def test_bipartite_weighted_degrees(self):
G = nx.path_graph(5)
G.add_edge(0, 1, weight=0.1, other=0.2)
X = {1, 3}
Y = {0, 2, 4}
u, d = bipartite.degrees(G, Y, weight="weight")
assert dict(u) == {1: 1.1, 3: 2}
assert dict(d) == {0: 0.1, 2: 2, 4: 1}
u, d = bipartite.degrees(G, Y, weight="other")
assert dict(u) == {1: 1.2, 3: 2}
assert dict(d) == {0: 0.2, 2: 2, 4: 1}
def test_bipartite_weighted_degrees(self):
G=nx.path_graph(5)
G.add_edge(0,1,weight=0.1,other=0.2)
X=set([1,3])
Y=set([0,2,4])
u,d=bipartite.degrees(G,Y,weight='weight')
assert_equal(u,{1:1.1,3:2})
assert_equal(d,{0:0.1,2:2,4:1})
u,d=bipartite.degrees(G,Y,weight='other')
assert_equal(u,{1:1.2,3:2})
assert_equal(d,{0:0.2,2:2,4:1})
def test_bipartite_weighted_degrees(self):
G = nx.path_graph(5)
G.add_edge(0, 1, weight=0.1, other=0.2)
X = set([1, 3])
Y = set([0, 2, 4])
u, d = bipartite.degrees(G, Y, weight='weight')
assert_equal(u, {1: 1.1, 3: 2})
assert_equal(d, {0: 0.1, 2: 2, 4: 1})
u, d = bipartite.degrees(G, Y, weight='other')
assert_equal(u, {1: 1.2, 3: 2})
assert_equal(d, {0: 0.2, 2: 2, 4: 1})
def partition_strings_2set(X, C, X_file, C_file, params):
"""
"""
G_star = graphs.construct_exact_2set_nearest_neighbor_bipartite_graph(
X, C, X_file, C_file, params)
# G_star, alignment_graph = graphs.construct_2set_nearest_neighbor_bipartite_graph(X, C, X_file, C_file)
G_star_transposed = nx.reverse(G_star) #functions.transpose(G_star)
partition = {
} # dict with a center as key and a set containing all sequences chosen to this partition
# candidate_nodes, read_nodes = bipartite.sets(G_star_transposed)
read_nodes = set(n for n, d in G_star_transposed.nodes(data=True)
if d['bipartite'] == 0)
candidate_nodes = set(G_star_transposed) - read_nodes
read_deg, cand_deg = bipartite.degrees(G_star_transposed, candidate_nodes)
# print(len(read_nodes), len(candidate_nodes))
# print(read_deg)
# print(cand_deg)
######################
while len(candidate_nodes) > 0:
read_deg, cand_deg = bipartite.degrees(G_star_transposed,
candidate_nodes)
read_deg, cand_deg = dict(read_deg), dict(cand_deg)
# print(type(read_deg), read_deg)
# print(type(cand_deg), cand_deg)
# print("reads left:", len(read_deg))
# print("cands left:", len(cand_deg))
m = max(sorted(cand_deg), key=lambda key: cand_deg[key])
reads_supporting_m = list(G_star_transposed.neighbors(m))
partition[m] = set(reads_supporting_m)
G_star_transposed.remove_node(m)
G_star_transposed.remove_nodes_from(reads_supporting_m)
read_nodes = set(n for n, d in G_star_transposed.nodes(data=True)
if d['bipartite'] == 0)
candidate_nodes = set(G_star_transposed) - read_nodes
# candidate_nodes, read_nodes = bipartite.sets(G_star_transposed)
# print("total nodes left after removal:", len(G_star_transposed.nodes()), "tot candidate nodes left:", candidate_nodes)
# print(read_nodes, [G_star[node] for node in read_nodes])
# print(len(reads_supporting_m) , len(G_star_transposed.nodes()), G_star_transposed.nodes() )
# print([ (m,len(partition[m])) for m in partition] )
#####################
return G_star, partition
def collaborativeness(B):
# splitting the types of nodes of the graph object B
top_nodes = set(node for node, d in B.nodes(data=True)
if d['bipartite'] == 0) #set of top nodes
