def evaluate_unsupervised_embedding(di_graph,
graph_embedding,
is_undirected=True):
train_digraph, test_digraph = train_test_split.splitDiGraphToTrainTest2(
di_graph, train_ratio=0.8, is_undirected=True)
X, _ = graph_embedding.learn_embedding(graph=train_digraph,
no_python=False)
sample_edges = sample_edge_new(train_digraph, test_digraph, 0.5)
filtered_edge_list = getscore4(train_digraph, graph_embedding,
sample_edges)
AP, ROC = scores.computeAP_ROC(filtered_edge_list, test_digraph)
test_digraph1, node_l = graph_util.sample_graph(test_digraph, 1024)
X = X[node_l]
estimated_adj = graph_embedding.get_reconstructed_adj(X, node_l)
predicted_edge_list = evaluation_util.getEdgeListFromAdjMtx(
estimated_adj, is_undirected=True)
filtered_edge_list = [
e for e in predicted_edge_list
if not (train_digraph.has_edge(node_l[e[0]], node_l[e[1]]))
]
MAP = scores.computeMAP(filtered_edge_list, test_digraph1)
print(AP, ROC, MAP)
return AP, ROC, MAP
def evaluate_unsupervised_all(di_graph, is_undirected=True):
train_digraph, test_digraph = train_test_split.splitDiGraphToTrainTest2(
di_graph, train_ratio=0.8, is_undirected=True)
sample_edges = sample_edge_new(train_digraph, test_digraph)
test_digraph1, node_l = graph_util.sample_graph(test_digraph, 1024)
AP = []
ROC = []
MAP = []
heurestics = [cn, jc, pa, aa]
for x in heurestics:
estimated_adj = getscore1(train_digraph, node_l, x)
predicted_edge_list = evaluation_util.getEdgeListFromAdjMtx(
estimated_adj, is_undirected=True)
filtered_edge_list = [
e for e in predicted_edge_list
if not train_digraph.has_edge(node_l[e[0]], node_l[e[1]])
]
MAP1 = scores.computeMAP(filtered_edge_list, test_digraph1)
MAP.append(MAP1)
filtered_edge_list = getscore3(train_digraph, sample_edges, x)
AP1, ROC1 = scores.computeAP_ROC(filtered_edge_list, test_digraph)
AP.append(AP1)
ROC.append(ROC1)
print(AP1, ROC1, MAP1)
return AP, ROC, MAP
def evaluate_supervised(di_graph, graph_embedding, is_undirected=True):
train_digraph, test_digraph = train_test_split.splitDiGraphToTrainTest2(
di_graph, train_ratio=0.6, is_undirected=True)
train_digraph1, test_digraph = evaluation_util.splitDiGraphToTrainTest(
test_digraph, train_ratio=0.5, is_undirected=is_undirected)
X, _ = graph_embedding.learn_embedding(graph=train_digraph,
no_python=False)
trp, trn = create_edge_dataset(train_digraph, train_digraph1)
trd, trl = create_vector_dataset(trp, trn, hadamard2, X)
mean = np.mean(trd, axis=0)
std = np.std(trd, axis=0)
trd = (trd - mean) / std
clasifier = train_classifier(trd, trl)
for (st, ed) in train_digraph1.edges():
train_digraph.add_edge(st, ed)
sample_edges = sample_edge_new(train_digraph, test_digraph, 0.5)
X, _ = graph_embedding.learn_embedding(graph=train_digraph,
no_python=False)
filtered_edge_list = getscore5(train_digraph, sample_edges, clasifier,
hadamard2, X, mean, std)
AP, ROC = scores.computeAP_ROC(filtered_edge_list, test_digraph)
test_digraph, node_l = graph_util.sample_graph(test_digraph, 1024)
X = X[node_l]
estimated_adj = getscore2(train_digraph, node_l, clasifier, hadamard2, X,
mean, std)
predicted_edge_list = evaluation_util.getEdgeListFromAdjMtx(
estimated_adj, is_undirected=True)
filtered_edge_list = [
e for e in predicted_edge_list
