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 = SomTrainJob(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 = SomTrainJob(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 = SomTrainJob(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 = SomTrainJob(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 = SomTrainJob(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 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 = SomTrainJob(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 test_train_command(self):
"""Test case for validating that when we train a model and add it to task queue that it will run."""
mgr = Pipeline()
config = Configuration()
config.STORAGE_DATASOURCE = "local"
config.STORAGE_DATASINK = "stdout"
config.LS_INPUT_PATH = "validation_data/Hadoop_2k.json"
storage_adapter = SomStorageAdapter(config=config,
feedback_strategy=None)
model_adapter = SomModelAdapter(storage_adapter)
tc = SomTrainJob(node_map=2, model_adapter=model_adapter)
mgr.add_steps(tc)
self.assertEqual(len(mgr), TASKS_IN_QUEUE)
self.assertNotEqual(mgr.count, TASKS_IN_QUEUE)
mgr.execute_steps()
self.assertEqual(mgr.count, TASKS_IN_QUEUE)
mgr.clear()