def _test1():
data = "../Data/BPIC15_1_sorted_new.csv"
case_attr = "case"
act_attr = "event"
logfile = LogFile(data,
",",
0,
None,
None,
case_attr,
activity_attr=act_attr,
convert=False,
k=5)
logfile.keep_attributes(["case", "event", "role"])
logfile.convert2int()
# logfile.filter_case_length(5)
logfile.create_k_context()
train_log, test_log = logfile.splitTrainTest(70,
case=True,
method="train-test")
model = edbn_train(train_log)
acc = predict_next_event(model, test_log)
acc_update = predict_next_event_update(model, test_log)
print("ACC:", acc, acc_update)
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 run_sdl():
from Methods.SDL.sdl import train, test
labeled_logfile = "../Data/Outcome_Prediction/BPIC15_1_f2.csv"
log = LogFile(labeled_logfile,
";",
0,
None,
"time_timestamp",
"Case_ID",
activity_attr="label",
convert=True,
k=10)
columns = [
"label", "Case_ID", "Activity", "monitoringResource", "question",
"org_resource", "Responsible_actor", "SUMleges"
]
log.keep_attributes(columns)
log.create_k_context()
train_log, test_log = log.splitTrainTest(80, True, "train-test")
train_log.ignoreHistoryAttributes.add("label")
test_log.ignoreHistoryAttributes.add("label")
model = train(train_log, 200, 42)
print(test(test_log, model))
results1 = []
results2 = []
for case in test_log.get_cases():
pass
def run_experiment(data, prefix_size, add_end_event, split_method, split_cases, train_percentage):
logfile = LogFile(data, ",", 0, None, None, "case",
activity_attr="event", convert=False, k=prefix_size)
if add_end_event:
logfile.add_end_events()
logfile.keep_attributes(["case", "event", "role"])
logfile.convert2int()
logfile.create_k_context()
train_log, test_log = logfile.splitTrainTest(train_percentage, case=split_cases, method=split_method)
with open("Baseline/results.txt", "a") as fout:
fout.write("Data: " + data)
fout.write("\nPrefix Size: " + str(prefix_size))
fout.write("\nEnd event: " + str(add_end_event))
fout.write("\nSplit method: " + split_method)
fout.write("\nSplit cases: " + str(split_cases))
fout.write("\nTrain percentage: " + str(train_percentage))
fout.write("\nDate: " + time.strftime("%d.%m.%y-%H.%M", time.localtime()))
fout.write("\n------------------------------------")
baseline_acc = test(test_log, train(train_log, epochs=100, early_stop=10))
fout.write("\nBaseline: " + str(baseline_acc))
fout.write("\n")
fout.write("====================================\n\n")
if __name__ == "__main__":
data = "../Data/BPIC15_1_sorted_new.csv"
case_attr = "case"
act_attr = "event"
logfile = LogFile(data,
",",
0,
None,
"completeTime",
case_attr,
activity_attr=act_attr,
convert=False,
k=5)
logfile.keep_attributes(["case", "event", "role"])
logfile.convert2int()
logfile.create_k_context()
weeks = logfile.split_days("%Y-%m-%d %H:%M:%S")
weeks_sorted = sorted(weeks.keys())
num_weeks = len(weeks_sorted)
for i in range(num_weeks):
weeks[weeks_sorted[i]]["model"] = edbn_train(
weeks[weeks_sorted[i]]["data"])
#
# accs1 = []
# for i in range(1, num_weeks):
# accs1.append(predict_next_event_multi([weeks[w]["model"] for w in weeks_sorted[:i]], weeks[weeks_sorted[i]]["data"]))
#
def run_edbn():
from eDBN_Prediction import get_probabilities
from Methods.EDBN.Train import train
labeled_logfile = "../Data/Outcome_Prediction/BPIC15_1_f2.csv"
log = LogFile(labeled_logfile,
";",
0,
None,
"time_timestamp",
"Case_ID",
activity_attr="label",
convert=True,
k=1)
columns = [
"label", "Case_ID", "time_timestamp", "Activity", "monitoringResource",
"question", "org_resource", "Responsible_actor", "SUMleges"
]
log.keep_attributes(columns)
log.create_k_context()
train_log, test_log = log.splitTrainTest(80, True, "train-test")
train_log.ignoreHistoryAttributes.add("label")
model = train(train_log)
results1 = []
results2 = []