bottom_nodes = set(B) - top_nodes #set of bottom nodes
deg_top, deg_bottom = bipartite.degrees(
B, bottom_nodes) #dictionary: nodes as keys, degrees as values
# creating simple graph and multigraph bottom projections
G = bipartite.projected_graph(B, bottom_nodes)
Gm = bipartite.projected_graph(B, bottom_nodes, multigraph=True)
col_dict = {}
#ratio_dict = {}
#div_dict = {}
for node in bottom_nodes:
if G.degree(node) > 0:
gamma = 0
shared = 0
for nbr in B[node]:
gamma += math.log(B.degree(nbr))
if B.degree(nbr) > 1:
shared += 1
col_dict[node] = ((float(shared) / B.degree(node)) * gamma,
float(G.degree(node)) / Gm.degree(node))
#ratio_dict[node] = (float(shared)/B.degree(node))
#diversity_dict[node] = float(G.degree(node))/Gm.degree(node)
return col_dict
def test_bipartite_degrees(self):
G = nx.path_graph(5)
X = {1, 3}
Y = {0, 2, 4}
u, d = bipartite.degrees(G, Y)
assert dict(u) == {1: 2, 3: 2}
assert dict(d) == {0: 1, 2: 2, 4: 1}
def test_bipartite_degrees(self):
G = nx.path_graph(5)
X = set([1, 3])
Y = set([0, 2, 4])
u, d = bipartite.degrees(G, Y)
assert dict(u) == {1: 2, 3: 2}
assert dict(d) == {0: 1, 2: 2, 4: 1}
def test_bipartite_degrees(self):
G = nx.path_graph(5)
X = set([1, 3])
Y = set([0, 2, 4])
u, d = bipartite.degrees(G, Y)
assert_equal(u, {1: 2, 3: 2})
assert_equal(d, {0: 1, 2: 2, 4: 1})
def test_bipartite_degrees(self):
G=nx.path_graph(5)
X=set([1,3])
Y=set([0,2,4])
u,d=bipartite.degrees(G,Y)
assert_equal(u,{1:2,3:2})
assert_equal(d,{0:1,2:2,4:1})
def degree_distribution(G, nodes,weight):
if weight == True:
degree_values_users, degree_values_posts = bipartite.degrees(G,nodes,'weight')
else:
degree_values_users, degree_values_posts = bipartite.degrees(G,nodes)
#take a look at first 20 entries in each
def take(n, iterable):
"Return first n items of the iterable as a list"
return list(islice(iterable, n))
#print take(20,degree_values_posts.iteritems())
#print take(20,degree_values_users.iteritems())
vals_posts=degree_values_posts.values()
average_degree_p = sum(vals_posts)/float(len(vals_posts))
#crop out larger values
vals_posts= [s for s in vals_posts if s<=2000]
data_posts=Counter(vals_posts)
"""
vals_users=degree_values_users.values()
average_degree_u = sum(vals_users)/float(len(vals_users))
#crop out larger values
vals_users=[s for s in vals_users if s<=100]
data_users=Counter(vals_users)
"""
plt.figure(1)
plt.subplot(211)
plt.hist(data_posts.keys(),label = "Average Degree = %s" %(average_degree_p))
plt.title("Degree Distribution (post-projection) Histogram")
plt.xlabel("Degree")
plt.ylabel("Number of nodes with degree")
plt.legend(loc='best')
"""
plt.subplot(212)
plt.hist(data_users.keys(),label = "Average Degree = %s" %(average_degree_u))
plt.title("Degree Distribution (user-projection) Histrogram")
plt.xlabel("Degree")
plt.ylabel("Number of nodes with degree")
plt.legend(loc='best')
"""
plt.show()
def get_deg_list_by_partition(graph, partition):
"""
Get degree distribution for given partition of bipartite graph
"""
if not bipartite.is_bipartite(graph):
return []
nodes = [
node for node in graph.nodes
if graph.nodes[node]['bipartite'] == partition
]
return bipartite.degrees(graph, nodes)[1]
def suffle_edges_lc(G):
# Get the largest component
print("Getting largest component ...")