if not train_digraph.has_edge(node_l[e[0]], node_l[e[1]])
]
MAP = scores.computeMAP(filtered_edge_list, test_digraph)
print(MAP)
return AP, ROC, MAP
def evaluate_unsupervised_all(di_graph, is_undirected=True):
train_digraph, test_digraph = train_test_split.splitDiGraphToTrainTest2(
di_graph, train_ratio=0.8, is_undirected=True)
# train_digraph, test_digraph = train_test_split.splitDiGraphToTrainTest2(di_graph, train_ratio = 0.75, is_undirected=True)
# train_digraph1, test_digraph = evaluation_util.splitDiGraphToTrainTest(
# test_digraph,
# train_ratio=0.2,
# is_undirected=is_undirected
# )
# train_digraph_temp=train_digraph.copy()
# for (st,ed) in train_digraph1.edges():
# train_digraph_temp.add_edge(st,ed)
# sample_edges = sample_edge_new(train_digraph_temp,test_digraph, -1)
sample_edges = sample_edge_new(train_digraph, test_digraph, -1)
filtered_edge_list = getscore3(train_digraph, sample_edges, aa)
AP1, ROC1 = scores.computeAP_ROC(filtered_edge_list, test_digraph)
print(AP1, ROC1)
return AP1, ROC1
print ("saving for supervised")
for grp in xrange(len(list_graphs)):
for x in xrange(num_samples):
# load the graph as a networkx graph
G = graph_util.loadGraphFromEdgeListTxt(list_graphs[grp], directed=list_directed[grp])
G = G.to_directed()
if not os.path.exists('SAVER_SUP/'+fig_name[grp]+str(x+1)):
os.makedirs('SAVER_SUP/'+fig_name[grp]+str(x+1))
# split the graph into 60-20-20 ratio, 60% for calculating the edge features, 20% for training the classifier, 20% for evaluating the model.
train_digraph, test_digraph = train_test_split.splitDiGraphToTrainTest2(G, train_ratio = 0.6, is_undirected=True)
train_digraph1, test_digraph = evaluation_util.splitDiGraphToTrainTest(test_digraph, train_ratio=0.5, is_undirected=True)
# embeddings without relearning
print ("saving for LE")
for dim in dimensions:
embedding=LaplacianEigenmaps(d=dim)
X, _ = embedding.learn_embedding(graph=train_digraph, no_python=False)
file_name='SAVER_SUP/'+fig_name[grp]+str(x+1)+'/LE1_'+str(dim)
parameter_file=open(file_name, 'wb')
pickle.dump(X,parameter_file)
parameter_file.close()
print ("saving for DEEPWALK")
for dim in dimensions:
def evaluate_supervised_new(train_digraph,
embeddings,
hads,
is_undirected=True):
train_digraph, test_digraph = train_test_split.splitDiGraphToTrainTest2(
train_digraph, train_ratio=0.6, is_undirected=True)
for (st, ed) in train_digraph.edges():
if (test_digraph.has_edge(st, ed)):
test_digraph.remove_edge(st, ed)
train_digraph1, test_digraph = evaluation_util.splitDiGraphToTrainTest(
test_digraph, train_ratio=0.5, is_undirected=is_undirected)
l_emb = []
combine = []
for emb in embeddings:
X, _ = emb.learn_embedding(graph=train_digraph, no_python=False)
l_emb.append(X)
for had in hads:
if (had == 1):
combine.append(hadamard1)
elif (had == 0):
combine.append(hadamard2)
# combine.append(dotp1)
print("embeddings learned")
trp, trn = create_edge_dataset(train_digraph, train_digraph1)
trd, trl = create_mix_dataset(trp, trn, train_digraph, l_emb, combine)
mean = np.mean(trd, axis=0)
std = np.std(trd, axis=0)
trd = (trd - mean) / std
clasifier = train_classifier(trd, trl)
# print (clasifier.coef_)
# print (clasifier.intercept_)
train_digraph_temp = train_digraph.copy()
