def load_xes(self):
try:
with open(self.input_path) as log_file:
log = XUniversalParser().parse(log_file)[0]
# get classifiers
classifiers = []
for cl in log.get_classifiers():
classifiers.append(str(cl))
classifier = XEventAttributeClassifier("activity", [classifiers[0]])
log_list = list(map(lambda trace: list(map(classifier.get_class_identity, trace)), log))
self._event_log = set(tuple(trace) for trace in log_list)
except:
raise IOError('[ERROR]: Unable to import xes file')
def read_event_log_file(log_filepath):
if not os.path.isfile(log_filepath):
raise ValueError('{} is not a log file!'.format(log_filepath))
with open(log_filepath, 'r') as f:
logs = XUniversalParser.parse(f)
log = logs[0]
return log
def xlog():
xlog_fp = os.path.join('.', 'tests', 'testdata', 'BPIC2012.xes.gz')
start = time.time()
with open(xlog_fp, 'r') as f:
xlog = XUniversalParser.parse(f)[0]
size = sys.getsizeof(xlog)
print('BPIC2012 XLog size: {}b'.format(size))
diff = time.time() - start
print('Took {} secs to parse BPIC2012'.format(diff))
return xlog
def read_XES_log(path):
tic = time()
print("Parsing log")
with open(path) as log_file:
log = XUniversalParser().parse(log_file)[0] # take first log from file
toc = time()
print("Log parsed, took {} seconds..".format(toc - tic))
return log
def mapXes(self, lfile, header):
with open(lfile) as log_file:
log = XUniversalParser().parse(log_file)[0]
return log
ext_lifecycle = XExtensionParser().parse("http://www.xes-standard.org/lifecycle.xesext")
print("[info] XExtensionParser completed the extension parsing")
# Then we register the new extension
print("[info] XExtensionManager starts the registration of extensions")
XExtensionManager().register(meta_general)
XExtensionManager().register(meta_concept)
XExtensionManager().register(meta_time)
XExtensionManager().register(ext_concept)
XExtensionManager().register(ext_time)
XExtensionManager().register(ext_lifecycle)
print("[info] XExtensionManager completed the registration of extensions")
# Now we can parse
with open("./data/bpic2012.xes") as file:
logs = XUniversalParser().parse(file)
log = logs[0]
drift_idx = 0
for trace in log:
# the chosen case' id = 197611
if trace.get_attributes()['concept:name'].get_value() == '197611':
print('drift_idx = %d' % drift_idx)
break
drift_idx+=1
log = log[0:drift_idx] # select the training set before the drift occurs
log_dict = {'case_id':[], 'case_execution_time':[], 'case_execution_time_seconds':[], 'num_of_events':[]}
from opyenxes.classification.XEventAttributeClassifier import XEventAttributeClassifier
from opyenxes.data_in.XUniversalParser import XUniversalParser
file_path = "/home/bartlomiej/process-mining/process-mining-algorithms/event_logs/L1.xes"
output_directory = "./output/"
with open(file_path) as log_file:
# Parse the log
log = XUniversalParser().parse(log_file)[0]
# Generate the classifier
classifier = XEventAttributeClassifier("concept:name", ["concept:name"])
# Convert log object in array with only the Activity attribute of the event
log_list = list(
map(lambda trace: list(map(classifier.get_class_identity, trace)), log))
factory = XFactory()
print(os.listdir(datadir))
for dir in os.listdir(datadir):
if not os.path.isdir(os.path.join(datadir, dir)):
continue
outdir = os.path.join(datadir, dir, 'l1000')
os.makedirs(outdir)
for xlog_filepath in os.listdir(os.path.join(datadir, dir, 'l5000')):
if '.xes.gz' not in xlog_filepath:
continue
print('Processing {}'.format(xlog_filepath))
with open(os.path.join(datadir, dir, xlog_filepath), 'r') as f:
xlog = XUniversalParser().parse(f)[0]
assert isinstance(xlog, XLog)
