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():
with open("xes_file/New_cluster_log_{}.xes".format(str(log_id)),
"w") as file:
"""
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