def find_synthetic_factors(fname):
fname = "datasets/SBM_processed/" + fname + ".txt"
max_nodes = 500
num_timestamps = 151
G_times = SBM_loader.load_temporarl_edgelist(fname)
T = toTensor(G_times)
dim = 30
print("CPD starts")
print(datetime.datetime.now())
factors = apply_parafac(T, dimension=dim)
normal_util.save_object(factors, "SBM_factors" + str(dim) + ".pkl")
print(datetime.datetime.now())
print("CPD ends")
#factors = normal_util.load_object("SBM_factors30.pkl")
real_events = [16, 31, 61, 76, 91, 106, 136]
'''
either can be an option here
'''
anomalies = LocalOutlierFactor_anomalies(factors, n_neighbors=20)
#anomalies = DBSCAN_anomalies(factors, eps=3, min_samples=2, min_size=10)
accuracy = compute_accuracy(anomalies, real_events)
print(anomalies)
print("prediction accuracy is " + str(accuracy))
def compute_UCI_SVD(num_eigen=6, top=True):
fname = "datasets/UCI_processed/OCnodeslinks_chars.txt"
max_nodes = 1901
directed = True
G_times = UCI_loader.load_temporarl_edgelist(fname, max_nodes=max_nodes)
(Temporal_eigenvalues, activity_vecs) = SVD_perSlice(G_times,
directed=directed,
num_eigen=num_eigen,
top=top,
max_size=max_nodes)
normal_util.save_object(Temporal_eigenvalues, "UCI_L_singular.pkl")
def compute_legis_SVD(num_eigen=6, top=True):
fname = "datasets/USLegis_processed/LegisEdgelist.txt"
directed = False
G_times = USLegis_loader.load_legis_temporarl_edgelist(fname)
max_nodes = 102
(Temporal_eigenvalues, activity_vecs) = SVD_perSlice(G_times,
directed=directed,
num_eigen=num_eigen,
top=top,
max_size=max_nodes)
normal_util.save_object(Temporal_eigenvalues, "USLegis_L_singular.pkl")
def find_factors_UCI():
fname = "datasets/UCI_processed/OCnodeslinks_chars.txt"
max_nodes = 1901
G_times = UCI_loader.load_temporarl_edgelist(fname, max_nodes=max_nodes)
T = toTensor(G_times, max_nodes)
dim = 3
print("CPD starts")
print(datetime.datetime.now())
factors = apply_parafac(T, dimension=dim)
print(datetime.datetime.now())
print("CPD ends")
tname = "UCI_factors.pkl"
normal_util.save_object(factors, tname)
def compute_adj_SVD(outEigenFile,
outVecFile,
fname="datasets/OCnodeslinks_chars.txt",
max_nodes=1901,
UCI=True):
if UCI:
G_times = UCI_loader.load_temporarl_edgelist(fname,
max_nodes=max_nodes)
else:
G_times = DBLP_loader.load_dblp_temporarl_edgelist(fname,
max_nodes=max_nodes)
(Temporal_eigenvalues,
activity_vecs) = adj_eigenvecs_perSlice(G_times, directed=UCI)
normal_util.save_object(Temporal_eigenvalues, outEigenFile)
normal_util.save_object(activity_vecs, outVecFile)
def find_canVote_factors():
fname = "datasets/canVote_processed/canVote_edgelist.txt"
G_times = canVote_loader.load_canVote_temporarl_edgelist(fname)
T = toTensor(G_times)
dim = 10
print("CPD starts")
print(datetime.datetime.now())
factors = apply_parafac(T, dimension=dim)
print(datetime.datetime.now())
print("CPD ends")
normal_util.save_object(factors, "canVote_factors" + str(dim) + ".pkl")
anomalies = LocalOutlierFactor_anomalies(factors, n_neighbors=7)
print(anomalies)
def compute_canVote_SVD(num_eigen=338, top=True):
fname = "datasets/canVote_processed/canVote_edgelist.txt"
directed = True
G_times = canVote_loader.load_canVote_temporarl_edgelist(fname)
max_len = 0
for G in G_times:
if (len(G) > max_len):
max_len = len(G)
print(max_len)
max_nodes = max_len
(Temporal_eigenvalues, activity_vecs) = SVD_perSlice(G_times,
directed=directed,
num_eigen=num_eigen,
top=top,
max_size=max_nodes)
normal_util.save_object(Temporal_eigenvalues, "canVote_L_singular.pkl")
def find_USLegis_factors():
fname = "datasets/USLegis_processed/LegisEdgelist.txt"
G_times = USLegis_loader.load_legis_temporarl_edgelist(fname)
T = toTensor(G_times)
dim = 10
print("CPD starts")
print(datetime.datetime.now())
factors = apply_parafac(T, dimension=dim)
print(datetime.datetime.now())
print("CPD ends")
normal_util.save_object(factors, "USLegis_factors" + str(dim) + ".pkl")
real_events = [3, 7]
anomalies = LocalOutlierFactor_anomalies(factors, n_neighbors=5)
accuracy = compute_accuracy(anomalies, real_events)
print(anomalies)
print("prediction accuracy is " + str(accuracy))
def compute_synthetic_SVD(fname, num_eigen=499, top=True):
edgefile = "datasets/SBM_processed/" + fname + ".txt"
'''
careful
'''
max_nodes = 1000
max_time = 151
directed = False
G_times = SBM_loader.load_temporarl_edgelist(edgefile)
(Temporal_eigenvalues, activity_vecs) = SVD_perSlice(G_times,
directed=directed,
num_eigen=num_eigen,
top=top,
max_size=max_nodes)
#print (Temporal_eigenvalues)
normal_util.save_object(Temporal_eigenvalues, fname + ".pkl")
def find_UCI_factors():
fname = "datasets/UCI_processed/OCnodeslinks_chars.txt"
max_nodes = 1901
num_timestamps = 196
G_times = UCI_loader.load_temporarl_edgelist(fname, max_nodes=max_nodes)
T = toTensor(G_times)
dim = 30
print("CPD starts")
print(datetime.datetime.now())
factors = apply_parafac(T, dimension=dim)
normal_util.save_object(factors, "UCI_factors" + str(dim) + ".pkl")
print(datetime.datetime.now())
print("CPD ends")
#factors = normal_util.load_object("UCI_factors1000.pkl")
real_events = [65, 158]
anomalies = DBSCAN_anomalies(factors, eps=3, min_samples=2, min_size=10)
#anomalies = LocalOutlierFactor_anomalies(factors, n_neighbors=20)
accuracy = compute_accuracy(anomalies, real_events)
print(anomalies)
print("prediction accuracy is " + str(accuracy))