def test_kmeans_airflow_config_uploads_data_source_to_s3(
sagemaker_session, cpu_instance_type):
with timeout(seconds=AIRFLOW_CONFIG_TIMEOUT_IN_SECONDS):
kmeans = KMeans(
role=ROLE,
instance_count=SINGLE_INSTANCE_COUNT,
instance_type=cpu_instance_type,
k=10,
sagemaker_session=sagemaker_session,
)
kmeans.init_method = "random"
kmeans.max_iterations = 1
kmeans.tol = 1
kmeans.num_trials = 1
kmeans.local_init_method = "kmeans++"
kmeans.half_life_time_size = 1
kmeans.epochs = 1
kmeans.center_factor = 1
kmeans.eval_metrics = ["ssd", "msd"]
records = kmeans.record_set(datasets.one_p_mnist()[0][:100])
training_config = _build_airflow_workflow(
estimator=kmeans, instance_type=cpu_instance_type, inputs=records)
_assert_that_s3_url_contains_data(
sagemaker_session,
training_config["InputDataConfig"][0]["DataSource"]["S3DataSource"]
["S3Uri"],
)
def test_transform_byo_estimator(sagemaker_session, cpu_instance_type):
data_path = os.path.join(DATA_DIR, "one_p_mnist")
pickle_args = {} if sys.version_info.major == 2 else {"encoding": "latin1"}
tags = [{"Key": "some-tag", "Value": "value-for-tag"}]
# Load the data into memory as numpy arrays
train_set_path = os.path.join(data_path, "mnist.pkl.gz")
with gzip.open(train_set_path, "rb") as f:
train_set, _, _ = pickle.load(f, **pickle_args)
kmeans = KMeans(
role="SageMakerRole",
train_instance_count=1,
train_instance_type=cpu_instance_type,
k=10,
sagemaker_session=sagemaker_session,
output_path="s3://{}/".format(sagemaker_session.default_bucket()),
)
# set kmeans specific hp
kmeans.init_method = "random"
kmeans.max_iterators = 1
kmeans.tol = 1
kmeans.num_trials = 1
kmeans.local_init_method = "kmeans++"
kmeans.half_life_time_size = 1
kmeans.epochs = 1
records = kmeans.record_set(train_set[0][:100])
job_name = unique_name_from_base("test-kmeans-attach")
with timeout(minutes=TRAINING_DEFAULT_TIMEOUT_MINUTES):
kmeans.fit(records, job_name=job_name)
estimator = Estimator.attach(training_job_name=job_name, sagemaker_session=sagemaker_session)
estimator._enable_network_isolation = True
transform_input_path = os.path.join(data_path, "transform_input.csv")
transform_input_key_prefix = "integ-test-data/one_p_mnist/transform"
transform_input = kmeans.sagemaker_session.upload_data(
path=transform_input_path, key_prefix=transform_input_key_prefix
)
transformer = estimator.transformer(1, cpu_instance_type, tags=tags)
transformer.transform(transform_input, content_type="text/csv")
with timeout_and_delete_model_with_transformer(
transformer, sagemaker_session, minutes=TRANSFORM_DEFAULT_TIMEOUT_MINUTES
):
transformer.wait()
model_desc = sagemaker_session.sagemaker_client.describe_model(
ModelName=transformer.model_name
)
assert model_desc["EnableNetworkIsolation"]
model_tags = sagemaker_session.sagemaker_client.list_tags(
ResourceArn=model_desc["ModelArn"]
)["Tags"]
assert tags == model_tags
def test_kmeans(sagemaker_session):
with timeout(minutes=15):
data_path = os.path.join(DATA_DIR, 'one_p_mnist', 'mnist.pkl.gz')
pickle_args = {} if sys.version_info.major == 2 else {'encoding': 'latin1'}
# Load the data into memory as numpy arrays
with gzip.open(data_path, 'rb') as f:
train_set, _, _ = pickle.load(f, **pickle_args)
kmeans = KMeans(role='SageMakerRole', train_instance_count=1,
train_instance_type='ml.c4.xlarge',
k=10, sagemaker_session=sagemaker_session, base_job_name='test-kmeans')
kmeans.init_method = 'random'
kmeans.max_iterators = 1
kmeans.tol = 1
kmeans.num_trials = 1
kmeans.local_init_method = 'kmeans++'
kmeans.half_life_time_size = 1
kmeans.epochs = 1
kmeans.center_factor = 1
kmeans.fit(kmeans.record_set(train_set[0][:100]))
endpoint_name = name_from_base('kmeans')
