def train_lin(data_folder, model_folder):
from RelatedMethods.Lin.model import train
logfile = LogFile(data_folder + "full_log.csv",
",",
0,
None,
None,
"case",
activity_attr="event",
convert=False,
k=0)
logfile.add_end_events()
logfile.convert2int()
train_log = LogFile(data_folder + "train_log.csv",
",",
0,
None,
None,
"case",
activity_attr="event",
convert=False,
k=0,
values=logfile.values)
train_log.add_end_events()
train_log.convert2int()
train(logfile, train_log, model_folder)
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")
def train_edbn(data_folder, model_folder, k=None, next_event=True):
from EDBN.Execute import train
from Predictions.eDBN_Prediction import learn_duplicated_events, predict_next_event, predict_suffix
if k is None:
best_model = {}
for k in range(1, 6):
train_log = LogFile(data_folder + "train_log.csv",
",",
0,
None,
None,
"case",
activity_attr="event",
convert=False,
k=k)
train_train_log, train_test_log = train_log.splitTrainTest(80)
train_train_log.add_end_events()
train_train_log.convert2int()
train_train_log.create_k_context()
train_test_log.values = train_train_log.values
train_test_log.add_end_events()
train_test_log.convert2int()
train_test_log.create_k_context()
model = train(train_train_log)
# Train average number of duplicated events
model.duplicate_events = learn_duplicated_events(train_train_log)
if next_event:
acc = predict_next_event(model, train_test_log)
else:
acc = predict_suffix(model, train_test_log)
print("Testing k=", k, " | Validation acc:", acc)
if "Acc" not in best_model or best_model["Acc"] < acc:
best_model["Acc"] = acc
best_model["Model"] = model
best_model["k"] = k
print("Best k value:", best_model["k"], " | Validation acc of",
best_model["Acc"])
k = best_model["k"]
train_log = LogFile(data_folder + "train_log.csv",
",",
0,
None,
None,
"case",
activity_attr="event",
convert=False,
k=k)
train_log.add_end_events()
train_log.convert2int()
train_log.create_k_context()
model = train(train_log)
# Train average number of duplicated events
model.duplicate_events = learn_duplicated_events(train_log)
with open(os.path.join(model_folder, "model"), "wb") as pickle_file:
pickle.dump(model, pickle_file)
with open(os.path.join(model_folder, "k"), "w") as outfile:
outfile.write(str(k))
return acc
if __name__ == "__main__":
# data = "../../Data/Helpdesk.csv"
data = "../../Data/Taymouri_bpi_12_w.csv"
case_attr = "case"
act_attr = "event"
logfile = LogFile(data,
",",
0,
None,
None,
case_attr,
activity_attr=act_attr,
convert=False,
k=35)
logfile.add_end_events()
logfile.convert2int()
logfile.create_k_context()
train_log, test_log = logfile.splitTrainTest(80,
case=True,
method="train-test")
train_data, test_data = create_input(train_log, test_log, 5)
model = train(train_data)
test(test_data, 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")
