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')
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)
max_iter=MAX_ITERATIONS,
init=INITIALIZE_CLUSTERS,
tol=CONVERGENCE_TOLERANCE,
n_jobs=NUM_THREADS)
# Create the cluster with the log vector
kmeans.fit(log_vector)
# Create new log with the attribute for the original log
new_logs = {}
for i in range(len(kmeans.cluster_centers_)):
new_log = XFactory.create_log(log.get_attributes().clone())
for elem in log.get_extensions():
new_log.get_extensions().add(elem)
new_log.__classifiers = log.get_classifiers().copy()
new_log.__globalTraceAttributes = log.get_global_trace_attributes(
).copy()
new_log.__globalEventAttributes = log.get_global_event_attributes(
).copy()
new_logs[str(i)] = new_log
# Distribute the trace depending the cluster.
for point, trace in zip(log_vector, log):
cluster = kmeans.predict([point])[0]
new_logs[str(cluster)].append(trace)
# Write the new logs
log_id = 0
for log in new_logs.values():