def execute_walks_graph_embedding(graph: nx.Graph,
length: int,
iterations: int,
p: float = 1.0,
q: float = 1.0,
**kwargs: Dict) -> np.ndarray:
"""Execute first/second order walks using GraphEmbedding walker.
Parameters
--------------------------
graph: nx.Graph,
The graph on which to run the walks.
length: int,
Lenght of the walks.
iterations: int,
Number of walks to start from each node.
p: float = 1.0,
Inverse weight for making the walk local.
By default, the walk will be uniform.
q: float = 1.0,
Inverse weight for making the walk a deep first.
By default, the walk will be uniform.
kwargs: Dict,
Additional parameters to be used in other libraries but not this one.
Returns
--------------------------
Computed walks as numpy array.
"""
return Node2Vec(graph,
walk_length=length,
num_walks=iterations,
workers=cpu_count(),
p=p,
q=q).sentences
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)
emb_list = []
for k in X:
emb_list.append(embeddings[k])
emb_list = np.array(emb_list)
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)
# 分辨率参数-dpi，画布大小参数-figsize
plt.figure(dpi=300, figsize=(24, 12))
for c, idx in color_idx.items():
plt.scatter(node_pos[idx, 0], node_pos[idx, 1], label=c)
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)])
model = Node2Vec(G, walk_length=10, num_walks=80,
p=0.25, q=4, workers=1, use_rejection_sampling=0)
model.train(window_size = 5, iter = 3)
embeddings=model.get_embeddings()
# evaluate_embeddings(embeddings)
plot_embeddings(embeddings)
parser = argparse.ArgumentParser()
parser.add_argument('--dataset',
type=str,
default="cora",
help='dataset for training')
parser.add_argument('--tr_frac', type=float, default=0.2, help='tr_frac')
args = parser.parse_args()
# load_data
adj, features, y_train, y_val, y_test, train_mask, val_mask, test_mask, labels = load_data(
args.dataset)
idx = np.argmax(labels, axis=1)
f = open('labels.txt', 'w')
for i in range(labels.shape[0]):
f.write(f'{i} {idx[i]} \n')
adj = adj.toarray()
G = nx.from_numpy_array(adj, create_using=nx.DiGraph())
nx.write_edgelist(G, "test.edgelist", data=[('weight', int)])
G = nx.read_edgelist('test.edgelist',
create_using=nx.DiGraph(),
nodetype=None,
data=[('weight', int)])
model = Node2Vec(G, walk_length=10, num_walks=80, p=0.25, q=4, workers=1)
model.train(window_size=5, iter=3)
embeddings = model.get_embeddings()
evaluate_embeddings(embeddings, args.tr_frac)
plot_embeddings(embeddings)
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/flight/brazil-airports.edgelist',
create_using=nx.DiGraph(),
nodetype=None,
data=[('weight', int)])
model = Node2Vec(G, 10, 80, workers=1, p=0.25, q=2)
model.train()
embeddings = model.get_embeddings()
evaluate_embeddings(embeddings)
plot_embeddings(embeddings)
# p=0.25, q=2, workers=1, use_rejection_sampling=0)
# model.train(window_size=5, iter=3)
#
# embeddings = model.get_embeddings()
# dic = evaluate_embeddings(embeddings)
# sum_mic+=dic['micro']
# sum_mac+=dic['macro']
# sum_acc+=dic['acc']
#
# print('ave_micro:')
# print(sum_mic/iter)
# print('ave_macro:')
# print(sum_mac/iter)
# print('ave_acc:')
# print(sum_acc/iter)
# model = DeepWalk(G, embed_size=128,walk_length=10, num_walks=80, workers=1)
# model.train(window_size=5, iter=3)
# model = LINE(G, embedding_size=128, order='second')
# model = LINE(G, embedding_size=128, order='first')
# model = LINE(G, embedding_size=128, order='all')
# model.train(batch_size=1024, epochs=50, verbose=2)
#
model = Node2Vec(G, embed_size=128,walk_length=10, num_walks=80,
p=0.25, q=2, workers=1, use_rejection_sampling=0)
model.train(window_size=5, iter=3)
embeddings = model.get_embeddings()
plot_embeddings(embeddings)
# plot_embeddings_3D(embeddings)
emb_list = []
for k in X:
emb_list.append(embeddings[k])
emb_list = np.array(emb_list)
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))
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)])
model=Node2Vec(G, walk_length = 10, num_walks = 80,
p = 0.25, q = 4, workers = 1)
model.train(window_size = 5, iter = 3)
embeddings=model.get_embeddings()
evaluate_embeddings(embeddings)
plot_embeddings(embeddings)
# embeddings = model.get_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 = Node2Vec(G,
10,
80,
workers=1,
p=0.25,
q=2,
use_rejection_sampling=0)
model.train(embed_size=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()