def compare_bpic_total(path):
train = path + "BPIC15_train_total.csv"
test = path + "BPIC15_test_total.csv"
output = path + "Output/BPIC_15_output_total.csv"
output_edbn = path + "Output/BPIC15_edbn_output_total.csv"
prec_recall = path + "Output/prec_recall_total.png"
roc = path + "Output/roc_total.png"
if not os.path.exists(path + "Output"):
os.mkdir(path + "Output")
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 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 compare(files, nolle_result, nolle_labels):
i = 0
for file in files:
results = []
results.append(file + "_output_sample.csv")
results.append(file + "_output_full.csv")
results.append(file + "_output_bohmer.csv")
plot.plot_compare_prec_recall_curve(
results, ["Sample", "Full", "Bohmer"] + nolle_labels,
nolle_result,
"Comparison",
save_file="../Data/Nolle_Graphs/" + file.split("/")[-1] +
"_compare_precrec.png")
plot.plot_compare_roc_curve(results, ["Sample", "Full", "Bohmer"],
"Comparison",
save_file="../Data/Nolle_Graphs/" +
file.split("/")[-1] + "_compare_roc.png")
i += 1
def compare_bpic_total(path):
train = path + "BPIC15_train_total.csv"
test = path + "BPIC15_test_total.csv"
output = path + "Output/BPIC_15_output_total.csv"
output_edbn = path + "Output/BPIC15_edbn_output_total.csv"
prec_recall = path + "Output/prec_recall_total.png"
roc = path + "Output/roc_total.png"
#bohmer_model = bmr.train(train, header = 0, length = 5000000)
#bmr.test(train, test, output, bohmer_model, ",", 5000000, skip=0)
train_data = LogFile(train, ",", 0, 500000, None, "Case")
train_data.remove_attributes(["Anomaly"])
test_data = LogFile(test, ",", 0, 500000, None, "Case", train_data.string_2_int, train_data.int_2_string)
edbn_model = edbn.train(train_data)
edbn.test(test_data, output_edbn, edbn_model, "Anomaly", "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 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)
#bohmer_model = bmr.train(train + "_ints", header = 0, length = 500000)
#bmr.test(train + "_ints", test + "_ints", output, bohmer_model, ",", 500000, skip=0)
train_data = LogFile(train, ",", 0, 500000, None, "Case")
train_data.remove_attributes(["Anomaly"])
test_data = LogFile(test, ",", 0, 500000, None, "Case", train_data.string_2_int, train_data.int_2_string)
edbn_model = edbn.train(train_data)
edbn.test(test_data, output_edbn, edbn_model, "Anomaly", "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 run_full():
# Use the BPIC15_x_sorted.csv to generate new training and test datafiles with anomalies introduced
# After running this once you can comment this line out
#preProcessData("../Data/")
for i in range(1, 2):
# Indicate which are the training and test files
train_file = "../Data/bpic15_%i_train.csv" % (i)
test_file = "../Data/bpic15_%i_test.csv" % (i)
# Load logfile to use as training data
train_data = LogFile(train_file,
",",
0,
500000,
time_attr="Complete_Timestamp",
trace_attr="Case_ID",
activity_attr="Activity")
train_data.remove_attributes(["Anomaly"])
# train_data.keep_attributes(["Case_ID", "Complete_Timestamp", "Activity", "Resource", "case_termName"])
train_data.remove_attributes(["planned"])
train_data.remove_attributes(["dueDate"])
train_data.remove_attributes(["dateFinished"])
# train_data.keep_attributes(["Case_ID", "Complete_Timestamp", "Activity", "Resource", "Weekday"])
# train_data.create_k_context()
# train_data.add_duration_to_k_context()
# Train the model
model = edbn.train(train_data)
# Test the model and save the scores in ../Data/output.csv
test_data = LogFile(test_file,
",",
header=0,
rows=500000,
time_attr="Complete_Timestamp",
trace_attr="Case_ID",
values=train_data.values)
# test_data.create_k_context()
# test_data.add_duration_to_k_context()
edbn.test(test_data,
"../Data/output2_%i.csv" % (i),
model,
label="Anomaly",
normal_val="0",
train_data=train_data)
# Plot the ROC curve based on the results
plot.plot_single_roc_curve("../Data/output2_%i.csv" % (i),
title="BPIC15_%i" % (i))
plot.plot_single_prec_recall_curve("../Data/output2_%i.csv" % (i),
title="BPIC15_%i" % (i))
out_files = []
labels = []
for i in range(1, 6):
out_files.append("../Data/output2_%i.csv" % (i))
labels.append("MUNIS_%i" % (i))
plot.plot_compare_roc_curve(out_files, labels, "BPIC15 Comparison")
plot.plot_compare_prec_recall_curve(out_files, labels, "BPIC15 Comparison")