components = sorted(nx.connected_components(G), key=len, reverse=True)
largest_component = components[0]
C = G.subgraph(largest_component)
degX, degY = bipartite.degrees(C, nodes_0)
degATC = dict(degX).values()
degCIE = dict(degY).values()
counterATC = collections.Counter(degATC)
counterCIE = collections.Counter(degCIE)
nodes_0_c = []
nodes_1_c = []
for n in C.nodes(data=True):
if n[1]['bipartite'] == 0:
nodes_0_c.append(n[0])
if n[1]['bipartite'] == 1:
nodes_1_c.append(n[0])
print("Shuffling edges ... ")
unfrozen_graph = nx.Graph(C)
# C_shuffled = copy.copy(C)
k = 0
iter = 2 * unfrozen_graph.size()
while k < iter:
r1 = random.choice(sorted(dict(degY).keys()))
d1 = random.choice(list(unfrozen_graph.neighbors(r1)))
r2 = random.choice(sorted(dict(degY).keys()))
d2 = random.choice(list(unfrozen_graph.neighbors(r2)))
if (unfrozen_graph.has_edge(r1, d2)
== False) & (unfrozen_graph.has_edge(r2, d1) == False):
unfrozen_graph.add_edge(r1, d2)
unfrozen_graph.remove_edge(r1, d1)
unfrozen_graph.add_edge(r2, d1)
unfrozen_graph.remove_edge(r2, d2)
# print(k)
k = k + 1
return unfrozen_graph, counterATC, counterCIE, dict(degX), dict(
degY), nodes_0_c, nodes_1_c
def from_bipartitegraph_to_mergesplitmetric(bipart_graph, sv_nodes):
degX, degY = bipartite.degrees(bipart_graph, sv_nodes)
num_of_merges = 0
SVids_merger = []
skeleton_groups = []
for node_id, node_degree in degY.iteritems():
if node_degree > 1:
num_of_merges += node_degree - 1
SVids_merger.append(node_id)
skeletons = bipart_graph[node_id].keys(
) # This gets all the nodes the node is connected to.
skeletons = [int(id, 16) for id in skeletons]
skeleton_groups.append(skeletons)
num_of_splits = 0
for node_id, node_degree in degX.iteritems():
if node_degree > 1:
num_of_splits += node_degree - 1
return num_of_merges, num_of_splits, skeleton_groups, SVids_merger
def commit_here(username):
G = nx.Graph()
users = set()
users.update(user
for user in followers(username, page="1", followers_list=[]))
users.update(user
for user in following(username, page="1", following_list=[]))
users = list(users)
repos = set()
user2repo = []
for user in users:
if user == username:
continue
user_repos = get_repos(user, url="", repo_list=[])
repos.update(repo + "_repo" for repo in user_repos)
user2repo += [(user, repo + "_repo") for repo in user_repos]
repos = list(repos)
G.add_nodes_from(users, bipartite="users")
G.add_nodes_from(repos, bipartite="repos")
G.add_edges_from(user2repo)
for repo in repos:
degX, degY = bipartite.degrees(G, repo)
break
degX = list(degX)
repos_only = []
for ind in degX:
if ind[0] not in users:
repos_only.append(ind)
repos_only.sort(key=lambda x: x[-1], reverse=True)
repos_only = [list(repo) for repo in repos_only]
return repos_only[:10]
#use one less process to be a little more stable
#p = multiprocessing.Pool(processes = multiprocessing.cpu_count()-5)
p = multiprocessing.Pool()
#timing it...
start = time.time()
# for file in names:
# p.apply_async(multip, [file])
for i in range(1, 5, 1):
print("Shuffle edges ... iteration " + str(i))
#H = add_and_remove_edges(C, type_proj, dict(degX), dict(degY))
C, counterATC, counterCIE, degX, degY, nodes_0_c, nodes_1_c = suffle_edges_lc(
G)
# suffle_edges(C, sorted(dict(degX).keys()), sorted(dict(degY).keys()))
degX_sh, degY_sh = bipartite.degrees(C, nodes_0_c)
degATC_sh = dict(degX_sh).values()
degCIE_sh = dict(degY_sh).values()
counterATC_sh = collections.Counter(degATC_sh)
counterCIE_sh = collections.Counter(degCIE_sh)
nx.write_graphml(C, 'networks/bipartite_sh_' + str(i) + '.graphml')
print("Apply threshold analysis to shuffled graph ... " + str(i))
for th_icd in sorted(list(counterCIE_sh.keys())):
p.apply_async(threshold_analysis, [C, th_icd, 0, len(degY_sh), i])
for th_atc in sorted(list(counterATC_sh.keys())):
p.apply_async(threshold_analysis, [C, th_atc, 1, len(degX_sh), i])
# if type_proj == 0:
# for th in sorted(list(counterCIE_sh.keys())):
if u in M:
del_edges.append((u, v))
B.remove_edges_from(del_edges)
sys.stderr.write("\nedges after deletion are: " + str(B.edges()))
if nx.is_bipartite(B):
logging.info("\n ... graph is bipartite.")
else:
logging.info("\n ... graph is NOT bipartite.")
