def get_embeddings(self, inst, th=1):
G = nx.parse_edgelist(self._compose_edge_list(inst.dist_mat, th), create_using=nx.DiGraph(), nodetype=None,
data=[('weight', float)])
if self._embedding == 'deepwalk':
model = DeepWalk(G, walk_length=10, num_walks=80, workers=1)
model.train(window_size=5, iter=3)
elif self._embedding == 'node2vec':
model = Node2Vec(G, walk_length=10, num_walks=80, p=0.25, q=4, workers=1) # init model
model.train(window_size=5, iter=3) # train model
elif self._embedding == 'line':
model = LINE(G, embedding_size=128, order='second') # init model,order can be ['first','second','all']
model.train(batch_size=1024, epochs=50, verbose=2) # train model
elif self._embedding == 'sdne':
model = SDNE(G, hidden_size=[256, 128]) # init model
model.train(batch_size=3000, epochs=40, verbose=2) # train model
elif self._embedding == 'struc2vec':
model = Struc2Vec(G, 10, 80, workers=4, verbose=40, ) # init model
model.train(window_size=5, iter=3) # train model
else:
return self._normalise(inst)
ebds = model.get_embeddings()
coords = []
for i in range(inst.n):
coords.append(ebds[str(i)])
return np.array(coords)
model = TSNE(n_components=2)
node_pos = model.fit_transform(emb_list)
color_idx = {}
for i in range(len(X)):
color_idx.setdefault(Y[i][0], [])
color_idx[Y[i][0]].append(i)
for c, idx in color_idx.items():
plt.scatter(node_pos[idx, 0], node_pos[idx, 1],
label=c) # c=node_colors)
plt.legend()
plt.show()
if __name__ == "__main__":
# G = nx.read_edgelist('../data/wiki/Wiki_edgelist.txt',
# create_using=nx.DiGraph(), nodetype=None, data=[('weight', int)])
G = nx.read_edgelist(
'../data/ETH/Phishing node classification/TransEdgelist.txt',
create_using=nx.MultiDiGraph(),
delimiter=',',
nodetype=None,
data=[('amount', float), ('weight', int)])
model = SDNE(G, hidden_size=[256, 128])
model.train(batch_size=3000, epochs=40, verbose=2)
embeddings = model.get_embeddings()
evaluate_embeddings(embeddings)
plot_embeddings(embeddings)
#
# model = SDNE(G, hidden_size=[256, 64],)
# model.train(batch_size=3000, epochs=40, verbose=2)
# embeddings = model.get_embeddings()
# print(embeddings)
# evaluate_embeddings(embeddings)
# plot_embeddings(embeddings)
import pandas as pd
df = pd.DataFrame()
df['source'] = [str(i) for i in [0, 1, 2, 3, 4, 4, 6, 7, 7, 9]]
df['target'] = [str(i) for i in [1, 4, 4, 4, 6, 7, 5, 8, 9, 8]]
G = nx.from_pandas_edgelist(df, create_using=nx.Graph())
model = SDNE(
G,
hidden_size=[4, 2],
)
# model.train(batch_size=3000, epochs=40, verbose=2)
embeddings = model.get_embeddings()
# print(embeddings)
x, y = [], []
print(sorted(embeddings.items(), key=lambda x: x[0]))
for k, i in embeddings.items():
x.append(i[0])
y.append(i[1])
plt.scatter(x, y)
plt.show()
G = nx.read_edgelist("data/" + d_set[i] + "/" + d_set[i] +
".edges",
create_using=nx.DiGraph(),
nodetype=None,
data=[('weight', int)])
if (mdl[j] == "Node2Vec"):
model = Node2Vec(G,
walk_length=10,
num_walks=80,
p=0.25,
q=4,
workers=1)
model.train(window_size=5, iter=3)
elif (mdl[j] == "SDNE"):
model = SDNE(
G,
hidden_size=[256, 128],
)
model.train(batch_size=3000, epochs=40, verbose=2)
elif (mdl[j] == "Struc2Vec"):
model = Struc2Vec(
G,
10,
80,
workers=4,
verbose=40,
)
model.train(window_size=5, iter=3)
elif (mdl[j] == "DeepWalk"):
model = DeepWalk(G, walk_length=10, num_walks=80, workers=1)
model.train(window_size=5, iter=3)
elif (mdl[j] == "LINE"):