with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
model = KMeansModel(kmeans.model_data, role='SageMakerRole', sagemaker_session=sagemaker_session)
predictor = model.deploy(1, 'ml.c4.xlarge', endpoint_name=endpoint_name)
result = predictor.predict(train_set[0][:10])
assert len(result) == 10
for record in result:
assert record.label["closest_cluster"] is not None
assert record.label["distance_to_cluster"] is not None
def test_kmeans(sagemaker_session):
job_name = unique_name_from_base("kmeans")
with timeout(minutes=TRAINING_DEFAULT_TIMEOUT_MINUTES):
data_path = os.path.join(DATA_DIR, "one_p_mnist", "mnist.pkl.gz")
pickle_args = {} if sys.version_info.major == 2 else {
"encoding": "latin1"
}
# Load the data into memory as numpy arrays
with gzip.open(data_path, "rb") as f:
train_set, _, _ = pickle.load(f, **pickle_args)
kmeans = KMeans(
role="SageMakerRole",
train_instance_count=1,
train_instance_type="ml.c4.xlarge",
k=10,
sagemaker_session=sagemaker_session,
)
kmeans.init_method = "random"
kmeans.max_iterations = 1
kmeans.tol = 1
kmeans.num_trials = 1
kmeans.local_init_method = "kmeans++"
kmeans.half_life_time_size = 1
kmeans.epochs = 1
kmeans.center_factor = 1
assert kmeans.hyperparameters() == dict(
init_method=kmeans.init_method,
local_lloyd_max_iter=str(kmeans.max_iterations),
local_lloyd_tol=str(kmeans.tol),
local_lloyd_num_trials=str(kmeans.num_trials),
local_lloyd_init_method=kmeans.local_init_method,
half_life_time_size=str(kmeans.half_life_time_size),
epochs=str(kmeans.epochs),
extra_center_factor=str(kmeans.center_factor),
k=str(kmeans.k),
force_dense="True",
)
kmeans.fit(kmeans.record_set(train_set[0][:100]), job_name=job_name)
with timeout_and_delete_endpoint_by_name(job_name, sagemaker_session):
model = KMeansModel(kmeans.model_data,
role="SageMakerRole",
sagemaker_session=sagemaker_session)
predictor = model.deploy(1, "ml.c4.xlarge", endpoint_name=job_name)
result = predictor.predict(train_set[0][:10])
assert len(result) == 10
for record in result:
assert record.label["closest_cluster"] is not None
assert record.label["distance_to_cluster"] is not None
predictor.delete_model()
with pytest.raises(Exception) as exception:
sagemaker_session.sagemaker_client.describe_model(ModelName=model.name)
assert "Could not find model" in str(exception.value)
def test_async_kmeans(sagemaker_session, cpu_instance_type):
job_name = unique_name_from_base("kmeans")
with timeout(minutes=5):
data_path = os.path.join(DATA_DIR, "one_p_mnist", "mnist.pkl.gz")
pickle_args = {} if sys.version_info.major == 2 else {"encoding": "latin1"}
# Load the data into memory as numpy arrays
with gzip.open(data_path, "rb") as f:
train_set, _, _ = pickle.load(f, **pickle_args)
kmeans = KMeans(
role="SageMakerRole",
train_instance_count=1,
train_instance_type=cpu_instance_type,
k=10,
sagemaker_session=sagemaker_session,
)
kmeans.init_method = "random"
kmeans.max_iterations = 1
kmeans.tol = 1
kmeans.num_trials = 1
kmeans.local_init_method = "kmeans++"
kmeans.half_life_time_size = 1
kmeans.epochs = 1
kmeans.center_factor = 1
assert kmeans.hyperparameters() == dict(
init_method=kmeans.init_method,
local_lloyd_max_iter=str(kmeans.max_iterations),
local_lloyd_tol=str(kmeans.tol),
local_lloyd_num_trials=str(kmeans.num_trials),
local_lloyd_init_method=kmeans.local_init_method,
half_life_time_size=str(kmeans.half_life_time_size),
epochs=str(kmeans.epochs),
extra_center_factor=str(kmeans.center_factor),
k=str(kmeans.k),
force_dense="True",
)
kmeans.fit(kmeans.record_set(train_set[0][:100]), wait=False, job_name=job_name)
print("Detached from training job. Will re-attach in 20 seconds")
time.sleep(20)
print("attaching now...")