new_xlog = factory.create_log(xlog.get_attributes())
traces = np.random.choice(xlog, nb_traces, replace=False)
new_xlog.get_classifiers().append(xlog.get_classifiers()[0])
for t in traces:
new_xlog.append(t)
with open(outdir + os.sep + xlog_filepath, 'w') as f:
XesXmlGZIPSerializer().serialize(new_xlog, f)
def readLogFile(file):
with open(file) as log_file:
return XUniversalParser().parse(log_file), xes_importer.apply(file)
from opyenxes.model.XLog import XLog
from opyenxes.data_in.XUniversalParser import XUniversalParser
from opyenxes.classification.XEventAttributeClassifier import XEventAttributeClassifier
from opyenxes.out.XesXmlSerializer import XesXmlSerializer
from sklearn.cluster import KMeans
from opyenxes.factory.XFactory import XFactory
if __name__ == '__main__':
path = "xes_file/log_to_cluster.xes"
# Parse Logs
with open(path) as log_file:
log = XUniversalParser().parse(log_file)[0] # type: XLog
# Convert log object in array with only the Activity attribute of the event
classifier = XEventAttributeClassifier("activity", ["Activity"])
log_list = list(
map(lambda trace: list(map(classifier.get_class_identity, trace)),
log))
event_set = set()
for trace in log_list:
for event in trace:
event_set.add(event)
all_event = list(event_set)
log_vector = []
for trace in log_list:
trace_vector = []
for event in all_event:
trace_vector.append(trace.count(event))
return log
filePath = sys.argv[1]
epsilon = sys.argv[2]
dbName = sys.argv[3]
secure_token = sys.argv[4]
#preprocess file
#os.mkdir(secure_token)
print("\n Starting privatize_df.py \n")
outPath = filePath.replace(".xes","_%s.xes" % (epsilon))
log = xes_import_factory.apply(filePath)
parser = XUniversalParser()
if parser.can_parse(filePath):
print("log can be parsed.")
else:
print("log can not be parsed.")
log_file = open(filePath)
log_list = parser.parse(log_file)
#log = log_list[0]
event_mapping = create_event_int_mapping(log)
privatize_df(log_list, event_mapping, epsilon, outPath)
#write to db
print("Writing to DB")
return merged_log
if __name__ == "__main__":
normLogs = []
devLogs = []
normPathTemp = "out_xraynorm{}.xes"
devPathTemp = "out_xraydev{}.xes"
normLogCount = 7
devLogCount = 1
for i in range(1, normLogCount + 1):
logPath = normPathTemp.format(i)
with open(logPath) as log_file:
normLogs.append(XUniversalParser().parse(log_file)[0])
for i in range(1, devLogCount + 1):
logPath = devPathTemp.format(i)
with open(logPath) as log_file:
devLogs.append(XUniversalParser().parse(log_file)[0])
merged_log = merge_and_label(normLogs, devLogs)
shuffle(merged_log)
with open("merged_xray.xes", "w") as f:
XesXmlSerializer().serialize(merged_log, f)
"""
Anonymize a log.
All value of "resource" attribute and "org:resource" attribute will be "UNKNOWN" now:
"""
from opyenxes.data_in.XUniversalParser import XUniversalParser
from opyenxes.data_out.XesXmlSerializer import XesXmlSerializer
path = "xes_file/general_example.xes"
with open(path) as log_file:
log = XUniversalParser().parse(log_file)[0]
# Search in global trace attribute
for attribute in log.get_global_trace_attributes():
if attribute.get_key() in ["Resource", "org:resource"]:
attribute.set_value("UNKNOWN")
# Search in global event attribute
for attribute in log.get_global_event_attributes():
if attribute.get_key() in ["Resource", "org:resource"]:
attribute.set_value("UNKNOWN")
# Search in trace
for trace in log:
# Search in trace attribute
for attribute in trace.get_attributes().values():
if attribute.get_key() in ["Resource", "org:resource"]:
attribute.set_value("UNKNOWN")
# Search in event
for event in trace:
# Search in event attribute