for (st, ed) in train_digraph1.edges():
train_digraph_temp.add_edge(st, ed)
sample_edges = sample_edge_new(train_digraph_temp,
test_digraph,
-1,
num_edges=500000)
# co=0
# for (st,ed) in sample_edges:
# for (st1,ed1) in trn:
# if(st==st1 and ed==ed1):
# if(test_digraph.has_edge(st,ed)):
# print ("1")
# for (st1,ed1) in trp:
# if(st==st1 and ed==ed1):
# if(test_digraph.has_edge(st,ed)):
# print ("2")
# else:
# print ("3")
# l_emb1 = []
# for emb in embeddings:
# X, _ = emb.learn_embedding(graph=train_digraph_temp, no_python=False)
# l_emb1.append(X)
# break
# l_emb1.append(l_emb[1])
print("embeddings learned")
# filtered_edge_list = getscore9(train_digraph, sample_edges, clasifier, l_emb1, combine, mean, std)
# AP, ROC = scores.computeAP_ROC(filtered_edge_list, test_digraph)
# print (AP,ROC)
filtered_edge_list = getscore9(train_digraph_temp, sample_edges, clasifier,
l_emb, combine, mean, std)
AP, ROC = scores.computeAP_ROC(filtered_edge_list, test_digraph)
print(AP, ROC)
trd, trl = create_score_dataset(trp, trn, allh, train_digraph)
mean = np.mean(trd, axis=0)
std = np.std(trd, axis=0)
trd = (trd - mean) / std
clasifier = train_classifier(trd, trl)
filtered_edge_list = getscore7(train_digraph_temp, sample_edges, clasifier,
allh, mean, std)
AP2, ROC2 = scores.computeAP_ROC(filtered_edge_list, test_digraph)
print(AP2, ROC2)
# G11 = train_digraph.to_undirected()
# f1=[]
# f2=[]
# for (st,ed,w) in filtered_edge_list:
# f1.append(w)
# f2.append(cn(G11,st,ed))
# f1=np.array(f1)
# f2=np.array(f2)
# ind1 = np.argsort(-1*f1)
# ind2 = np.argsort(-1*f2)
# print (ind1[:1000])
# print (ind2[:1000])
# print (f1[ind1[:1000]])
# print (f2[ind1[:1000]])
# filtered_edge_list = getscore3(train_digraph_temp, sample_edges, aa)
# AP, ROC = scores.computeAP_ROC(filtered_edge_list, test_digraph)
# print (AP,ROC)
return AP, ROC
# labels=[]
# score=[]
# dist=[]
# G=train_digraph.to_undirected()
# print (len(filtered_edge_list))
# for (st,ed,w) in filtered_edge_list:
# # if not(nx.shortest_path_length(G,source=st,target=ed)==2):
# # continue
# if(test_digraph.has_edge(st,ed)):
# labels.append(1)
# else:
# labels.append(0)
# score.append(w)
# ap = average_precision_score(labels, score)
# print (ap)
# ind = np.argsort(-1*np.asarray(score))
# labels = np.array(labels)
# print (labels[ind[:1000]])
# labels=[]
# score=[]
# dist=[]
# G=train_digraph.to_undirected()
# for (st,ed,w) in filtered_edge_list:
# if (nx.shortest_path_length(G,source=st,target=ed)==2):
# continue
# if(test_digraph.has_edge(st,ed)):
# labels.append(1)
# else:
# labels.append(0)
# score.append(w)
# ap = average_precision_score(labels, score)
# print (ap)
# ind = np.argsort(-1*np.asarray(score))
# labels = np.array(labels)
# print (labels[ind[:1000]])
# test_digraph, node_l = graph_util.sample_graph(test_digraph, 1024)
# estimated_adj = getscore8(train_digraph, node_l, clasifier, l_emb1, combine)
# predicted_edge_list = evaluation_util.getEdgeListFromAdjMtx(estimated_adj,is_undirected=True)
# filtered_edge_list = [e for e in predicted_edge_list if not train_digraph.has_edge(node_l[e[0]], node_l[e[1]])]
# MAP = scores.computeMAP(filtered_edge_list, test_digraph)
# print (MAP)
MAP = 0
return AP, ROC, MAP