],
rho=0.3,
n_iter=30,
xeta=0.005,
n_batch=50,
modelfile=[
'./intermediate/enc_model.json',
'./intermediate/dec_model.json'
],
weightfile=[
'./intermediate/enc_weights.hdf5',
'./intermediate/dec_weights.hdf5'
],
)
dynamic_embedding.learn_embeddings([g[0] for g in dynamic_sbm_series])
plot_dynamic_sbm_embedding.plot_dynamic_sbm_embedding(
dynamic_embedding.get_embeddings(), dynamic_sbm_series)
plt.savefig('result/visualization_DynRNN_rp.png')
plt.show()
elif args.testDataType == 'sbm_cd':
node_num = 1000
community_num = 2
node_change_num = args.nodemigration
dynamic_sbm_series = dynamic_SBM_graph.get_community_diminish_series_v2(
node_num, community_num, length, 1, node_change_num)
dynamic_embedding = DynAERNN(d=dim_emb,
beta=5,
n_prev_graphs=lookback,
nu1=1e-6,
nu2=1e-6,
n_aeunits=[500, 300],
n_lstmunits=[500, dim_emb],
from __future__ import print_function
disp_avlbl = True
import os
if os.name == 'posix' and 'DISPLAY' not in os.environ:
disp_avlbl = False
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
from dynamicgem.embedding.graphFac_dynamic import GraphFactorization
from dynamicgem.visualization import plot_dynamic_sbm_embedding
from dynamicgem.graph_generation import dynamic_SBM_graph
if __name__ == '__main__':
node_num = 100
community_num = 2
node_change_num = 2
length = 5
dynamic_sbm_series = dynamic_SBM_graph.get_community_diminish_series_v2(
node_num, community_num, length, 1, node_change_num)
dynamic_embeddings = GraphFactorization(16, 10, 10, 5 * 10**-2, 1.0, 1.0)
# pdb.set_trace()
dynamic_embeddings.learn_embeddings([g[0] for g in dynamic_sbm_series])
plot_dynamic_sbm_embedding.plot_dynamic_sbm_embedding(
dynamic_embeddings.get_embeddings(), list(dynamic_sbm_series))
plt.show()