with timeout_and_delete_endpoint_by_name(job_name, sagemaker_session):
estimator = KMeans.attach(training_job_name=job_name, sagemaker_session=sagemaker_session)
model = KMeansModel(
estimator.model_data, role="SageMakerRole", sagemaker_session=sagemaker_session
)
predictor = model.deploy(1, cpu_instance_type, endpoint_name=job_name)
result = predictor.predict(train_set[0][:10])
assert len(result) == 10
for record in result:
assert record.label["closest_cluster"] is not None
assert record.label["distance_to_cluster"] is not None
def test_async_kmeans():
training_job_name = ""
endpoint_name = name_from_base('kmeans')
with timeout(minutes=5):
sagemaker_session = sagemaker.Session(boto_session=boto3.Session(
region_name=REGION))
data_path = os.path.join(DATA_DIR, 'one_p_mnist', 'mnist.pkl.gz')
pickle_args = {} if sys.version_info.major == 2 else {
'encoding': 'latin1'
}
# Load the data into memory as numpy arrays
with gzip.open(data_path, 'rb') as f:
train_set, _, _ = pickle.load(f, **pickle_args)
kmeans = KMeans(role='SageMakerRole',
train_instance_count=1,
train_instance_type='ml.c4.xlarge',
k=10,
sagemaker_session=sagemaker_session,
base_job_name='test-kmeans')
kmeans.init_method = 'random'
kmeans.max_iterators = 1
kmeans.tol = 1
kmeans.num_trials = 1
kmeans.local_init_method = 'kmeans++'
kmeans.half_life_time_size = 1
kmeans.epochs = 1
kmeans.center_factor = 1
kmeans.fit(kmeans.record_set(train_set[0][:100]), wait=False)
training_job_name = kmeans.latest_training_job.name
print("Detached from training job. Will re-attach in 20 seconds")
time.sleep(20)
print("attaching now...")
with timeout_and_delete_endpoint_by_name(endpoint_name,
sagemaker_session,
minutes=35):
estimator = KMeans.attach(training_job_name=training_job_name,
sagemaker_session=sagemaker_session)
model = KMeansModel(estimator.model_data,
role='SageMakerRole',
sagemaker_session=sagemaker_session)
predictor = model.deploy(1,
'ml.c4.xlarge',
endpoint_name=endpoint_name)
result = predictor.predict(train_set[0][:10])
assert len(result) == 10
for record in result:
assert record.label["closest_cluster"] is not None
assert record.label["distance_to_cluster"] is not None
def test_kmeans_serverless_inference(sagemaker_session, cpu_instance_type,
training_set):
job_name = unique_name_from_base("kmeans-serverless")
with timeout(minutes=TRAINING_DEFAULT_TIMEOUT_MINUTES):
kmeans = KMeans(
role="SageMakerRole",
instance_count=1,
instance_type=cpu_instance_type,
k=10,
sagemaker_session=sagemaker_session,
)
kmeans.init_method = "random"
kmeans.max_iterations = 1
kmeans.tol = 1
kmeans.num_trials = 1
kmeans.local_init_method = "kmeans++"
kmeans.half_life_time_size = 1
kmeans.epochs = 1
kmeans.center_factor = 1
kmeans.eval_metrics = ["ssd", "msd"]
assert kmeans.hyperparameters() == dict(
init_method=kmeans.init_method,
local_lloyd_max_iter=str(kmeans.max_iterations),
local_lloyd_tol=str(kmeans.tol),
local_lloyd_num_trials=str(kmeans.num_trials),
local_lloyd_init_method=kmeans.local_init_method,
half_life_time_size=str(kmeans.half_life_time_size),
epochs=str(kmeans.epochs),
extra_center_factor=str(kmeans.center_factor),
k=str(kmeans.k),
eval_metrics=json.dumps(kmeans.eval_metrics),
force_dense="True",
)
kmeans.fit(kmeans.record_set(training_set[0][:100]), job_name=job_name)
with timeout_and_delete_endpoint_by_name(job_name, sagemaker_session):
model = KMeansModel(kmeans.model_data,
role="SageMakerRole",
sagemaker_session=sagemaker_session)
predictor = model.deploy(