numOfNodes = B.number_of_nodes()
numOfEdges = B.number_of_edges()
k = numOfEdges
logging.info(
'\n...done. Created a bipartite graph with %d nodes and %d edges' %
(numOfNodes, numOfEdges))
degN, degM = bipartite.degrees(B, M)
degrees = dict(degN)
print("degree dict: " + str(degrees))
descending_degrees = sorted(degrees.values(), reverse=True)
print("degrees descending: " + str(descending_degrees))
sorted_nodes = sorted(range(len(degrees.values())),
key=lambda c: degrees.values()[c],
reverse=True)
print("nodes sorted by descending degrees: " + str(sorted_nodes))
max_degree = descending_degrees[0]
min_degree = descending_degrees[-1]
mean = (sum(degrees.values()) * 1.0) / len(degrees)
std_dev = np.sqrt((sum([(degrees[i] - mean)**2
for i in degrees]) * 1.0) / len(degrees))
logging.info(
'\nMax degree: %s, min degree: %s, mean: %s, and standard deviation: %s.'
def threshold(G, bp):
degX, degY = bipartite.degrees(G, nodes_0)
degATC = dict(degX).values()
degCIE = dict(degY).values()
counterATC = collections.Counter(degATC)
counterCIE = collections.Counter(degCIE)
c_list = []
nc_list = []
nuc_list = []
if bp == 0:
for th in sorted(list(counterCIE.keys())):
#th = 1
H = nx.Graph()
#for v in G.nodes(data = True):
# if v[1]['bipartite'] == 0:
# H.add_node(v[0])
for n in G.nodes(data=True):
if n[1]['bipartite'] == 0:
sourceNode = n[0]
s_neighbors = set(G.neighbors(n[0]))
for m in G.nodes(data=True):
if m[1]['bipartite'] == 0: #### Change to 1 to change the projection to active ingredient
targetNode = m[0]
t_neighbors = set(G.neighbors(m[0]))
if sourceNode != targetNode:
if len(s_neighbors & t_neighbors) >= th:
H.add_node(sourceNode)
H.add_node(targetNode)
H.add_edge(sourceNode, targetNode)
components = sorted(nx.connected_components(H),
key=len,
reverse=True)
#sum(list(map(lambda c: len(c), components)))
c_list.append(len(components))
nodes_connected = sum(list(map(lambda c: len(c), components)))
nc_list.append(nodes_connected)
nuc_list.append(len(nodes_0) - nodes_connected)
#nx.write_graphml(H,'proCIE_th_'+str(th)+'.graphml')
else:
for th in sorted(list(counterATC.keys())):
#th = 136
H = nx.Graph()
#for v in G.nodes(data = True):
# if v[1]['bipartite'] == 1:
# H.add_node(v[0])
for n in G.nodes(data=True):
if n[1]['bipartite'] == 1:
sourceNode = n[0]
s_neighbors = set(G.neighbors(n[0]))
for m in G.nodes(data=True):
if m[1]['bipartite'] == 1: #### Change to 1 to change the projection to active ingredient
targetNode = m[0]
t_neighbors = set(G.neighbors(m[0]))
if sourceNode != targetNode:
if len(s_neighbors & t_neighbors) >= th:
#print(len(s_neighbors & t_neighbors))
#print(sourceNode + " " + targetNode)
H.add_node(sourceNode)
H.add_node(targetNode)
H.add_edge(sourceNode, targetNode)
components = sorted(nx.connected_components(H),
key=len,
reverse=True)
c_list.append(len(components))
nodes_connected = sum(list(map(lambda c: len(c), components)))
nc_list.append(nodes_connected)
nuc_list.append(len(nodes_1) - nodes_connected)
#nx.write_graphml(H,'proATC_th_'+str(th)+'.graphml')
#degXH,degYH=bipartite.degrees(H,nodes_0)
#degATCH = dict(degXH).values()
#degCIEH = dict(degYH).values()
#counterATCH = collections.Counter(degATCH)
#counterCIEH = collections.Counter(degCIEH)
return c_list, nc_list, nuc_list, counterATC, counterCIE
user2repo = []
for user in users:
if user == username: # Don't recommend self repos
continue
user_repos = get_repos(user, url="", repo_list=[])
repos.update(repo + "_repo" for repo in user_repos)
user2repo += [(user, repo + "_repo") for repo in user_repos]
repos = list(repos)
G.add_nodes_from(users, bipartite="users")
G.add_nodes_from(repos, bipartite="repos")
G.add_edges_from(user2repo)
nx.write_edgelist(G, "imro8_bipartite_recommending_repo.edgelist")
# G = nx.read_edgelist('imro8_bipartite_recommending_repo.edgelist')
# print(G.edges())
# repos = ['teach-flask-through-doing_repo', 'Hades_App_repo']
for repo in repos:
degX, degY = bipartite.degrees(G, repo)
break
degX = list(degX)
repos_only = []
for ind in degX:
if ind[0] not in users:
repos_only.append(ind)
repos_only.sort(key=lambda x: x[-1], reverse=True)
print(repos_only[:10])
bipartite=0) # Add the node attribute “bipartite” disease
G.add_nodes_from(nodes_1, bipartite=1) # active substance
# Add edges without weight
for m in vdmdata.iterrows():
enfermedad = m[1][0]
#peso = m[1][3];
sustancia = m[1][1]
G.add_edge(enfermedad, sustancia)
print("Getting largest component ...")