for case in test_log.get_cases():
case_df = case[1]
case_probs = {1: 1, 2: 1}
ground = 0
for row in case_df.iterrows():
ground = getattr(row[1], "label")
parents = model.variables["label"].conditional_table.parents
value = []
for parent in parents:
value.append(getattr(row[1], parent.attr_name))
tuple_val = tuple(value)
activity_var = model.variables["label"]
probs, unknown = get_probabilities(activity_var, tuple_val,
parents)
case_probs[1] += probs.get(1, 0)
case_probs[2] += probs.get(2, 0)
# correct_prob = sum(case_probs) / len(case_probs)
if ground == 1:
if case_probs[1] > case_probs[2]:
results1.append(1)
else:
results1.append(0)
if ground == 2:
if case_probs[2] > case_probs[1]:
results2.append(1)
else:
results2.append(0)
print(len(results1), sum(results1) / len(results1))
print(len(results2), sum(results2) / len(results2))
if __name__ == "__main__":
data = "../../Data/Helpdesk.csv"
# data = "../../Data/BPIC15_1_sorted_new.csv"
case_attr = "case"
act_attr = "event"
logfile = LogFile(data,
",",
0,
None,
"completeTime",
case_attr,
activity_attr=act_attr,
convert=False,
k=5)
logfile.keep_attributes(["case", "event", "role", "completeTime"])
logfile.convert2int()
logfile.create_k_context()
train_log, test_log = logfile.splitTrainTest(70,
case=True,
method="train-test")
create_data(train_log, test_log, "helpdesk/")
# model = train(train_log, 5, 20)
# model = keras.models.load_model("premiere_model")
# print("Accuracy:", test(test_log, model))
def run_experiment(data,
prefix_size,
add_end_event,
split_method,
split_cases,
train_percentage,
filename="results.txt"):
data = DATA_FOLDER + data
logfile = LogFile(data,
",",
0,
None,
"completeTime",
"case",
activity_attr="event",
convert=False,
k=prefix_size)
if prefix_size is None:
prefix_size = max(logfile.data.groupby(logfile.trace).size())
if prefix_size > 40:
prefix_size = 40
logfile.k = prefix_size
if add_end_event:
logfile.add_end_events()
# logfile.keep_attributes(["case", "event", "role", "completeTime"])
logfile.keep_attributes(["case", "event", "role"])
logfile.convert2int()
logfile.create_k_context()
train_log, test_log = logfile.splitTrainTest(train_percentage,
case=split_cases,
method=split_method)
with open(filename, "a") as fout:
fout.write("Data: " + data)
fout.write("\nPrefix Size: " + str(prefix_size))
fout.write("\nEnd event: " + str(add_end_event))
fout.write("\nSplit method: " + split_method)
fout.write("\nSplit cases: " + str(split_cases))
fout.write("\nTrain percentage: " + str(train_percentage))
fout.write("\nDate: " +
time.strftime("%d.%m.%y-%H.%M", time.localtime()))
fout.write("\n------------------------------------\n")
processes = []
processes.append(
Process(target=execute_tax,
args=(train_log, test_log, filename),
name="Tax"))
processes.append(
Process(target=execute_taymouri,
args=(train_log, test_log, filename),
name="Taymouri"))
processes.append(
Process(target=execute_camargo,
args=(train_log, test_log, filename),
name="Camargo"))
processes.append(
Process(target=execute_lin,
args=(train_log, test_log, filename),
name="Lin"))
processes.append(
Process(target=execute_dimauro,
args=(train_log, test_log, filename),
name="Di Mauro"))
processes.append(
Process(target=execute_pasquadibisceglie,
args=(train_log, test_log, filename),
name="Pasquadibisceglie"))
processes.append(
Process(target=execute_edbn,
args=(train_log, test_log, filename),
name="EDBN"))
processes.append(
Process(target=execute_baseline,
args=(train_log, test_log, filename),
name="Baseline"))
# processes.append(Process(target=execute_new_method, args=(train_log, test_log, filename), name="New Method"))
print("Starting Processes")
for p in processes:
p.start()
print(p.name, "started")
print("All processes running")
for p in processes:
p.join()
