def test_random(self):
split = split_single(
split_ordering=SplitOrderingMethods.SPLIT_RANDOM.value)
training_log1, _, _ = get_train_test_log(split)
training_log2, _, _ = get_train_test_log(split)
training_names1 = trace_names(training_log1)
training_names2 = trace_names(training_log2)
self.assertNotEqual(training_names1, training_names2)
def retrieve_proper_encoder(job: Job) -> Encoder:
if job.incremental_train is not None:
return retrieve_proper_encoder(job.incremental_train)
else:
training_log, test_log, additional_columns = get_train_test_log(job.split)
training_df, _ = encode_label_logs(training_log, test_log, job, additional_columns=additional_columns,
encode=False)
return Encoder(training_df, job.encoding)
def test_sequential(self):
split = split_single(
split_ordering=SplitOrderingMethods.SPLIT_SEQUENTIAL.value)
training_log, test_log, _ = get_train_test_log(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, _ = get_train_test_log(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, _ = get_train_test_log(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 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
"""
logger.info('\tGetting Dataset')
if use_cache and \
(job.predictive_model is not None and
job.predictive_model.predictive_model != PredictiveModels.TIME_SERIES_PREDICTION.value):
if LabelledLog.objects.filter(split=job.split,
encoding=job.encoding,
labelling=job.labelling).exists():
try:
training_df, test_df = get_labelled_logs(job)
except FileNotFoundError: #cache invalidation
LabelledLog.objects.filter(split=job.split,
encoding=job.encoding,
labelling=job.labelling).delete()
logger.info('\t\tError pre-labeled cache invalidated!')
return get_encoded_logs(job, use_cache)
else:
if job.split.train_log is not None and \
job.split.test_log is not None and \
LoadedLog.objects.filter(split=job.split).exists():
try:
training_log, test_log, additional_columns = get_loaded_logs(
job.split)
except FileNotFoundError: # cache invalidation
LoadedLog.objects.filter(split=job.split).delete()
logger.info('\t\tError pre-loaded cache invalidated!')
return get_encoded_logs(job, use_cache)
else:
training_log, test_log, additional_columns = get_train_test_log(
job.split)
if job.split.type == SplitTypes.SPLIT_SINGLE.value:
search_for_already_existing_split = Split.objects.filter(
type=SplitTypes.SPLIT_DOUBLE.value,
original_log=job.split.original_log,
test_size=job.split.test_size,
splitting_method=job.split.splitting_method)
if len(search_for_already_existing_split) >= 1:
job.split = search_for_already_existing_split[0]
job.split.save()
job.save()
return get_encoded_logs(job, use_cache=use_cache)
else:
# job.split = duplicate_orm_row(Split.objects.filter(pk=job.split.pk)[0]) #todo: replace with simple CREATE
job.split = Split.objects.create(
type=job.split.type,
original_log=job.split.original_log,
test_size=job.split.test_size,
splitting_method=job.split.splitting_method,
train_log=job.split.train_log,
test_log=job.split.test_log,
additional_columns=job.split.additional_columns
) #todo: futurebug if object changes
job.split.type = SplitTypes.SPLIT_DOUBLE.value
train_name = 'SPLITTED_' + job.split.original_log.name.split(
'.')[0] + '_0-' + str(
int(100 - (job.split.test_size * 100)))
job.split.train_log = create_log(
EventLog(training_log), train_name + '.xes')
test_name = 'SPLITTED_' + job.split.original_log.name.split(
'.')[0] + '_' + 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.split.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 = get_train_test_log(
job.split)
training_df, test_df = encode_label_logs(
training_log, test_log, job, additional_columns=additional_columns)
return training_df, test_df
def progetto_padova():
JOB = Job.objects.get_or_create(
status=JobStatuses.CREATED.value,
type=JobTypes.PREDICTION.value,
split=Split.objects.get_or_create( # this creates the split of the log
type=SplitTypes.SPLIT_DOUBLE.value,
train_log=create_log( # this imports the log
import_log(BASE_DIR + RELATIVE_TRAIN_PATH),
RELATIVE_TRAIN_PATH,
BASE_DIR,
import_in_cache=False),
test_log=create_log( # this imports the log
import_log(BASE_DIR + RELATIVE_VALIDATION_PATH),
RELATIVE_VALIDATION_PATH,
BASE_DIR,
import_in_cache=False))[0],
encoding=Encoding.objects.
get_or_create( # this defines the encoding method
data_encoding=DataEncodings.LABEL_ENCODER.value,
value_encoding=ValueEncodings.SIMPLE_INDEX.value,
add_elapsed_time=False,
add_remaining_time=False,
add_executed_events=False,
add_resources_used=False,
add_new_traces=False,
prefix_length=5,
padding=True,
task_generation_type=TaskGenerationTypes.ALL_IN_ONE.value,
features=[])[0],
labelling=Labelling.objects.get_or_create( # this defines the label
type=LabelTypes.ATTRIBUTE_STRING.value,
attribute_name='label',
threshold_type=None,
threshold=None)[0],
clustering=Clustering.init(ClusteringMethods.NO_CLUSTER.value,
configuration={}),
predictive_model=PredictiveModel.
