def plot_UCI():
'''
plot statistics from UCI Message
'''
fname = "datasets/UCI_processed/OCnodeslinks_chars.txt"
max_nodes = 1901
G_times = UCI_loader.load_temporarl_edgelist(fname, max_nodes=max_nodes)
graph_name = "UCI_Message"
'''
dictionary of weak labels
'''
labels_dict = {}
print ("edge")
labels_dict['edge'] = normal_util.plot_edges(G_times, graph_name)
print ("acc")
labels_dict['acc'] = normal_util.plot_avg_clustering(G_times, graph_name)
print ("component")
labels_dict['component'] = normal_util.plot_num_components_directed(G_times, graph_name)
print ("weights")
labels_dict['weights'] = normal_util.plot_weighted_edges(G_times, graph_name)
print ("degree")
labels_dict['degree'] = normal_util.plot_degree_changes(G_times, graph_name)
return labels_dict
def UCI_Message():
timestamps = 196
percent_ranked = 0.05
eigen_file = "UCI_L_singular.pkl"
fname = "UCI"
difference = True
G_times = UCI_loader.load_temporarl_edgelist(
"datasets/UCI_processed/OCnodeslinks_chars.txt", max_nodes=1901)
#real_events = [65,158]
window1 = 7
window2 = 14
initial_window = 14
(z_shorts, z_longs, z_scores,
events) = detection_with_bothwindows(eigen_file=eigen_file,
timestamps=timestamps,
percent_ranked=percent_ranked,
window1=window1,
window2=window2,
initial_window=initial_window,
difference=difference)
scores = []
scores.append(z_shorts)
scores.append(z_longs)
score_labels = ["short term " + str(window1), "long term " + str(window2)]
plot_anomaly_score("UCI", fname, scores, score_labels, events)
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 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 plot_UCI_allinOne():
fname = "datasets/UCI_processed/OCnodeslinks_chars.txt"
max_nodes = 1901
G_times = UCI_loader.load_temporarl_edgelist(fname, max_nodes=max_nodes)
LAD = [69, 70, 184, 185, 187, 188, 189, 191, 192, 194]
activity = [57, 75, 78, 85, 89, 90, 104, 176, 188, 192]
CPD = [13, 16, 17, 20, 22, 23, 24, 31, 38, 40, 124]
label_sets = []
label_sets.append(LAD)
label_sets.append(activity)
label_sets.append(CPD)
graph_name = "UCI_Message"
normal_util.all_in_one_compare(G_times, graph_name, label_sets, True)
graph_name = "UCI_Message"
normal_util.all_plots_in_one(G_times, graph_name)
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))