def replay_prediction(replay_job: Job, training_initial_job: Job,
trace_id) -> list:
"""The function create a set with timestamps of events, then create a list of requests
simulating the log in the time passing
:param trace_id:
: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()
trace = log[int(trace_id)]
for key in log.attributes.keys():
eventlog.attributes[key] = log.attributes[key]
for index in range(len(trace)):
new_trace = Trace(trace[0:index])
for key in trace.attributes:
new_trace.attributes[key] = trace.attributes[key]
eventlog.append(new_trace)
replay_job.case_id = trace_id
replay_job.event_number = len(trace)
replay_job.save()
try:
logger.error("Sending request for replay_prediction task.")
r = requests.post(
url="http://127.0.0.1:8000/runtime/replay_prediction/",
data=export_log_as_string(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))
return requests_list
def replay_prediction_task(replay_prediction_job: Job, training_initial_job: Job, log: Log):
""" The function create a replat prediction task to ask a single prediction to the server for a portion of a trace
:param replay_prediction_job: job dictionary
:param training_initial_job: job dictionary
:param log: job dictionary
"""
logger.info("Start replay_prediction task ID {}".format(replay_prediction_job.id))
try:
replay_prediction_job.status = JobStatuses.RUNNING.value
replay_prediction_job.save()
max_len = max(len(trace) for trace in log)
if replay_prediction_job.encoding.prefix_length != max_len:
prediction_job = create_prediction_job(training_initial_job, max_len)
prediction_task(prediction_job.id)
prediction_job.refresh_from_db()
new_replay_prediction_job = duplicate_orm_row(prediction_job)
new_replay_prediction_job.split = Split.objects.filter(pk=replay_prediction_job.split.id)[0]
new_replay_prediction_job.type = JobTypes.REPLAY_PREDICT.value
new_replay_prediction_job.parent_job = replay_prediction_job.parent_job
new_replay_prediction_job.status = JobStatuses.CREATED.value
replay_prediction_task(new_replay_prediction_job, prediction_job, log)
return
result_dict, events_for_trace = replay_prediction_calculate(replay_prediction_job, log)
replay_prediction_job.results = dict(result_dict)
replay_prediction_job.event_number = dict(events_for_trace)
replay_prediction_job.status = JobStatuses.COMPLETED.value
replay_prediction_job.error = ''
except Exception as e:
logger.error(e)
replay_prediction_job.status = JobStatuses.ERROR.value
replay_prediction_job.error = str(e.__repr__())
raise e
finally:
replay_prediction_job.save()
publish(replay_prediction_job)
def replay_prediction_task(replay_prediction_job: Job,
training_initial_job: Job, log: Log):
""" The function create a replat prediction task to ask a single prediction to the server for a portion of a trace
:param replay_prediction_job: job dictionary
:param training_initial_job: job dictionary
:param log: job dictionary
"""
logger.info("Start replay_prediction task ID {}".format(
replay_prediction_job.id))
try:
replay_prediction_job.status = JobStatuses.RUNNING.value
replay_prediction_job.save()
max_len = max(len(trace) for trace in log)
if replay_prediction_job.encoding.prefix_length != max_len:
prediction_job = create_prediction_job(training_initial_job,
max_len)
prediction_task(prediction_job.id)
prediction_job.refresh_from_db()
# new_replay_prediction_job = duplicate_orm_row(prediction_job) #todo: replace with simple CREATE
new_replay_prediction_job = Job.objects.create(
created_date=prediction_job.created_date,
modified_date=prediction_job.modified_date,
error=prediction_job.error,
status=prediction_job.status,
type=prediction_job.type,
create_models=prediction_job.create_models,
case_id=prediction_job.case_id,
event_number=prediction_job.event_number,
gold_value=prediction_job.gold_value,
results=prediction_job.results,
parent_job=prediction_job.parent_job,
split=prediction_job.split,
encoding=prediction_job.encoding,
labelling=prediction_job.labelling,
clustering=prediction_job.clustering,
predictive_model=prediction_job.predictive_model,
evaluation=prediction_job.evaluation,
hyperparameter_optimizer=prediction_job.
hyperparameter_optimizer,
incremental_train=prediction_job.incremental_train)
new_replay_prediction_job.split = Split.objects.filter(
pk=replay_prediction_job.split.id)[0]
new_replay_prediction_job.type = JobTypes.REPLAY_PREDICT.value
new_replay_prediction_job.parent_job = replay_prediction_job.parent_job
new_replay_prediction_job.status = JobStatuses.CREATED.value
replay_prediction_task(new_replay_prediction_job, prediction_job,
log)
return
result_dict, events_for_trace = replay_prediction_calculate(
replay_prediction_job, log)
replay_prediction_job.results = dict(result_dict)
replay_prediction_job.event_number = dict(events_for_trace)
replay_prediction_job.status = JobStatuses.COMPLETED.value
replay_prediction_job.error = ''
except Exception as e:
logger.error(e)
replay_prediction_job.status = JobStatuses.ERROR.value
replay_prediction_job.error = str(e.__repr__())
raise e
finally:
replay_prediction_job.save()
publish(replay_prediction_job)
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
