def sample_stream(event_log, no_events=100):
"""
Randomly sample a fixed number of events from the original event log
Parameters
-----------
event_log
Event log
no_events
Number of events that the sample should have
Returns
-----------
newLog
Filtered log
"""
new_log = EventStream(attributes=event_log.attributes,
extensions=event_log.extensions,
globals=event_log._omni,
classifiers=event_log.classifiers)
set_events = set()
for i in range(0, min(no_events, len(event_log._list))):
set_events.add(random.randrange(0, len(event_log._list)))
set_events = list(set_events)
for event in set_events:
new_log.append(copy(event_log._list[event]))
return new_log
def preprocess_log(log, activities=None, parameters=None):
"""
Preprocess a log to enable correlation mining
Parameters
--------------
log
Log object
activities
(if provided) list of activities of the log
parameters
Parameters of the algorithm
Returns
--------------
transf_stream
Transformed stream
activities_grouped
Grouped activities
activities
List of activities of the log
"""
if parameters is None:
parameters = {}
activity_key = exec_utils.get_param_value(Parameters.ACTIVITY_KEY, parameters, xes_constants.DEFAULT_NAME_KEY)
timestamp_key = exec_utils.get_param_value(Parameters.TIMESTAMP_KEY, parameters,
xes_constants.DEFAULT_TIMESTAMP_KEY)
start_timestamp_key = exec_utils.get_param_value(Parameters.START_TIMESTAMP_KEY, parameters,
xes_constants.DEFAULT_TIMESTAMP_KEY)
index_key = exec_utils.get_param_value(Parameters.INDEX_KEY, parameters, DEFAULT_INDEX_KEY)
if type(log) is pd.DataFrame:
# keep only the two columns before conversion
log = log[list(set([activity_key, timestamp_key, start_timestamp_key]))]
log = converter.apply(log, variant=converter.TO_EVENT_STREAM, parameters=parameters)
transf_stream = EventStream()
for idx, ev in enumerate(log):
transf_stream.append(
Event({activity_key: ev[activity_key], timestamp_key: ev[timestamp_key].timestamp(),
start_timestamp_key: ev[start_timestamp_key].timestamp(), index_key: idx}))
transf_stream = sorted(transf_stream, key=lambda x: (x[start_timestamp_key], x[timestamp_key], x[index_key]))
if activities is None:
activities = sorted(list(set(x[activity_key] for x in transf_stream)))
activities_grouped = {x: [y for y in transf_stream if y[activity_key] == x] for x in activities}
return transf_stream, activities_grouped, activities