def test_lda(sagemaker_session):
with timeout(minutes=15):
data_path = os.path.join(DATA_DIR, 'lda')
data_filename = 'nips-train_1.pbr'
with open(os.path.join(data_path, data_filename), 'rb') as f:
all_records = read_records(f)
# all records must be same
feature_num = int(all_records[0].features['values'].float32_tensor.shape[0])
lda = LDA(role='SageMakerRole', train_instance_type='ml.c4.xlarge', num_topics=10,
sagemaker_session=sagemaker_session, base_job_name='test-lda')
record_set = prepare_record_set_from_local_files(data_path, lda.data_location,
len(all_records), feature_num, sagemaker_session)
lda.fit(record_set, 100)
endpoint_name = name_from_base('lda')
with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
model = LDAModel(lda.model_data, role='SageMakerRole', sagemaker_session=sagemaker_session)
predictor = model.deploy(1, 'ml.c4.xlarge', endpoint_name=endpoint_name)
predict_input = np.random.rand(1, feature_num)
result = predictor.predict(predict_input)
assert len(result) == 1
for record in result:
assert record.label["topic_mixture"] is not None
def test_tuning_lda(sagemaker_session, cpu_instance_type):
with timeout(minutes=TUNING_DEFAULT_TIMEOUT_MINUTES):
data_path = os.path.join(DATA_DIR, "lda")
data_filename = "nips-train_1.pbr"
with open(os.path.join(data_path, data_filename), "rb") as f:
all_records = read_records(f)
# all records must be same
feature_num = int(
all_records[0].features["values"].float32_tensor.shape[0])
lda = LDA(
role="SageMakerRole",
instance_type=cpu_instance_type,
num_topics=10,
sagemaker_session=sagemaker_session,
)
record_set = prepare_record_set_from_local_files(
data_path, lda.data_location, len(all_records), feature_num,
sagemaker_session)
test_record_set = prepare_record_set_from_local_files(
data_path, lda.data_location, len(all_records), feature_num,
sagemaker_session)
test_record_set.channel = "test"
# specify which hp you want to optimize over
hyperparameter_ranges = {
"alpha0": ContinuousParameter(1, 10),
"num_topics": IntegerParameter(1, 2),
}
objective_metric_name = "test:pwll"
tuner = HyperparameterTuner(
estimator=lda,
objective_metric_name=objective_metric_name,
hyperparameter_ranges=hyperparameter_ranges,
objective_type="Maximize",
max_jobs=2,
max_parallel_jobs=2,
early_stopping_type="Auto",
)
tuning_job_name = unique_name_from_base("test-lda", max_length=32)
print("Started hyperparameter tuning job with name:" + tuning_job_name)
tuner.fit([record_set, test_record_set],
mini_batch_size=1,
job_name=tuning_job_name)
attached_tuner = HyperparameterTuner.attach(
tuning_job_name, sagemaker_session=sagemaker_session)
assert attached_tuner.early_stopping_type == "Auto"
assert attached_tuner.estimator.alpha0 == 1.0
assert attached_tuner.estimator.num_topics == 1
best_training_job = attached_tuner.best_training_job()
with timeout_and_delete_endpoint_by_name(best_training_job,
sagemaker_session):
predictor = tuner.deploy(1, cpu_instance_type)
predict_input = np.random.rand(1, feature_num)
result = predictor.predict(predict_input)
assert len(result) == 1
for record in result:
assert record.label["topic_mixture"] is not None
def test_tuning_lda(sagemaker_session):
with timeout(minutes=TUNING_DEFAULT_TIMEOUT_MINUTES):
data_path = os.path.join(DATA_DIR, 'lda')
data_filename = 'nips-train_1.pbr'
with open(os.path.join(data_path, data_filename), 'rb') as f:
all_records = read_records(f)
# all records must be same
feature_num = int(
all_records[0].features['values'].float32_tensor.shape[0])
lda = LDA(role='SageMakerRole',
train_instance_type='ml.c4.xlarge',
num_topics=10,
sagemaker_session=sagemaker_session)
record_set = prepare_record_set_from_local_files(
data_path, lda.data_location, len(all_records), feature_num,
sagemaker_session)
test_record_set = prepare_record_set_from_local_files(
data_path, lda.data_location, len(all_records), feature_num,
sagemaker_session)
test_record_set.channel = 'test'
# specify which hp you want to optimize over
hyperparameter_ranges = {
'alpha0': ContinuousParameter(1, 10),
'num_topics': IntegerParameter(1, 2)
}
objective_metric_name = 'test:pwll'
tuner = HyperparameterTuner(
estimator=lda,
objective_metric_name=objective_metric_name,
hyperparameter_ranges=hyperparameter_ranges,
objective_type='Maximize',
max_jobs=2,
max_parallel_jobs=2,
early_stopping_type='Auto')
tuning_job_name = unique_name_from_base('test-lda', max_length=32)
tuner.fit([record_set, test_record_set],
mini_batch_size=1,
job_name=tuning_job_name)
latest_tuning_job_name = tuner.latest_tuning_job.name
print('Started hyperparameter tuning job with name:' +
latest_tuning_job_name)
time.sleep(15)
tuner.wait()
desc = tuner.latest_tuning_job.sagemaker_session.sagemaker_client \
.describe_hyper_parameter_tuning_job(HyperParameterTuningJobName=latest_tuning_job_name)
assert desc['HyperParameterTuningJobConfig'][
'TrainingJobEarlyStoppingType'] == 'Auto'
best_training_job = tuner.best_training_job()
with timeout_and_delete_endpoint_by_name(best_training_job,
sagemaker_session):
predictor = tuner.deploy(1, 'ml.c4.xlarge')
predict_input = np.random.rand(1, feature_num)
result = predictor.predict(predict_input)
assert len(result) == 1
for record in result:
assert record.label['topic_mixture'] is not None