init( # this defines the predictive model
get_prediction_method_config(
PredictiveModels.CLASSIFICATION.value,
ClassificationMethods.DECISION_TREE.value,
payload={
'max_depth': 2,
'min_samples_split': 2,
'min_samples_leaf': 2
})),
hyperparameter_optimizer=HyperparameterOptimization.init(
{ # this defines the hyperparameter optimisation procedure
'type': HyperparameterOptimizationMethods.HYPEROPT.value,
'max_evaluations': 10,
'performance_metric': HyperOptAlgorithms.TPE.value,
'algorithm_type': HyperOptLosses.AUC.value
}),
create_models=True)[0]
# load log
train_log, test_log, additional_columns = get_train_test_log(JOB.split)
# encode
train_df, test_df = encode_label_logs(train_log, test_log, JOB)
# train + evaluate
results, model_split = MODEL[JOB.predictive_model.predictive_model][
ModelActions.BUILD_MODEL_AND_TEST.value](train_df, test_df,
_init_clusterer(
JOB.clustering, train_df),
JOB)
if JOB.create_models:
save_models(model_split, JOB)
# predict
data_df = pd.concat([train_df, test_df])
results = MODEL[JOB.predictive_model.predictive_model][
ModelActions.PREDICT.value](JOB, data_df)
results = MODEL[JOB.predictive_model.predictive_model][
ModelActions.PREDICT_PROBA.value](JOB, data_df)
# lime
exp = Explanation.objects.get_or_create(
type=ExplanationTypes.LIME.value,
split=JOB.
split, # this defines the analysed log, you can use a different one from the training one
predictive_model=JOB.predictive_model,
job=JOB)[0]
error, result = explanation(exp.id, int(EXPLANATION_TARGET))
def test_size(self):
split = split_single(test_size=0.5)
training_log, test_log, _ = get_train_test_log(split)
self.assertEqual(3, len(training_log))
self.assertEqual(3, len(test_log))
def test_split_double(self):
training_log, test_log, _ = get_train_test_log(split_double())
self.assertEqual(4, len(training_log))
self.assertEqual(2, len(test_log))
def replay_core(replay_job: Job, training_initial_job: Job) -> list:
"""The function create a set with timestamps of events, then create a list of requests
simulating the log in the time passing
:param replay_job: job dictionary
:param training_initial_job: job dictionary
:return: List of requests
"""
split = replay_job.split
log = get_log(split.train_log)
requests_list = list()
eventlog = EventLog()
for key in log.attributes.keys():
eventlog.attributes[key] = log.attributes[key]
for trace in log:
new_trace = Trace(trace)
for key in trace.attributes:
new_trace.attributes[key] = trace.attributes[key]
eventlog.append(new_trace)
times = sorted(
set([event['time:timestamp'] for trace in eventlog
for event in trace]))
for t in times[2::int((len(times) - 2) / 5)]:
filtered_eventlog = timestamp_filter.apply_events(
eventlog, times[0].replace(tzinfo=None), t.replace(tzinfo=None))
trace_list = list()
event_number = dict()
for trace in filtered_eventlog:
trace_list.append(trace.attributes['concept:name'])
event_number[trace.attributes['concept:name']] = len(trace)
replay_job.case_id = trace_list
replay_job.event_number = event_number
replay_job.save()
try: #TODO check logger usage
logger.info("Sending request for replay_prediction task.")
r = requests.post(
url="http://server:8000/runtime/replay_prediction/",
data=export_log_as_string(filtered_eventlog),
params={
'jobId': replay_job.id,
'training_job': training_initial_job.id
},
headers={
'Content-Type': 'text/plain',
'charset': 'UTF-8'
})
requests_list.append(str(r))
except Exception as e:
requests_list.append(str(e))
logger.warning(str(e))
training_log, test_log, additional_columns = get_train_test_log(
replay_job.split)
training_df, _ = encode_label_logs(training_log,
test_log,
replay_job,
additional_columns=additional_columns)
gold_values = dict(zip(training_df['trace_id'], training_df['label']))
parent_id = replay_job.id
# final_job = duplicate_orm_row(replay_job) #todo: replace with simple CREATE
final_job = Job.objects.create(
created_date=replay_job.created_date,
modified_date=replay_job.modified_date,
error=replay_job.error,
status=replay_job.status,
type=replay_job.type,
create_models=replay_job.create_models,
case_id=replay_job.case_id,
event_number=replay_job.event_number,
gold_value=replay_job.gold_value,
results=replay_job.results,
parent_job=replay_job.parent_job,
split=replay_job.split,
encoding=replay_job.encoding,
labelling=replay_job.labelling,
clustering=replay_job.clustering,
predictive_model=replay_job.predictive_model,
evaluation=replay_job.evaluation,
hyperparameter_optimizer=replay_job.hyperparameter_optimizer,
incremental_train=replay_job.incremental_train)
final_job.parent_job = Job.objects.filter(pk=parent_id)[0]
final_job.gold_value = gold_values
final_job.type = JobTypes.REPLAY_PREDICT.value
final_job.save()
return requests_list