()):
assert key1 == key2
total_net[key1] = val1 - val2
nx.set_node_attributes(G, total_net, 'total_net')
# check that net totals is zero across network (conservation of people:-):
nets = []
for node in G.nodes():
nets.append(G.nodes()[node]['total_net'])
assert sum(nets) == 0
nx.set_node_attributes(G, pi_dict, 'popularity')
nx.set_node_attributes(G, node_sizes, 'size')
# nx.set_node_attributes(G, node_geo, 'coords_lat_lon')
G.name = 'Israeli migration network'
G.graph['level'] = level
G.graph['year'] = year
G.graph['density'] = nx.density(G)
try:
G.graph['triadic_closure'] = nx.transitivity(G)
except NetworkXNotImplemented as e:
print('nx.transitivity {}'.format(e))
# G.graph['global_reaching_centrality'] = nx.global_reaching_centrality(G, weight=weight_col)
# G.graph['average_clustering'] = nx.average_clustering(G, weight=weight_col)
# if weight_col is not None:
# print('adding {} as weights'.format(weight_col))
# # add weights:
# edgelist = [x for x in nx.to_edgelist(G)]
# weighted_edges = [
# (edgelist[x][0],
# edgelist[x][1],
# edgelist[x][2][weight_col]) for x in range(
# len(edgelist))]
# G.add_weighted_edges_from(weighted_edges)
print(nx.info(G))
for key, val in G.graph.items():
if isinstance(val, float):
print(key + ' : {:.2f}'.format(val))
else:
print(key + ' :', val)
# G, metdf = calculate_metrics(G, weight_col=weight_col)
if return_json:
return nx.node_link_data(G)
else:
return G
#Bueno para recursar
#Es buena debatiendo pero
print("Cloud from: Low rec teachers")
generate_word_cloud(low_rec_common)
#tokens = [t for t in low_rec_common.split()]
#freq = nltk.FreqDist(tokens)
#freq.plot(20, cumulative=False)
print("Cloud from: Medium rec teachers")
generate_word_cloud(medium_rec_common)
print("Cloud from: High rec teachers")
generate_word_cloud(high_rec_common)
#Compare the relevant words from each comment to every other comment to check for duplicates
#if a duplicate exists, then add an edge between those two nodes.
list_check = []
counter = 1
for i in range(0, len(comment_list) - 1):
for j in range(counter, len(comment_list)):
list_check = str(set(comment_list[i].split())) + str(
set(comment_list[j].split()))
if len(list_check) != len(set(list_check)):
for k in range(0, len(list_check) - len(set(list_check))):
graph.add_edge(comment_list[i], comment_list[j])
counter += 1
print(nx.info(graph))
nx.draw_random(graph)
plt.show()
# =============================================================================
# edge, nodes准备
# =============================================================================
edges = corrMatrix.stack().reset_index()
edges.columns = ['theOne', 'theOther', 'correlation']
# remove self correlations
# list, 含 pairwise correlation信息
edges = edges.loc[edges['theOne'] != edges['theOther']].copy()
# undirected graph with weights corresponding to the correlation magnitude
G0 = nx.from_pandas_edgelist(edges,
'theOne',
'theOther',
edge_attr=['correlation'])
print(nx.info(G0))
#%%
# =============================================================================
# Density
# =============================================================================
def get_density(G):
