data = "../../Data/BPIC12W.csv"
# data = "../../Data/Helpdesk.csv"
# data = "../../Data/Taymouri_bpi_12_w.csv"
case_attr = "case"
act_attr = "event"
k = 15
logfile = LogFile(data,
",",
0,
None,
None,
case_attr,
activity_attr=act_attr,
convert=False,
k=10)
logfile.convert2int()
logfile.filter_case_length(5)
# logfile.k = min(k, max(logfile.data.groupby(logfile.trace).size()))
logfile.create_k_context()
train_log, test_log = logfile.splitTrainTest(70,
case=False,
method="test-train")
model = train(train_log, epochs=100, early_stop=10)
# model.save("tmp.h5")
# from keras.models import load_model
# test(test_log, load_model("tmp.h5"))
test(test_log, model)
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)