components = sorted(nx.connected_components(G), key=len, reverse=True)
largest_component = components[0]
C = G.subgraph(largest_component)
degX, degY = bipartite.degrees(C, nodes_0)
degATC = dict(degX).values()
degCIE = dict(degY).values()
counterATC = collections.Counter(degATC)
counterCIE = collections.Counter(degCIE)
df_icd = pd.DataFrame(dict(degY).items(), columns=['node', 'degree'])
df_atc = pd.DataFrame(dict(degX).items(), columns=['node', 'degree'])
df_icd = df_icd.sort_values(by=['degree', 'node'], ascending=False)
df_atc = df_atc.sort_values(by=['degree', 'node'], ascending=False)
nodes_0_c = []
nodes_1_c = []
for n in C.nodes(data=True):
if n[1]['bipartite'] == 0:
#--------------------------------------------------------------------------
# Calculate the density of the bipartite graph
#--------------------------------------------------------------------------
print(round(bipartite.density(B, bottom_nodes), 3))
#--------------------------------------------------------------------------
# Calculate the degree distribution of universities from the bipartite projected graph.
# We need to have a multigraph because it works for counting the mappings
#--------------------------------------------------------------------------
U = bipartite.weighted_projected_graph(B, bottom_nodes)
#--------------------------------------------------------------------------
# Calculate the degree for the top and bottom nodes of the bipartite graph
#--------------------------------------------------------------------------
import operator
degX, degY = bipartite.degrees(U, top_nodes, weight='weight')
#universites
a, b = zip(*degX)
degreeCount = collections.Counter(b)
deg, cnt = zip(*degreeCount.items())
#The degree seq below does not take into account the weights of the edges
#degree_sequence = sorted([d for n, d in U.degree()], reverse=True) # degree sequence
#degreeCount = collections.Counter(degree_sequence)
plt.rcParams['axes.facecolor'] = 'grey'
plt.rcParams['savefig.facecolor'] = 'grey'
fig, ax = plt.subplots(figsize=(10, 8))
#plt.title("Degree Histogram and Graph of Universities",fontsize=11)
plt.ylabel("Count of links", fontsize=14)
plt.xlabel("Degree", fontsize=14)
B = nx.Graph()
edges = []
x = 0
for i in range(len(top_nodes)):
edges.append((top_nodes[i], bottom_nodes[i], weight[i]))
B.add_weighted_edges_from(edges)
# print(B.edges())
# 二模转一模
# G=bipartite.projected_graph(B,bottom_nodes,multigraph=True)
# print(G.edges(keys=True))
# 计算二模网络的度
degX,degY=bipartite.degrees(B,bottom_nodes,weight='weight')
# 计算二模网络的点度中心性
D = bipartite.degree_centrality(B, bottom_nodes)
degX_dict, degY_dict, D_dict = dict(degX), dict(degY), dict(D)
print('模1的度为：', len(degX), degX_dict, '模2的度为：', len(degY), degY_dict, '模2的点度中心性', len(D), D_dict, sep='\n')
arcpy.env.overwriteOutput = True
targetsource1 = targetsource + 'output'
print(targetsource)
arcpy.Copy_management(in_data=targetsource, out_data=targetsource1)
mo2fieldname,mo1fieldname,mo2centraldegree = 'mo2degree', 'mo1degree', 'mo2centraldegree'
arcpy.AddField_management(targetsource1, mo2fieldname, "FLOAT",field_alias=mo2fieldname, field_is_nullable="NULLABLE")
arcpy.AddField_management(targetsource1, mo1fieldname, "FLOAT",field_alias=mo1fieldname, field_is_nullable="NULLABLE")