# How many possible edges?
possible_edges = len(G.nodes) * (len(G.nodes) - 1) / 2
actual_edges = len(G.edges)
return actual_edges / possible_edges
print('density: ', get_density(G0))
print('node connectivity: ', nx.node_connectivity(G0))
# まとめてedgeを追加
# G.add_edges_from([("A", "B"), ("B", "C"), ("B", "F"),("C", "D"), ("C", "E"), ("C", "F"), ("B", "F")])
# edgeを追加。有向グラフなので1つ目の引数がstart、2つ目の引数がtarget
for node_start, node_target in nodes_list:
print("node_start: %s, node_target: %s" % (node_start, node_target))
G.add_edge(node_start, node_target)
print("Edges: ", G.edges())
# G.remove_node(nodes_list[0][0])
# G.remove_node(nodes_list[0][1])
# Graphオブジェクトの情報
print("Info: ", nx.info(G))
# nodeの総数
print("number of nodes:", G.number_of_nodes())
# nodeの要素一覧
print("Nodes:", G.nodes())
# edgeの総数
print("Number of edges:", G.number_of_edges())
# edgeの要素一覧
print("Edges:", G.edges())
# 次数（nodeが持つedgeの数）
print("Degrees:", G.degree())
# 指定したノードに対する、隣接しているノードの数
print("Node: %s, Degree: %d" % ('0', G.degree('0')))
# 指定したノードに対する、隣接しているノードの一覧
print("nx.all_neighbors: ", list(nx.all_neighbors(G, '0')))
user = client.get_user(USER)
repo = user.get_repo(REPO)
stargazers = list(repo.get_stargazers()) #加星的用户集合
print repo
g = nx.DiGraph()
g.add_node(repo.name + '(repo)',
type='repo',
lang=repo.language,
owner=user.login)
for sg in stargazers:
g.add_node(sg.login + '(user)', type='user')
g.add_edge(sg.login + '(user)', repo.name + '(repo)', type='gazes')
# 打印图的基本属性
print(nx.info(g), '\n')
# 打印项目和用户点的基本属性
print(g.node['findspark(repo)'])
print(g.node['luzhijun(user)'], '\n')
# 打印这条边属性
print(g['luzhijun(user)']['findspark(repo)'])
# 打印起点为XXX的信息
print(g['luzhijun(user)'])
print(g['findspark(repo)'])
# 打印用户的出入度信息
print(g.in_edges(['luzhijun(user)']))
print(g.out_edges(['luzhijun(user)']))
# 打印项目的出入度信息
print(g.in_edges(['findspark(repo)']))
print(g.out_edges(['findspark(repo)']))
CDR.append(cdr)
#print(c.msisdn,contact.msisdn,random_date().strftime("%d-%m-%y %H:%M"),random.randint(0,120*60))
network_dict = {}
for cdr in CDR:
connection = cdr.caller.msisdn + "->" + cdr.called.msisdn
if connection not in network_dict:
network_dict[connection] = 1
else:
network_dict[connection] += 1
G_weighted = nx.Graph()
for c in network_dict:
G_weighted.add_edge(c.split("->")[0],
c.split("->")[1],
weight=network_dict[c])
print(nx.info(G_weighted))
pos = nx.spectral_layout(G_weighted)
betCent = nx.betweenness_centrality(G_weighted,
normalized=True,
endpoints=True)
node_color = [20000.0 * G_weighted.degree(v) for v in G_weighted]
node_size = [v * 1000 for v in betCent.values()]
plt.figure(figsize=(20, 20))
nx.draw_networkx(G_weighted,
pos=pos,
with_labels=False,
node_color=node_color,
node_size=node_size)
print "Importing Libraries"
import sys
import networkx as nx
print "Reading in Full Graph."
g = nx.read_edgelist('data/wiki-Talk.txt',
create_using=nx.DiGraph(),
nodetype=int)
print "Graph Imported, analysing basic info."
file = open("results/basic_info.txt", "w+")
file.write("*** Full Graph ***\n")
print "Basic Graph Info."
sys.stdout.flush()
file.write(nx.info(g))
print "Reciprocity."
sys.stdout.flush()
reciprocated = 0
for (u, v) in g.edges_iter():
if g.has_edge(v, u):
reciprocated = reciprocated + 1
file.write("\nReciprocity: {}\n".format(
float(reciprocated) / nx.number_of_edges(g)))
file.flush()
print "Clustering."
sys.stdout.flush()
file.write("Clustering: {}\n".format(nx.average_clustering(g.to_undirected())))
file.close()
'''
Creamos el grafo a partir del archivo datos.txt el cual contiene los valores de
cada nodo y el peso de las aristas
'''
GRAFO = nx.read_edgelist('data.txt',
create_using=tipo_grafo,
data=(('weight', float), ))
# Definimos nodo origen y destino para determinar la rutina más corta del grafo
origen = 'A'
destino = 'D'
'''
Imprimimos la información más importante del grafo como es el número de nodos, el número
número de aristas y el grado promedio
'''
print nx.info(GRAFO)
print("\n Ruta mas corta")
