def test_end2endtraining(config):
"""Test anomaly detection training on public dataset."""
storage_adapter = SomStorageAdapter(config=config, feedback_strategy=None)
model_adapter = SomModelAdapter(storage_adapter=storage_adapter)
tc = SomTrainCommand(node_map=2, model_adapter=model_adapter)
result, dist = tc.execute()
assert result == 0
def test_model_shape(config):
"""Test that the trained model size is expected based on given parameters."""
storage_adapter = SomStorageAdapter(config=config, feedback_strategy=None)
model_adapter = SomModelAdapter(storage_adapter=storage_adapter)
tc = SomTrainCommand(node_map=2, model_adapter=model_adapter)
result, dist = tc.execute()
assert model_adapter.model.model.shape[0:2] == (2, 2)
def test_output_length(config):
"""Test that correct number of outputs are generated with Hadoop_2k.json."""
storage_adapter = SomStorageAdapter(config=config, feedback_strategy=None)
model_adapter = SomModelAdapter(storage_adapter=storage_adapter)
tc = SomTrainCommand(node_map=2, model_adapter=model_adapter)
result, dist = tc.execute()
assert len(dist) == 2000
def test_output_values(config):
"""Test that all distance values in training set are less than or equal to 1 on Hadoop_2k.json."""
storage_adapter = SomStorageAdapter(config=config, feedback_strategy=None)
model_adapter = SomModelAdapter(storage_adapter=storage_adapter)
tc = SomTrainCommand(node_map=2, model_adapter=model_adapter)
result, dist = tc.execute()
assert sum(dist) <= 2000
def test_vocab_length(config):
"""Check length of processed vocab on on Hadoop_2k.json."""
storage_adapter = SomStorageAdapter(config=config, feedback_strategy=None)
model_adapter = SomModelAdapter(storage_adapter=storage_adapter)
tc = SomTrainCommand(node_map=2, model_adapter=model_adapter)
result, dist = tc.execute()
assert len(model_adapter.w2v_model.model["message"].wv.vocab) == 141
def test_loss_value(config):
"""Check the loss value is not greater then during testing."""
storage_adapter = SomStorageAdapter(config=config, feedback_strategy=None)
model_adapter = SomModelAdapter(storage_adapter=storage_adapter)
tc = SomTrainCommand(node_map=2, model_adapter=model_adapter)
result, dist = tc.execute()
print(model_adapter.w2v_model.model["message"].get_latest_training_loss())
tl = model_adapter.w2v_model.model["message"].get_latest_training_loss()
assert tl < 320000.0
def get_score(config, node_map, feedback):
"""Simple utility function for injecting custom mock function into Detector."""
feedback_strategy = FeedbackStrategy(config, fn=feedback)
storage_adapter = SomStorageAdapter(config=config,
feedback_strategy=feedback_strategy)
model_adapter = SomModelAdapter(storage_adapter=storage_adapter)
tc = SomTrainCommand(node_map=node_map, model_adapter=model_adapter)
success, dist = tc.execute()
freq_one = dist[-1]
return freq_one
def test_training_infer(config):
"""Test anomaly detection training on public dataset."""
model_adapter = SomModelAdapter(
SomStorageAdapter(config=config, feedback_strategy=None))
tc_train = SomTrainCommand(node_map=2,
model_adapter=model_adapter,
recreate_model=True)
result, dist = tc_train.execute()
assert result == 0
model_adapter = SomModelAdapter(
SomStorageAdapter(config=config, feedback_strategy=None))
tc_infer = SomInferCommand(model_adapter=model_adapter, sleep=False)
result = tc_infer.execute()
assert result == 0
def train(self, node_map=24):
"""Run training of model and provides size of map.
:param node_map: by default the node_map is 24 and is custom field for SOM model.
:return: None
"""
train = SomTrainCommand(node_map=node_map,
model_adapter=self.__model_adapter)
self.tasks.add_steps(train)
self.start_job()
def run(self, single_run=False):
"""Abstraction around model adapter run method."""
break_out = False
train = SomTrainCommand(model_adapter=self.__model_adapter)
infer = SomInferCommand(model_adapter=self.__model_adapter)
self.mgr.add_steps(train)
self.mgr.add_steps(infer)
while break_out is False:
self.mgr.execute_steps()
print("log::facade::run")
time.sleep(5)
break_out = single_run
def test_log_similarity(config):
"""Check that two words have consistent similar logs after training."""
storage_adapter = SomStorageAdapter(config=config, feedback_strategy=None)
model_adapter = SomModelAdapter(storage_adapter=storage_adapter)
tc = SomTrainCommand(node_map=2, model_adapter=model_adapter)
result, dist = tc.execute()
log_1 = 'INFOmainorgapachehadoopmapreducevappMRAppMasterExecutingwithtokens'
answer_1 = 'INFOmainorgapachehadoopmapreducevappMRAppMasterCreatedMRAppMasterforapplicationappattempt'
match_1 = [
model_adapter.w2v_model.model["message"].wv.most_similar(log_1)[i][0]
for i in range(3)
]
assert answer_1 in match_1
log_2 = 'ERRORRMCommunicatorAllocatororgapachehadoopmapreducevapprmRMContainerAllocatorERRORINCONTACTINGRM'
answer_2 = 'WARNLeaseRenewermsrabimsrasaorgapachehadoophdfsLeaseRenewerFailedtorenewleaseforDFSClient' \
'NONMAPREDUCEforsecondsWillretryshortly'
match_2 = [
model_adapter.w2v_model.model["message"].wv.most_similar(log_2)[i][0]
for i in range(3)
]
print(match_2[0])
assert answer_2 in match_2
def run(self, single_run=False):
"""Run train and inference and main event loop.
:param single_run: if this is set to TRUE then we exit loop after first iteration.
:return: None
"""
exit = False
while exit is False:
try:
train = SomTrainCommand(model_adapter=self.__model_adapter)
infer = SomInferCommand(model_adapter=self.__model_adapter)
self.tasks.add_steps(train)
self.tasks.add_steps(infer)
self.start_job()
logging.info("Job ran succesfully")
except EmptyDataSetException as e:
logging.debug(e)
finally:
time.sleep(5)
exit = single_run
def train(self, node_map=24):
"""Abstraction around model adapter train method."""
tc = SomTrainCommand(node_map=node_map,
model_adapter=self.__model_adapter)
self.mgr.add_steps(tc)
self.mgr.execute_steps()
