def test_ae_static():
# Parameters for Stochastic block model graph
# Todal of 1000 nodes
node_num = 100
# Test with two communities
community_num = 2
# At each iteration migrate 10 nodes from one community to the another
node_change_num = 2
# Length of total time steps the graph will dynamically change
length = 7
# output directory for result
outdir = './output'
intr = './intermediate'
if not os.path.exists(outdir):
os.mkdir(outdir)
if not os.path.exists(intr):
os.mkdir(intr)
testDataType = 'sbm_cd'
# Generate the dynamic graph
dynamic_sbm_series = list(sbm.get_community_diminish_series_v2(node_num,
community_num,
length,
1, # comminity ID to perturb
node_change_num))
graphs = [g[0] for g in dynamic_sbm_series]
# parameters for the dynamic embedding
# dimension of the embedding
dim_emb = 8
lookback = 2
# AE Static
embedding = AE(d=dim_emb,
beta=5,
nu1=1e-6,
nu2=1e-6,
K=3,
n_units=[500, 300],
n_iter=2,
xeta=1e-4,
n_batch=100,
modelfile=['./intermediate/enc_modelsbm.json',
'./intermediate/dec_modelsbm.json'],
weightfile=['./intermediate/enc_weightssbm.hdf5',
'./intermediate/dec_weightssbm.hdf5'])
embs = []
t1 = time()
# ae static
for temp_var in range(length):
emb, _ = embedding.learn_embeddings(graphs[temp_var])
embs.append(emb)
print(embedding._method_name + ':\n\tTraining time: %f' % (time() - t1))
viz.plot_static_sbm_embedding(embs[-4:], dynamic_sbm_series[-4:])
def plotresults(self, dynamic_sbm_series):
plt.figure()
plt.clf()
viz.plot_static_sbm_embedding(self._X[-4:], dynamic_sbm_series[-4:])
resultdir = self._resultdir + '/' + self._datatype
if not os.path.exists(resultdir):
os.mkdir(resultdir)
resultdir = resultdir + '/' + self._method
if not os.path.exists(resultdir):
os.mkdir(resultdir)
# plt.savefig('./'+resultdir+'/V_'+self._method+'_nm'+str(self._nodemigration)+'_l'+str(self._length)+'_theta'+str(theta)+'_emb'+str(self._K*2)+'.pdf',bbox_inches='tight',dpi=600)
plt.show()
n_iter = 200,
xeta = 1e-4,
n_batch = 100,
modelfile = ['./intermediate/enc_modelsbm.json',
'./intermediate/dec_modelsbm.json'],
weightfile = ['./intermediate/enc_weightssbm.hdf5',
'./intermediate/dec_weightssbm.hdf5'])
embs = []
t1 = time()
#ae static
for temp_var in range(length):
emb, _= embedding.learn_embeddings(graphs[temp_var])
embs.append(emb)
print (embedding._method_name+':\n\tTraining time: %f' % (time() - t1))
viz.plot_static_sbm_embedding(embs[-4:], dynamic_sbm_series[-4:])
#TIMERS
datafile = dataprep_util.prep_input_TIMERS(graphs, length, testDataType)
embedding = TIMERS(K = dim_emb,
Theta = 0.5,
datafile = datafile,
length = length,
nodemigration = node_change_num,
resultdir = outdir,
datatype = testDataType)
if not os.path.exists(outdir):
os.mkdir(outdir)
outdir_tmp=outdir+'/sbm_cd'
if not os.path.exists(outdir_tmp):
os.mkdir(outdir_tmp)
def plotresults(self, dynamic_sbm_series):
# plt.close()
plt.figure()
plt.clf()
viz.plot_static_sbm_embedding(self._X[-4:], dynamic_sbm_series[-4:])
parser.add_argument('-t', '--testDataType', default='sbm_cd', type=str,help='Type of data to test the code')
args = parser.parse_args()
if args.testDataType == 'sbm_rp':
node_num = 10000
community_num = 500
node_change_num = 100
length = 2
dynamic_sbm_series = dynamic_SBM_graph.get_random_perturbation_series(node_num, community_num, length, node_change_num)
dynamic_embedding = SDNE(d=100, beta=5, alpha=1e-5, nu1=1e-6, nu2=1e-6, K=3, n_units=[500, 300,], rho=0.3, n_iter=30, n_iter_subs=5, xeta=0.01, n_batch=500, modelfile=['./intermediate/enc_model.json', './intermediate/dec_model.json'], weightfile=['./intermediate/enc_weights.hdf5', './intermediate/dec_weights.hdf5'], node_frac=1, n_walks_per_node=10, len_rw=2)
dynamic_embedding.learn_embeddings([g[0] for g in dynamic_sbm_series], False, subsample=False)
plot_dynamic_sbm_embedding.plot_dynamic_sbm_embedding(dynamic_embedding.get_embeddings(), dynamic_sbm_series)
plt.savefig('result/visualization_sdne_rp.png')
plt.show()
elif args.testDataType == 'sbm_cd':
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_embedding = SDNE(d=16, beta=5, alpha=1e-5, nu1=1e-6, nu2=1e-6, K=3, n_units=[500, 300,], rho=0.3, n_iter=2, n_iter_subs=5, xeta=0.01, n_batch=50, modelfile=['./intermediate/enc_model.json', './intermediate/dec_model.json'], weightfile=['./intermediate/enc_weights.hdf5', './intermediate/dec_weights.hdf5'], node_frac=1, n_walks_per_node=10, len_rw=2)
embs= []
graphs = [g[0] for g in dynamic_sbm_series]
for temp_var in range(length):
emb= dynamic_embedding.learn_embedding(graphs[temp_var])
embs.append(emb)
viz.plot_static_sbm_embedding(embs[-4:], list(dynamic_sbm_series)[-4:])
else:
dynamic_graph_series = graph_util.loadRealGraphSeries('data/real/hep-th/month_', 1, 5)
dynamic_embedding = SDNE(d=100, beta=2, alpha=1e-6, nu1=1e-5, nu2=1e-5, K=3, n_units=[400, 250,], rho=0.3, n_iter=100, n_iter_subs=30, xeta=0.001, n_batch=500, modelfile=['./intermediate/enc_model.json', './intermediate/dec_model.json'], weightfile=['./intermediate/enc_weights.hdf5', './intermediate/dec_weights.hdf5'])
dynamic_embedding.learn_embeddings(dynamic_graph_series, False)
def plotresults(self, dynamic_sbm_series):
"""Function to plot the result"""
plt.figure()
plt.clf()
viz.plot_static_sbm_embedding(self._X[-4:], dynamic_sbm_series[-4:])