serverless_inference_config=ServerlessInferenceConfig(),
endpoint_name=job_name)
result = predictor.predict(training_set[0][:10])
assert len(result) == 10
for record in result:
assert record.label["closest_cluster"] is not None
assert record.label["distance_to_cluster"] is not None
predictor.delete_model()
with pytest.raises(Exception) as exception:
sagemaker_session.sagemaker_client.describe_model(
ModelName=model.name)
assert "Could not find model" in str(exception.value)
def test_async_kmeans(sagemaker_session, cpu_instance_type, training_set):
job_name = unique_name_from_base("kmeans")
with timeout(minutes=5):
kmeans = KMeans(
role="SageMakerRole",
instance_count=1,
instance_type=cpu_instance_type,
k=10,
sagemaker_session=sagemaker_session,
)
kmeans.init_method = "random"
kmeans.max_iterations = 1
kmeans.tol = 1
kmeans.num_trials = 1
kmeans.local_init_method = "kmeans++"
kmeans.half_life_time_size = 1
kmeans.epochs = 1
kmeans.center_factor = 1
assert kmeans.hyperparameters() == dict(
init_method=kmeans.init_method,
local_lloyd_max_iter=str(kmeans.max_iterations),
local_lloyd_tol=str(kmeans.tol),
local_lloyd_num_trials=str(kmeans.num_trials),
local_lloyd_init_method=kmeans.local_init_method,
half_life_time_size=str(kmeans.half_life_time_size),
epochs=str(kmeans.epochs),
extra_center_factor=str(kmeans.center_factor),
k=str(kmeans.k),
force_dense="True",
)
kmeans.fit(kmeans.record_set(training_set[0][:100]),
wait=False,
job_name=job_name)
print("Detached from training job. Will re-attach in 20 seconds")
time.sleep(20)
print("attaching now...")
with timeout_and_delete_endpoint_by_name(job_name, sagemaker_session):
estimator = KMeans.attach(training_job_name=job_name,
sagemaker_session=sagemaker_session)
model = KMeansModel(estimator.model_data,
role="SageMakerRole",
sagemaker_session=sagemaker_session)
predictor = model.deploy(1, cpu_instance_type, endpoint_name=job_name)
result = predictor.predict(training_set[0][:10])
assert len(result) == 10
for record in result:
assert record.label["closest_cluster"] is not None
assert record.label["distance_to_cluster"] is not None
def test_transform_byo_estimator(sagemaker_session):
data_path = os.path.join(DATA_DIR, 'one_p_mnist')
pickle_args = {} if sys.version_info.major == 2 else {'encoding': 'latin1'}
tags = [{'Key': 'some-tag', 'Value': 'value-for-tag'}]
# Load the data into memory as numpy arrays
train_set_path = os.path.join(data_path, 'mnist.pkl.gz')
with gzip.open(train_set_path, 'rb') as f:
train_set, _, _ = pickle.load(f, **pickle_args)
kmeans = KMeans(role='SageMakerRole',
train_instance_count=1,
train_instance_type='ml.c4.xlarge',
k=10,
sagemaker_session=sagemaker_session,
output_path='s3://{}/'.format(
sagemaker_session.default_bucket()))
# set kmeans specific hp
kmeans.init_method = 'random'
kmeans.max_iterators = 1
kmeans.tol = 1
kmeans.num_trials = 1
kmeans.local_init_method = 'kmeans++'
kmeans.half_life_time_size = 1
kmeans.epochs = 1
records = kmeans.record_set(train_set[0][:100])
job_name = unique_name_from_base('test-kmeans-attach')
with timeout(minutes=TRAINING_DEFAULT_TIMEOUT_MINUTES):
kmeans.fit(records, job_name=job_name)
transform_input_path = os.path.join(data_path, 'transform_input.csv')
transform_input_key_prefix = 'integ-test-data/one_p_mnist/transform'
transform_input = kmeans.sagemaker_session.upload_data(
path=transform_input_path, key_prefix=transform_input_key_prefix)
estimator = Estimator.attach(training_job_name=job_name,
sagemaker_session=sagemaker_session)
transformer = estimator.transformer(1, 'ml.m4.xlarge', tags=tags)
transformer.transform(transform_input, content_type='text/csv')
with timeout_and_delete_model_with_transformer(
transformer,
sagemaker_session,
minutes=TRANSFORM_DEFAULT_TIMEOUT_MINUTES):
transformer.wait()
model_desc = sagemaker_session.sagemaker_client.describe_model(
ModelName=transformer.model_name)
model_tags = sagemaker_session.sagemaker_client.list_tags(
ResourceArn=model_desc['ModelArn'])['Tags']
assert tags == model_tags
def test_async_kmeans(sagemaker_session):
training_job_name = ""
endpoint_name = name_from_base('kmeans')
with timeout(minutes=5):
data_path = os.path.join(DATA_DIR, 'one_p_mnist', 'mnist.pkl.gz')
pickle_args = {} if sys.version_info.major == 2 else {'encoding': 'latin1'}
# Load the data into memory as numpy arrays
with gzip.open(data_path, 'rb') as f:
train_set, _, _ = pickle.load(f, **pickle_args)
kmeans = KMeans(role='SageMakerRole', train_instance_count=1,
train_instance_type='ml.c4.xlarge',
k=10, sagemaker_session=sagemaker_session, base_job_name='test-kmeans')
kmeans.init_method = 'random'
kmeans.max_iterations = 1
kmeans.tol = 1
kmeans.num_trials = 1
kmeans.local_init_method = 'kmeans++'
kmeans.half_life_time_size = 1
kmeans.epochs = 1
kmeans.center_factor = 1
assert kmeans.hyperparameters() == dict(
init_method=kmeans.init_method,
local_lloyd_max_iter=str(kmeans.max_iterations),
local_lloyd_tol=str(kmeans.tol),
local_lloyd_num_trials=str(kmeans.num_trials),
local_lloyd_init_method=kmeans.local_init_method,
half_life_time_size=str(kmeans.half_life_time_size),
epochs=str(kmeans.epochs),
extra_center_factor=str(kmeans.center_factor),
k=str(kmeans.k),
force_dense='True',
)
kmeans.fit(kmeans.record_set(train_set[0][:100]), wait=False)
training_job_name = kmeans.latest_training_job.name
print("Detached from training job. Will re-attach in 20 seconds")
time.sleep(20)
print("attaching now...")
with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
estimator = KMeans.attach(training_job_name=training_job_name, sagemaker_session=sagemaker_session)
model = KMeansModel(estimator.model_data, role='SageMakerRole', sagemaker_session=sagemaker_session)
predictor = model.deploy(1, 'ml.c4.xlarge', endpoint_name=endpoint_name)
result = predictor.predict(train_set[0][:10])
assert len(result) == 10
for record in result:
assert record.label["closest_cluster"] is not None
assert record.label["distance_to_cluster"] is not None
def test_tuning_kmeans(sagemaker_session):
with timeout(minutes=20):
data_path = os.path.join(DATA_DIR, 'one_p_mnist', 'mnist.pkl.gz')
pickle_args = {} if sys.version_info.major == 2 else {'encoding': 'latin1'}
# Load the data into memory as numpy arrays
with gzip.open(data_path, 'rb') as f:
train_set, _, _ = pickle.load(f, **pickle_args)
kmeans = KMeans(role='SageMakerRole', train_instance_count=1,
train_instance_type='ml.c4.xlarge',
k=10, sagemaker_session=sagemaker_session, base_job_name='tk',
output_path='s3://{}/'.format(sagemaker_session.default_bucket()))
# set kmeans specific hp
kmeans.init_method = 'random'
kmeans.max_iterators = 1
kmeans.tol = 1
kmeans.num_trials = 1
kmeans.local_init_method = 'kmeans++'
kmeans.half_life_time_size = 1
kmeans.epochs = 1
records = kmeans.record_set(train_set[0][:100])
test_records = kmeans.record_set(train_set[0][:100], channel='test')
# specify which hp you want to optimize over
hyperparameter_ranges = {'extra_center_factor': IntegerParameter(1, 10),
'mini_batch_size': IntegerParameter(10, 100),
'epochs': IntegerParameter(1, 2),
'init_method': CategoricalParameter(['kmeans++', 'random'])}
objective_metric_name = 'test:msd'
tuner = HyperparameterTuner(estimator=kmeans, objective_metric_name=objective_metric_name,
hyperparameter_ranges=hyperparameter_ranges, objective_type='Minimize', max_jobs=2,
max_parallel_jobs=2)
tuner.fit([records, test_records])
print('Started hyperparameter tuning job with name:' + tuner.latest_tuning_job.name)
time.sleep(15)
tuner.wait()
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')
result = predictor.predict(train_set[0][:10])
assert len(result) == 10
for record in result:
assert record.label['closest_cluster'] is not None
assert record.label['distance_to_cluster'] is not None
def test_tuning_kmeans(sagemaker_session):
with timeout(minutes=TUNING_DEFAULT_TIMEOUT_MINUTES):
data_path = os.path.join(DATA_DIR, 'one_p_mnist', 'mnist.pkl.gz')
pickle_args = {} if sys.version_info.major == 2 else {'encoding': 'latin1'}
# Load the data into memory as numpy arrays
with gzip.open(data_path, 'rb') as f:
train_set, _, _ = pickle.load(f, **pickle_args)
kmeans = KMeans(role='SageMakerRole', train_instance_count=1,
train_instance_type='ml.c4.xlarge',
k=10, sagemaker_session=sagemaker_session, base_job_name='tk',
output_path='s3://{}/'.format(sagemaker_session.default_bucket()))
# set kmeans specific hp
kmeans.init_method = 'random'
kmeans.max_iterators = 1
kmeans.tol = 1
kmeans.num_trials = 1
kmeans.local_init_method = 'kmeans++'
kmeans.half_life_time_size = 1
kmeans.epochs = 1
records = kmeans.record_set(train_set[0][:100])
test_records = kmeans.record_set(train_set[0][:100], channel='test')
# specify which hp you want to optimize over
hyperparameter_ranges = {'extra_center_factor': IntegerParameter(1, 10),
'mini_batch_size': IntegerParameter(10, 100),
'epochs': IntegerParameter(1, 2),
'init_method': CategoricalParameter(['kmeans++', 'random'])}
objective_metric_name = 'test:msd'
tuner = HyperparameterTuner(estimator=kmeans, objective_metric_name=objective_metric_name,
hyperparameter_ranges=hyperparameter_ranges, objective_type='Minimize', max_jobs=2,
max_parallel_jobs=2)
tuner.fit([records, test_records])
print('Started hyperparameter tuning job with name:' + tuner.latest_tuning_job.name)
time.sleep(15)
tuner.wait()
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')
result = predictor.predict(train_set[0][:10])
assert len(result) == 10
for record in result:
assert record.label['closest_cluster'] is not None
assert record.label['distance_to_cluster'] is not None
def test_attach_transform_kmeans(sagemaker_session, cpu_instance_type):
data_path = os.path.join(DATA_DIR, "one_p_mnist")
pickle_args = {} if sys.version_info.major == 2 else {"encoding": "latin1"}
# Load the data into memory as numpy arrays
train_set_path = os.path.join(data_path, "mnist.pkl.gz")
with gzip.open(train_set_path, "rb") as f:
train_set, _, _ = pickle.load(f, **pickle_args)
kmeans = KMeans(
role="SageMakerRole",
train_instance_count=1,
train_instance_type=cpu_instance_type,
k=10,
sagemaker_session=sagemaker_session,
output_path="s3://{}/".format(sagemaker_session.default_bucket()),
)
# set kmeans specific hp
kmeans.init_method = "random"
kmeans.max_iterators = 1
kmeans.tol = 1
kmeans.num_trials = 1
kmeans.local_init_method = "kmeans++"
kmeans.half_life_time_size = 1
kmeans.epochs = 1
records = kmeans.record_set(train_set[0][:100])
job_name = unique_name_from_base("test-kmeans-attach")
with timeout(minutes=TRAINING_DEFAULT_TIMEOUT_MINUTES):
kmeans.fit(records, job_name=job_name)
transform_input_path = os.path.join(data_path, "transform_input.csv")
transform_input_key_prefix = "integ-test-data/one_p_mnist/transform"
transform_input = kmeans.sagemaker_session.upload_data(
path=transform_input_path, key_prefix=transform_input_key_prefix)
transformer = _create_transformer_and_transform_job(
kmeans, transform_input, cpu_instance_type)
attached_transformer = Transformer.attach(
transformer.latest_transform_job.name,
sagemaker_session=sagemaker_session)
with timeout_and_delete_model_with_transformer(
transformer,
sagemaker_session,
minutes=TRANSFORM_DEFAULT_TIMEOUT_MINUTES):
attached_transformer.wait()
def kmeans_estimator(sagemaker_session):
kmeans = KMeans(role='SageMakerRole', train_instance_count=1,
train_instance_type='ml.c4.xlarge',
k=10, sagemaker_session=sagemaker_session, base_job_name='tk',
output_path='s3://{}/'.format(sagemaker_session.default_bucket()))
# set kmeans specific hp
kmeans.init_method = 'random'
kmeans.max_iterators = 1
kmeans.tol = 1
kmeans.num_trials = 1
kmeans.local_init_method = 'kmeans++'
kmeans.half_life_time_size = 1
kmeans.epochs = 1
return kmeans
def test_attach_transform_kmeans(sagemaker_session):
data_path = os.path.join(DATA_DIR, 'one_p_mnist')
pickle_args = {} if sys.version_info.major == 2 else {'encoding': 'latin1'}
# Load the data into memory as numpy arrays
train_set_path = os.path.join(data_path, 'mnist.pkl.gz')
with gzip.open(train_set_path, 'rb') as f:
train_set, _, _ = pickle.load(f, **pickle_args)
kmeans = KMeans(role='SageMakerRole',
train_instance_count=1,
train_instance_type='ml.c4.xlarge',
k=10,
sagemaker_session=sagemaker_session,
output_path='s3://{}/'.format(
sagemaker_session.default_bucket()))
# set kmeans specific hp
kmeans.init_method = 'random'
kmeans.max_iterators = 1
kmeans.tol = 1
kmeans.num_trials = 1
kmeans.local_init_method = 'kmeans++'
kmeans.half_life_time_size = 1
kmeans.epochs = 1
records = kmeans.record_set(train_set[0][:100])
with timeout(minutes=TRAINING_DEFAULT_TIMEOUT_MINUTES):
kmeans.fit(records)
transform_input_path = os.path.join(data_path, 'transform_input.csv')
transform_input_key_prefix = 'integ-test-data/one_p_mnist/transform'
transform_input = kmeans.sagemaker_session.upload_data(
path=transform_input_path, key_prefix=transform_input_key_prefix)
transformer = _create_transformer_and_transform_job(
kmeans, transform_input)
attached_transformer = Transformer.attach(
transformer.latest_transform_job.name,
sagemaker_session=sagemaker_session)
with timeout_and_delete_model_with_transformer(
transformer,
sagemaker_session,
minutes=TRANSFORM_DEFAULT_TIMEOUT_MINUTES):
attached_transformer.wait()
def kmeans_estimator(sagemaker_session, cpu_instance_type):
kmeans = KMeans(
role="SageMakerRole",
instance_count=1,
instance_type=cpu_instance_type,
k=10,
sagemaker_session=sagemaker_session,
output_path="s3://{}/".format(sagemaker_session.default_bucket()),
)
# set kmeans specific hp
kmeans.init_method = "random"
kmeans.max_iterators = 1
kmeans.tol = 1
kmeans.num_trials = 1
kmeans.local_init_method = "kmeans++"
kmeans.half_life_time_size = 1
kmeans.epochs = 1
return kmeans
def test_attach_transform_kmeans(sagemaker_session, cpu_instance_type):
kmeans = KMeans(
role="SageMakerRole",
instance_count=1,
instance_type=cpu_instance_type,
k=10,
sagemaker_session=sagemaker_session,
output_path="s3://{}/".format(sagemaker_session.default_bucket()),
)
# set kmeans specific hp
kmeans.init_method = "random"
kmeans.max_iterators = 1
kmeans.tol = 1
kmeans.num_trials = 1
kmeans.local_init_method = "kmeans++"
kmeans.half_life_time_size = 1
kmeans.epochs = 1
records = kmeans.record_set(datasets.one_p_mnist()[0][:100])
job_name = unique_name_from_base("test-kmeans-attach")
with timeout(minutes=TRAINING_DEFAULT_TIMEOUT_MINUTES):
kmeans.fit(records, job_name=job_name)
transform_input_path = os.path.join(DATA_DIR, "one_p_mnist",
"transform_input.csv")
transform_input_key_prefix = "integ-test-data/one_p_mnist/transform"
transform_input = kmeans.sagemaker_session.upload_data(
path=transform_input_path, key_prefix=transform_input_key_prefix)
transformer = _create_transformer_and_transform_job(
kmeans, transform_input, cpu_instance_type)
attached_transformer = Transformer.attach(
transformer.latest_transform_job.name,
sagemaker_session=sagemaker_session)
with timeout_and_delete_model_with_transformer(
transformer,
sagemaker_session,
minutes=TRANSFORM_DEFAULT_TIMEOUT_MINUTES):
attached_transformer.wait()
def test_kmeans_airflow_config_uploads_data_source_to_s3(
sagemaker_session, cpu_instance_type):
with timeout(seconds=AIRFLOW_CONFIG_TIMEOUT_IN_SECONDS):
data_path = os.path.join(DATA_DIR, "one_p_mnist", "mnist.pkl.gz")
pickle_args = {} if sys.version_info.major == 2 else {
"encoding": "latin1"
}
# Load the data into memory as numpy arrays
with gzip.open(data_path, "rb") as f:
train_set, _, _ = pickle.load(f, **pickle_args)
kmeans = KMeans(
role=ROLE,
train_instance_count=SINGLE_INSTANCE_COUNT,
train_instance_type=cpu_instance_type,
k=10,
sagemaker_session=sagemaker_session,
)
kmeans.init_method = "random"
kmeans.max_iterations = 1
kmeans.tol = 1
kmeans.num_trials = 1
kmeans.local_init_method = "kmeans++"
kmeans.half_life_time_size = 1
kmeans.epochs = 1
kmeans.center_factor = 1
kmeans.eval_metrics = ["ssd", "msd"]
records = kmeans.record_set(train_set[0][:100])
training_config = _build_airflow_workflow(
estimator=kmeans, instance_type=cpu_instance_type, inputs=records)
_assert_that_s3_url_contains_data(
sagemaker_session,
training_config["InputDataConfig"][0]["DataSource"]["S3DataSource"]
["S3Uri"],
)
def test_attach_transform_kmeans(sagemaker_session):
data_path = os.path.join(DATA_DIR, 'one_p_mnist')
pickle_args = {} if sys.version_info.major == 2 else {'encoding': 'latin1'}
# Load the data into memory as numpy arrays
train_set_path = os.path.join(data_path, 'mnist.pkl.gz')
with gzip.open(train_set_path, 'rb') as f:
train_set, _, _ = pickle.load(f, **pickle_args)
kmeans = KMeans(role='SageMakerRole', train_instance_count=1,
train_instance_type='ml.c4.xlarge', k=10, sagemaker_session=sagemaker_session,
output_path='s3://{}/'.format(sagemaker_session.default_bucket()))
# set kmeans specific hp
kmeans.init_method = 'random'
kmeans.max_iterators = 1
kmeans.tol = 1
kmeans.num_trials = 1
kmeans.local_init_method = 'kmeans++'
kmeans.half_life_time_size = 1
kmeans.epochs = 1
records = kmeans.record_set(train_set[0][:100])
with timeout(minutes=TRAINING_DEFAULT_TIMEOUT_MINUTES):
kmeans.fit(records)
transform_input_path = os.path.join(data_path, 'transform_input.csv')
transform_input_key_prefix = 'integ-test-data/one_p_mnist/transform'
transform_input = kmeans.sagemaker_session.upload_data(path=transform_input_path,
key_prefix=transform_input_key_prefix)
transformer = _create_transformer_and_transform_job(kmeans, transform_input)
attached_transformer = Transformer.attach(transformer.latest_transform_job.name,
sagemaker_session=sagemaker_session)
attached_transformer.wait()