print(p.name, "stopped")
with open(filename, "a") as fout:
fout.write("====================================\n\n")
print("All processes stopped")
def get_data(dataset, dataset_size, k, add_end, reduce_tasks, resource_pools, remove_resource):
filename_parts = [dataset, str(dataset_size), str(k)]
for v in [add_end, reduce_tasks, resource_pools, remove_resource]:
if v:
filename_parts.append(str(1))
else:
filename_parts.append(str(0))
print(filename_parts)
cache_file = LOGFILE_PATH + "/" + "_".join(filename_parts)
colTitles = []
if os.path.exists(cache_file):
print("Loading file from cache")
with open(cache_file, "rb") as pickle_file:
preprocessed_log = pickle.load(pickle_file)
else:
resource_attr = None
if dataset == BPIC15_1 or dataset == BPIC15:
logfile = LogFile("../Data/BPIC15_1_sorted_new.csv", ",", 0, dataset_size, "Complete Timestamp", "Case ID", activity_attr="Activity", convert=False, k=k)
resource_attr = "Resource"
colTitles = ["Case ID", "Activity", "Resource"]
logfile.keep_attributes(colTitles)
logfile.filter_case_length(5)
elif dataset == BPIC15_2:
logfile = LogFile("../Data/BPIC15_2_sorted_new.csv", ",", 0, dataset_size, "Complete Timestamp", "Case ID",
activity_attr="Activity", convert=False, k=k)
resource_attr = "Resource"
colTitles = ["Case ID", "Activity", "Resource"]
logfile.keep_attributes(colTitles)
logfile.filter_case_length(5)
elif dataset == BPIC15_3:
logfile = LogFile("../Data/BPIC15_3_sorted_new.csv", ",", 0, dataset_size, "Complete Timestamp", "Case ID", activity_attr="Activity", convert=False, k=k)
resource_attr = "Resource"
colTitles = ["Case ID", "Activity", "Resource"]
logfile.keep_attributes(colTitles)
logfile.filter_case_length(5)
elif dataset == BPIC15_4:
logfile = LogFile("../Data/BPIC15_4_sorted_new.csv", ",", 0, dataset_size, "Complete Timestamp", "Case ID", activity_attr="Activity", convert=False, k=k)
resource_attr = "Resource"
colTitles = ["Case ID", "Activity", "Resource"]
logfile.keep_attributes(colTitles)
logfile.filter_case_length(5)
elif dataset == BPIC15_5:
logfile = LogFile("../Data/BPIC15_5_sorted_new.csv", ",", 0, dataset_size, "Complete Timestamp", "Case ID", activity_attr="Activity", convert=False, k=k)
resource_attr = "Resource"
colTitles = ["Case ID", "Activity", "Resource"]
logfile.keep_attributes(colTitles)
logfile.filter_case_length(5)
elif dataset == BPIC12:
logfile = LogFile("../Data/BPIC12.csv", ",", 0, dataset_size, "completeTime", "case", activity_attr="event", convert=False, k=k)
resource_attr = "org:resource"
colTitles = ["case", "event", "org:resource"]
logfile.keep_attributes(colTitles)
logfile.filter_case_length(5)
elif dataset == BPIC12W:
logfile = LogFile("../Data/BPIC12W.csv", ",", 0, dataset_size, "completeTime", "case", activity_attr="event", convert=False, k=k)
resource_attr = "org:resource"
colTitles = ["case", "event", "org:resource"]
logfile.keep_attributes(colTitles)
logfile.filter_case_length(5)
elif dataset == HELPDESK:
logfile = LogFile("../Data/Helpdesk.csv", ",", 0, dataset_size, "completeTime", "case", activity_attr="event", convert=False, k=k)
resource_attr = "Resource"
colTitles = ["case", "event", "Resource"]
logfile.keep_attributes(colTitles)
logfile.filter_case_length(3)
elif dataset == BPIC18:
logfile = LogFile("../Data/bpic2018.csv", ",", 0, dataset_size, "startTime", "case", activity_attr="event", convert=False, k=k)
colTitles = ["case", "event", "subprocess"]
logfile.keep_attributes(colTitles)
else:
print("Unknown Dataset")
return None
preprocessed_log = preprocess(logfile, add_end, reduce_tasks, resource_pools, resource_attr, remove_resource)
preprocessed_log.create_k_context()
with open(cache_file, "wb") as pickle_file:
pickle.dump(preprocessed_log, pickle_file)
return preprocessed_log, "_".join(filename_parts)