# Método que nos permite calcular la ruta más corta del grafo usando Dijkstra
ruta_mas_corta = nx.dijkstra_path(GRAFO, origen, destino)
print(' -> '.join(ruta_mas_corta))
print("Longitud de la ruta mas corta")
# Método que nos permite calcular la longitud de la ruta más corta del grafo
print(nx.dijkstra_path_length(GRAFO, origen, destino))
# Métodos para dibujar el grafo en 2D con los nombres de cada nodo
nx.draw(GRAFO, with_labels=True)
plt.show()
# reorder nodes from 0,len(G)-1
node_id += 1
if edge1 in edges_map.keys():
edges_map[edge1].append(edge2)
nr_edges += 1
else:
edges_map[edge1] = [edge2]
nr_edges += 1
G = nx.Graph()
for n in nodes.keys():
G.add_node(nodes[n], id=nodes[n], predicate='user')
for e in edges_map.keys():
for e1 in edges_map[e]:
G.add_edge(nodes[e], nodes[e1])
pickle.dump(G, open(FILE_NAME, 'wb'))
data = nx.read_gpickle(FILE_NAME)
print("Nr nodes AMAZON: ", len(data.nodes()))
print("Nr edges AMAZON: ", len(data.edges()))
print("Max degree AMAZON: ", an.get_maximum_node_degree(data))
print("Density AMAZON: ", nx.density(data))
print("INFO AMAZON:", nx.info(data))
#print an.get_maximum_node_degree(graph)
number_of_pages = 0
for node in data.nodes():
if data.node[node]['predicate'] == 'page':
number_of_pages += 1
vis.visualize_graph_standard(data)
edges = [tuple(e) for e in df.values]
# print('Nodes:', len(node_names))
# print('Edges:', len(edges))
# resultFile.write('Nodes: {} '.format(len(node_names)) + '\n')
# print('\n')
# This will create a new Graph object
G = nx.Graph()
# add your lists of nodes and edges like so:
G.add_nodes_from(node_names)
G.add_edges_from(edges)
# get basic information about your newly-created network using the info function:
print(nx.info(G), '\n')
resultFile.write('# Information about the newly-created network is:\n{}'.
format(nx.info(G)) + '\n\n')
# Compute the following node measures:
print('# Compute the following node measures: \n')
resultFile.write('# Compute the following node measures:' + '\n\n')
# a. Degree Centrality (normalized)
degree_centrality = degree_centrality(G)
sorted_degree = sorted(degree_centrality.items(),
key=itemgetter(1),
reverse=True)
print("# Top 10 nodes by degree centrality:")
resultFile.write('# Top 10 nodes by degree centrality:' + '\n')
'''building graph from dataset using networkx'''
import networkx as nx
import pickle
import json
class Graph(object):
def __init__(self, edges, author, w, trainingSet, testingSet):
self.train = nx.Graph()
self.test = nx.Graph()
for (node1, node2), year in edges:
weightEdge = 1 / w[(node1, node2)]
if year >= trainingSet[0] and year <= trainingSet[1]:
self.train.add_edge(node1, node2, weight=weightEdge)
elif year >= testingSet[0] and year <= testingSet[1]:
self.test.add_edge(node1, node2, weight=weightEdge)
self.train = max(nx.connected_component_subgraphs(self.train), key=len)
if __name__ == "__main__":
edges = pickle.load(open("newEdges.p", "rb"))
authors = pickle.load(open("newAuthor.p", "rb"))
w = pickle.load(open("weights.p", "rb"))
dataGraph = Graph(edges, authors, w, [1967, 2006], [2007, 2017])
print(nx.info(dataGraph.train))
pickle.dump(dataGraph, open('graph_data.p', "wb"))
except:
try:
with open(datafn, 'rb') as f:
G = pickle.load(f, encoding='latin1')
except Exception as ex:
print(ex)
print('Could not open graph: {}'.format(datafn))
sys.exit(0)
for n in G.nodes():
G.node[n] = {}
if method == 'percolation':
G = max(nx.connected_component_subgraphs(G), key=len)
print(nx.info(G))
ns = NodeRanking.get_instance(method, G)
flag = 0
for s in ['asc', 'desc']:
fn = os.path.join(output, '{}_{}_{}.pickle'.format(name, method, s))
if os.path.exists(fn):
flag += 1
if flag < 2:
ns.compute_node_scores()
for s in ['asc', 'desc']:
fn = os.path.join(output,
'{}_{}_{}.pickle'.format(name, method, s))
def corpus_graph(self,
language_file,
limit_range=3000000,
verbose=False,
lemmatizer=None,
stopwords=None,
min_char=4,
stemmer=None,
input_type="file"):
G = nx.DiGraph()
ctx = 0
reps = False
dictionary_with_counts_of_pairs = {}
