def test_file_full(file):
split_dataset(file + "_data.csv", file + "_labels.csv",
file + "_train.csv", file + "_test.csv", None)
train_data = LogFile(file + "_train.csv", ",", 0, 1000000, None, "case_id",
"name")
train_data.remove_attributes(["label"])
model = edbn.train(train_data)
test_data = LogFile(file + "_test.csv",
",",
0,
1000000,
None,
"case_id",
"name",
values=train_data.values)
edbn.test(test_data, file + "_output_full.csv", model, "label", "0",
train_data)
plot.plot_single_roc_curve(file + "_output_full.csv",
file,
save_file="../Data/Nolle_Graphs/" +
file.split("/")[-1] + "_roc.png")
plot.plot_single_prec_recall_curve(file + "_output_full.csv",
file,
save_file="../Data/Nolle_Graphs/" +
file.split("/")[-1] + "_precrec.png")
def duration_test():
path = "../Data/Experiments_Duration/"
train_rates = [0, 5, 10, 25]
test_rates = [1, 5, 10, 25, 50, 100, 250, 500]
anoms_rates = []
for train_rate in train_rates:
for test_rate in test_rates:
anoms_rates.append((train_rate, test_rate))
for i in range(len(anoms_rates)):
print(anoms_rates[i])
scores = []
for run in range(RUNS):
print("Run %i" % run)
train_file = path + "%i_train_%i.csv" % (i, anoms_rates[i][0])
test_file = path + "%i_test_%i.csv" % (i, anoms_rates[i][1])
duration_generator.generate(10000, 10000, anoms_rates[i][0],
anoms_rates[i][1], train_file,
test_file)
train_data = LogFile(train_file, ",", 0, 1000000, "date", "trace")
train_data.remove_attributes(["Anomaly"])
test_data = LogFile(test_file,
",",
0,
1000000,
"date",
"trace",
values=train_data.values)
train_data.keep_attributes(
["event", "date", "trace", "process", "resource", "random"])
train_data.create_k_context()
train_data.add_duration_to_k_context()
bins = train_data.discretize("duration_0")
test_data.create_k_context()
test_data.add_duration_to_k_context()
test_data.discretize("duration_0", bins)
model = edbn.train(train_data)
edbn.test(test_data, path + "Output_%i_%i.csv" % anoms_rates[i],
model, "anomaly", "0")
output_file = path + "Output_%i_%i.csv" % anoms_rates[i]
output_roc = path + "roc_%i_%i.png" % anoms_rates[i]
output_prec = path + "prec_recall_%i_%i.png" % anoms_rates[i]
score = plt.get_roc_auc(output_file)
scores.append(plt.get_roc_auc(output_file))
print("Score = %f" % score)
with open(path + "results.txt", "a") as fout:
fout.write("Testing:\ntrain rate: %i\ntest rate: %i\n" %
(anoms_rates[i][0], anoms_rates[i][1]))
fout.write("Result: " + str(scores) + "\n")
fout.write("Mean: %f Median: %f\n" %
(np.mean(scores), np.median(scores)))
fout.write("Variance: %f\n\n" % np.var(scores))
def compare_bpics(path):
for i in range(1, 6):
# Input Files
train = path + "BPIC15_train_%i.csv" % (i)
test = path + "BPIC15_test_%i.csv" % (i)
output = path + "Output/BPIC15_output_%i.csv" % (i)
output_edbn = path + "Output/BPIC15_edbn_output_%i.csv" % (i)
prec_recall = path + "Output/prec_recall_%i.png" % (i)
roc = path + "Output/roc_%i.png" % (i)
train_data = LogFile(train,
",",
0,
500000,
"Time",
"Case",
activity_attr="Activity",
convert=False)
train_data.remove_attributes(["Anomaly", "Type", "Time"])
test_data = LogFile(test,
",",
0,
500000,
"Time",
"Case",
activity_attr="Activity",
values=train_data.values,
convert=False)
bohmer_model = bmr.train(train_data)
bmr.test(test_data,
output,
bohmer_model,
label="Anomaly",
normal_val="0")
train_data.convert2int()
test_data.convert2int()
edbn_model = edbn.train(train_data)
edbn.test(test_data,
output_edbn,
edbn_model,
label="Anomaly",
normal_val="0")
plt.plot_compare_prec_recall_curve([output, output_edbn],
["Likelihood Graph", "EDBN"],
save_file=prec_recall)
plt.plot_compare_roc_curve([output, output_edbn],
["Likelihood Graph", "EDBN"], roc)
def categorical_test():
path = "../Data/Experiments/"
train_rates = [0, 5, 10, 25]
test_rates = [1, 5, 10, 25, 50, 100, 250, 500]
anoms_rates = []
for train_rate in train_rates:
for test_rate in test_rates:
anoms_rates.append((train_rate, test_rate))
for i in range(len(anoms_rates)):
print(anoms_rates[i])
scores = []
for run in range(RUNS):
print("Run %i" % run)
train_file = path + "%i_train_%i.csv" % (i, anoms_rates[i][0])
test_file = path + "%i_test_%i.csv" % (i, anoms_rates[i][1])
generator.create_shipment_data(10000, 10000, anoms_rates[i][0],
anoms_rates[i][1], train_file,
test_file)
train_data = LogFile(train_file, ",", 0, 1000000, None, "Case")
train_data.remove_attributes(["Anomaly"])
test_data = LogFile(test_file,
",",
0,
1000000,
None,
"Case",
values=train_data.values)
model = edbn.train(train_data)
edbn.test(test_data, path + "Output_%i_%i.csv" % anoms_rates[i],
model, "Anomaly", "0")
output_file = path + "Output_%i_%i.csv" % anoms_rates[i]
output_roc = path + "roc_%i_%i.png" % anoms_rates[i]
output_prec = path + "prec_recall_%i_%i.png" % anoms_rates[i]
score = plt.get_roc_auc(output_file)
scores.append(plt.get_roc_auc(output_file))
print("Score = %f" % score)
with open(path + "results.txt", "a") as fout:
fout.write("Testing:\ntrain rate: %i\ntest rate: %i\n" %
(anoms_rates[i][0], anoms_rates[i][1]))
fout.write("Result: " + str(scores) + "\n")
fout.write("Mean: %f Median: %f\n" %
(np.mean(scores), np.median(scores)))
fout.write("Variance: %f\n\n" % np.var(scores))