def get_encoded_logs(job: Job,
use_cache: bool = True) -> (DataFrame, DataFrame):
"""returns the encoded logs
returns the training and test DataFrames encoded using the given job configuration, loading from cache if possible
:param job: job configuration
:param use_cache: load or not saved datasets from cache
:return: training and testing DataFrame
"""
print('\tGetting Dataset')
if use_cache:
if LabelledLog.objects.filter(split=job.split,
encoding=job.encoding,
labelling=job.labelling).exists():
training_df, test_df = get_labelled_logs(job)
else:
if job.split.train_log is not None and \
job.split.test_log is not None and \
LoadedLog.objects.filter(train_log=job.split.train_log.path,
test_log=job.split.test_log.path).exists():
training_log, test_log, additional_columns = get_loaded_logs(
job.split)
else:
training_log, test_log, additional_columns = prepare_logs(
job.split)
if job.split.type == SplitTypes.SPLIT_SINGLE.value:
job.split = duplicate_orm_row(job.split)
job.split.type = SplitTypes.SPLIT_DOUBLE.value
train_name = '0-' + str(
int(100 - (job.split.test_size * 100)))
job.split.train_log = create_log(EventLog(training_log),
train_name + '.xes')
test_name = str(int(100 -
(job.split.test_size * 100))) + '-100'
job.split.test_log = create_log(EventLog(test_log),
test_name + '.xes')
job.split.additional_columns = str(
train_name +
test_name) # TODO: find better naming policy
job.save()
put_loaded_logs(job.split, training_log, test_log,
additional_columns)
training_df, test_df = encode_label_logs(
training_log,
test_log,
job,
additional_columns=additional_columns)
put_labelled_logs(job, training_df, test_df)
else:
training_log, test_log, additional_columns = prepare_logs(job.split)
training_df, test_df = encode_label_logs(
training_log, test_log, job, additional_columns=additional_columns)
return training_df, test_df
def test_random(self):
split = split_single(
split_ordering=SplitOrderingMethods.SPLIT_RANDOM.value)
training_log1, _, _ = prepare_logs(split)
training_log2, _, _ = prepare_logs(split)
training_names1 = trace_names(training_log1)
training_names2 = trace_names(training_log2)
self.assertNotEqual(training_names1, training_names2)
def test_sequential(self):
split = split_single(
split_ordering=SplitOrderingMethods.SPLIT_SEQUENTIAL.value)
training_log, test_log, _ = prepare_logs(split)
training_names = trace_names(training_log)
test_names = trace_names(test_log)
self.assertListEqual(['3', '2', '1', '6'], training_names)
self.assertListEqual(['5', '4'], test_names)
def test_strict_temporal(self):
split = split_single(
split_ordering=SplitOrderingMethods.SPLIT_STRICT_TEMPORAL.value)
training_log, test_log, _ = prepare_logs(split)
training_names = trace_names(training_log)
test_names = trace_names(test_log)
# Modified log to have only one trace here
self.assertListEqual(['1'], sorted(training_names))
self.assertListEqual(sorted(['6', '4']), sorted(test_names))
def test_temporal(self):
split = split_single(
split_ordering=SplitOrderingMethods.SPLIT_TEMPORAL.value)
training_log, test_log, _ = prepare_logs(split)
training_names = trace_names(training_log)
test_names = trace_names(test_log)
self.assertListEqual(sorted(['1', '2', '3', '5']),
sorted(training_names))
self.assertListEqual(sorted(['6', '4']), sorted(test_names))
def test_size(self):
split = split_single(test_size=0.5)
training_log, test_log, _ = prepare_logs(split)
self.assertEqual(3, len(training_log))
self.assertEqual(3, len(test_log))
def test_split_double(self):
training_log, test_log, _ = prepare_logs(split_double())
self.assertEqual(4, len(training_log))
self.assertEqual(2, len(test_log))