def process_line(line):
nonlocal G
nonlocal ctx
nonlocal reps
nonlocal dictionary_with_counts_of_pairs
stop = list(string.punctuation)
line = line.strip()
line = [i for i in word_tokenize(line.lower()) if i not in stop]
if not stopwords is None:
line = [w for w in line if not w in stopwords]
if not stemmer is None:
line = [stemmer.stem(w) for w in line]
if not lemmatizer is None:
new_line = []
for x in line:
lemma = lemmatizer.lemmatize(x)
if not (lemma in self.inverse_lemmatizer_mapping):
self.inverse_lemmatizer_mapping[lemma] = set()
self.inverse_lemmatizer_mapping[lemma].add(x)
new_line.append(lemma)
line = new_line
line = [x for x in line if len(x) > min_char]
if len(line) > 1:
ctx += 1
if ctx % 15000 == 0:
logging.info("Processed {} sentences.".format(ctx))
if ctx % limit_range == 0:
return True
for enx, el in enumerate(line):
if enx > 0:
edge_directed = (line[enx - 1], el)
if edge_directed[0] != edge_directed[1]:
G.add_edge(edge_directed[0], edge_directed[1])
else:
edge_directed = None
if enx < len(line) - 1:
edge_directed = (el, line[enx + 1])
if edge_directed[0] != edge_directed[1]:
G.add_edge(edge_directed[0], edge_directed[1])
else:
edge_directed = None
if edge_directed:
if edge_directed in dictionary_with_counts_of_pairs:
dictionary_with_counts_of_pairs[edge_directed] += 1
reps = True
else:
dictionary_with_counts_of_pairs[edge_directed] = 1
return False
if input_type == "file":
with open(language_file) as lf:
for line in lf:
breakBool = process_line(line)
if breakBool:
break
elif input_type == "text":
lines = language_file.split("\n")
for line in lines:
breakBool = process_line(line)
if breakBool:
break
## assign edge properties.
for edge in G.edges(data=True):
try:
edge[2]['weight'] = dictionary_with_counts_of_pairs[(edge[0],
edge[1])]
except Exception as es:
raise (es)
if verbose:
print(nx.info(G))
return (G, reps)
prev_state = state
if bystate is True:
# now simplify the multigraph by adding up the weights of
# multi-edges between any two nodes
for e in mg1.edges():
if g1.has_edge(*e):
continue
#print "Sum: ", sum([i['weight'] for i in mg1[e[0]][e[1]].values()])
g1.add_edge(e[0],
e[1],
weight=sum(
[i['weight'] for i in mg1[e[0]][e[1]].values()]))
print nx.info(g1)
#print "g1 nodes: ", str(g1.nodes())
#print "g1 edges: ", str(g1.edges(data=True))
#print "mg1 edges: ", str(mg1.edges(data=True))
#print "mg1 edges: ", str(mg1.edges(data=True))
g2 = nx.Graph(name="g2")
for n1 in senators:
for n2 in senators:
if n1 == n2:
continue
n1_bills = g1.neighbors(n1)
n2_bills = g1.neighbors(n2)
common_bills = list(set(n1_bills) & set(n2_bills))
if len(common_bills) is 0:
import networkx as nx G = nx.Graph() G.add_node(1) G.add_nodes_from([2, 3]) G.add_edge(1, 2) print G.nodes() nx.draw(G) print nx.info(G)
print(path) g1 = nx.scale_free_graph(size) cyjs1 = test_tools.TestTools.networkx_to_cyjs(g1) tt = test_tools.TestTools(BASE, VERBOSE) print(json.dumps(cyjs1)) # job_id = tt.post_job(path, json.dumps(cyjs1) ) job_id = tt.submit_network_to_service(path, cyjs1) res = tt.get_result(job_id, SLEEP_INTERVAL, 10) # print( res.json() ) cyjs2 = res.json() print(json.dumps(cyjs2, indent=4)) # print( 'Result is at http://192.168.59.103/v1/jobs/' + job_id ) g2 = tt.cyjs_to_networkx(cyjs2) print(nx.info(g2)) print(g2.nodes()) print(g2.edges()) print(tt.is_isomorphic(g1, g2)) # res = tt.delete_job( job_id ) # print(res) # print(json.dumps(res.json(), indent=4))
'source': np.array([ 0, 0.5])}
width=[float(d['weight']*1.2) for (u,v,d) in gd.edges(data=True)]
edge_labels=dict([((u,v,),d['weight']) for u,v,d in gd.edges(data=True)])
nx.draw_networkx_edge_labels(gd,pos,edge_labels=edge_labels, font_size = 15, alpha = .5)
nx.draw(gd, pos, node_size = 3000, node_color = 'orange',
alpha = 0.2, width = width, edge_color='orange',style='solid')
nx.draw_networkx_labels(gd,pos,font_size=18)
plt.show()
# In[10]:
nx.info(gd)
# In[11]:
# flow matrix
m = fn.getFlowMatrix(gd)
m
# In[12]:
fn.networkDissipate(gd)