def load(self, dataset_name):
"""
Load dataset from disk. If there exists a cached file, load from cache. If no cache file exists, load from
Event Log and cache it.
:param dataset_name:
:return:
"""
el_file = EventLogFile(dataset_name)
self.dataset_name = el_file.name
# Check for cache
if el_file.cache_file.exists():
self._load_dataset_from_cache(el_file.cache_file)
# Else generate from event log
elif el_file.path.exists():
self._event_log = EventLog.load(el_file.path)
self.from_event_log(self._event_log)
self._cache_dataset(el_file.cache_file)
'bpic15-0.0-5.json.gz',
'bpic12-0.0-0.json.gz',
'bpic17-0.0-1.json.gz',
'bpic17-0.0-2.json.gz'
]
np.random.seed(0) # This will ensure reproducibility
ps = [0.3]
event_log_paths = [
e.path for e in get_event_log_files(EVENTLOG_DIR)
if 'bpic' in e.name and e.p == 0.0
]
combinations = list(itertools.product(event_log_paths, ps))
for event_log_path, p in tqdm(combinations, desc='Add anomalies'):
event_log_file = EventLogFile(event_log_path)
event_log = EventLog.from_json(event_log_path)
anomalies = [
ReplaceAnomaly(max_replacements=1),
SkipSequenceAnomaly(max_sequence_size=2),
ReworkAnomaly(max_distance=5, max_sequence_size=3),
EarlyAnomaly(max_distance=5, max_sequence_size=2),
LateAnomaly(max_distance=5, max_sequence_size=2),
InsertAnomaly(max_inserts=2)
]
# if event_log.num_event_attributes > 0:
# anomalies.append(AttributeAnomaly(max_events=3, max_attributes=min(2, event_log.num_activities)))
for anomaly in anomalies: