def L_P_RWWR(network):
num_add = 0 # the number of egdes to be added
nodes_pair_without_edge = [] # the pairs of nodes without edges
probability_add = [] # the probabilities of the pairs of nodes to be added
score = 0 # the score of each pair of nodes in link prediction model
total_score_without_edge = 0.0 # the sum of scores of pairs of nodes without edge
# calculate the score of each pair of nodes
for i, elei in enumerate(list(network.nodes()), 1):
for j, elej in enumerate(list(network.nodes()), 1):
if i >= j:
continue
if not network.has_edge(elei, elej):
try:
score = (CCD(network, elei, elej, i, j, 0.15) +
CCD(network, elej, elei, j, i, 0.15)) / 2
except:
continue
total_score_without_edge += score
nodes_pair_without_edge.append((elei, elej, score))
for a, b, c in nodes_pair_without_edge:
probability_add.append(
c / total_score_without_edge
) # calculate the probabilities of edges to be added
# select edges to be added according to probabilities
edges_add = calculate_param.prob_select_distinct(nodes_pair_without_edge,
probability_add, num_add)
for a, b, c in edges_add:
network.add_edge(a, b) # add selected edges
return True
def L_P_KatzIndex(network, max_length):
num_add = 0 # the number of egdes to be added
nodes_pair_without_edge = [] # the pairs of nodes without edges
probability_add = [] # the probabilities of the pairs of nodes to be added
score = 0.0 # the score of each pair of nodes in link prediction model
score_old = 0.0 # the last score of each pair of nodes in link prediction model
total_score_without_edge = 0.0 # the sum of scores of pairs of nodes without edge
B = 0.1 # a free parameter to control path weights. The longer the path is, the less contribution the path made to the similarity
# calculate the score of each pair of nodes
for i, elei in enumerate(list(network.nodes())):
for j, elej in enumerate(list(network.nodes())):
if i >= j:
continue
if not network.has_edge(elei, elej):
try:
for l in range(2, max_length):
score_old = score
score += pow(B, l) * pow(nx.to_numpy_array(network),
l)[i][j]
if is_katz_converge(score, score_old):
break
except:
continue
total_score_without_edge += score
nodes_pair_without_edge.append((elei, elej, score))
for a, b, c in nodes_pair_without_edge:
probability_add.append(
c / total_score_without_edge
) # calculate the probabilities of edges to be added
# select edges to be added according to probabilities
edges_add = calculate_param.prob_select_distinct(nodes_pair_without_edge,
probability_add, num_add)
for a, b, c in edges_add:
network.add_edge(a, b) # add selected edges
return True
def L_P_ACT(network):
num_add = 0 # the number of egdes to be added
nodes_pair_without_edge = [
] # the pairs of nodes with edges and without edges
probability_add = [] # the probabilities of the pairs of nodes to be added
score = 0.0 # the score of each pair of nodes in link prediction model
total_score_without_edge = 0.0 # the sum of scores of pairs of nodes without edge
# calculate the score of each pair of nodes
for i, elei in enumerate(list(network.nodes(), 0)):
for j, elej in enumerate(list(network.nodes(), 0)):
if i >= j:
continue
if not network.has_edge(elei, elej):
try:
L = nx.laplacian_matrix(network).A
L_aa = L[i][i]
L_bb = L[j][j]
L_ab = L[i][j] # 修改L[a][b]变为L[i][j]
score = 1 / L_aa + L_bb - 2 * L_ab
except:
continue
total_score_without_edge += score
nodes_pair_without_edge.append((elei, elej, score))
for a, b, c in nodes_pair_without_edge:
probability_add.append(
c / total_score_without_edge
) # calculate the probabilities of edges to be added
# select edges to be added according to probabilities
edges_add = calculate_param.prob_select_distinct(nodes_pair_without_edge,
probability_add, num_add)
for a, b, c in edges_add:
network.add_edge(a, b) # add selected edges
return True
def L_P_SimRank(network, C=0.8, max_iter=100):
# C: float, 0< C <=1, it is the decay factor which represents the relative importance between in-direct neighbors and direct neighbors.
# max_iter: integer, the number specifies the maximum number of iterations for simrank
num_add = 0 # the number of egdes to be added
nodes_pair_without_edge = [] # the pairs of nodes without edges
probability_add = [] # the probabilities of the pairs of nodes to be added
score = 0.0 # the score of each pair of nodes in link prediction model
total_score_without_edge = 0.0 # the sum of scores of pairs of nodes without edge
# init.vars
sim = defaultdict(list) # the similarity between two nodes
sim_old = defaultdict(
list) # the similarity between two nodes in last recursion
for n in network.nodes():
sim[n] = defaultdict(int)
sim[n][n] = 1
sim_old[n] = defaultdict(int)
sim_old[n][n] = 0
# recursively calculate simrank
for iter_ctr in range(max_iter):
if _is_sim_converge(sim, sim_old):
break
# calculate the score of each pair of nodes
sim_old = copy.deepcopy(sim)
for i, elei in enumerate(list(network.nodes()), 1):
for j, elej in enumerate(list(network.nodes()), 1):
if i == j:
continue
try:
s_elei_elej = 0.0
for u in network.neighbors(elei):
for v in network.neighbors(elej):
s_elei_elej += sim_old[u][v]
sim[elei][elej] = (C * s_elei_elej /
(len(network.neighbors(elei)) *
len(network.neighbors(elej))))
except:
continue
for i, elei in enumerate(list(network.nodes()), 1):
for j, elej in enumerate(list(network.nodes()), 1):
if i >= j:
continue
if not network.has_edge(elei, elej):
try:
score = sim[elei][elej]
except:
continue
total_score_without_edge += score
nodes_pair_without_edge.append((elei, elej, score))
for a, b, c in nodes_pair_without_edge:
probability_add.append(
c / total_score_without_edge
) # calculate the probabilities of edges to be added
# select edges to be added according to probabilities
edges_add = calculate_param.prob_select_distinct(nodes_pair_without_edge,
probability_add, num_add)
for a, b, c in edges_add:
network.add_edge(a, b) # add selected edges
return True