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_pca_airflow_config_uploads_data_source_to_s3(sagemaker_session,
cpu_instance_type):
with timeout(seconds=AIRFLOW_CONFIG_TIMEOUT_IN_SECONDS):
pca = PCA(
role=ROLE,
instance_count=SINGLE_INSTANCE_COUNT,
instance_type=cpu_instance_type,
num_components=48,
sagemaker_session=sagemaker_session,
)
pca.algorithm_mode = "randomized"
pca.subtract_mean = True
pca.extra_components = 5
records = pca.record_set(datasets.one_p_mnist()[0][:100])
training_config = _build_airflow_workflow(
estimator=pca, instance_type=cpu_instance_type, inputs=records)
_assert_that_s3_url_contains_data(
sagemaker_session,
training_config["InputDataConfig"][0]["DataSource"]["S3DataSource"]
["S3Uri"],
)
def test_knn_airflow_config_uploads_data_source_to_s3(sagemaker_session,
cpu_instance_type):
with timeout(seconds=AIRFLOW_CONFIG_TIMEOUT_IN_SECONDS):
knn = KNN(
role=ROLE,
instance_count=SINGLE_INSTANCE_COUNT,
instance_type=cpu_instance_type,
k=10,
predictor_type="regressor",
sample_size=500,
sagemaker_session=sagemaker_session,
)
training_set = datasets.one_p_mnist()
records = knn.record_set(training_set[0][:200],
training_set[1][:200].astype("float32"))
training_config = _build_airflow_workflow(
estimator=knn, instance_type=cpu_instance_type, inputs=records)
_assert_that_s3_url_contains_data(
sagemaker_session,
training_config["InputDataConfig"][0]["DataSource"]["S3DataSource"]
["S3Uri"],
)
def test_fm_airflow_config_uploads_data_source_to_s3(sagemaker_session,
cpu_instance_type):
with timeout(seconds=AIRFLOW_CONFIG_TIMEOUT_IN_SECONDS):
fm = FactorizationMachines(
role=ROLE,
instance_count=SINGLE_INSTANCE_COUNT,
instance_type=cpu_instance_type,
num_factors=10,
predictor_type="regressor",
epochs=2,
clip_gradient=1e2,
eps=0.001,
rescale_grad=1.0 / 100,
sagemaker_session=sagemaker_session,
)
training_set = datasets.one_p_mnist()
records = fm.record_set(training_set[0][:200],
training_set[1][:200].astype("float32"))
training_config = _build_airflow_workflow(
estimator=fm, 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):
tags = [{"Key": "some-tag", "Value": "value-for-tag"}]
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)
estimator = Estimator.attach(training_job_name=job_name,
sagemaker_session=sagemaker_session)
estimator._enable_network_isolation = True
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 = 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_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_record_set(sagemaker_session, cpu_instance_type):
"""Test the method ``AmazonAlgorithmEstimatorBase.record_set``.
In particular, test that the objects uploaded to the S3 bucket are encrypted.
"""
kmeans = KMeans(
role="SageMakerRole",
instance_count=1,
instance_type=cpu_instance_type,
k=10,
sagemaker_session=sagemaker_session,
)
record_set = kmeans.record_set(datasets.one_p_mnist()[0][:100],
encrypt=True)
parsed_url = urlparse(record_set.s3_data)
s3_client = sagemaker_session.boto_session.client("s3")
head = s3_client.head_object(Bucket=parsed_url.netloc,
Key=parsed_url.path.lstrip("/"))
assert head["ServerSideEncryption"] == "AES256"
def test_tuning_byo_estimator(sagemaker_session, cpu_instance_type):
"""Use Factorization Machines algorithm as an example here.
First we need to prepare data for training. We take standard data set, convert it to the
format that the algorithm can process and upload it to S3.
Then we create the Estimator and set hyperparamets as required by the algorithm.
Next, we can call fit() with path to the S3.
Later the trained model is deployed and prediction is called against the endpoint.
Default predictor is updated with json serializer and deserializer.
"""
image_uri = image_uris.retrieve("factorization-machines",
sagemaker_session.boto_region_name)
training_data_path = os.path.join(DATA_DIR, "dummy_tensor")
with timeout(minutes=TUNING_DEFAULT_TIMEOUT_MINUTES):
prefix = "test_byo_estimator"
key = "recordio-pb-data"
s3_train_data = sagemaker_session.upload_data(path=training_data_path,
key_prefix=os.path.join(
prefix, "train",
key))
estimator = Estimator(
image_uri=image_uri,
role="SageMakerRole",
instance_count=1,
instance_type=cpu_instance_type,
sagemaker_session=sagemaker_session,
)
estimator.set_hyperparameters(num_factors=10,
feature_dim=784,
mini_batch_size=100,
predictor_type="binary_classifier")
hyperparameter_ranges = {"mini_batch_size": IntegerParameter(100, 200)}
tuner = HyperparameterTuner(
estimator=estimator,
objective_metric_name="test:binary_classification_accuracy",
hyperparameter_ranges=hyperparameter_ranges,
max_jobs=2,
max_parallel_jobs=2,
)
tuning_job_name = unique_name_from_base("byo", 32)
print("Started hyperparameter tuning job with name {}:".format(
tuning_job_name))
tuner.fit(
{
"train": s3_train_data,
"test": s3_train_data
},
include_cls_metadata=False,
job_name=tuning_job_name,
)
best_training_job = tuner.best_training_job()
with timeout_and_delete_endpoint_by_name(best_training_job,
sagemaker_session):
predictor = tuner.deploy(
1,
cpu_instance_type,
endpoint_name=best_training_job,
serializer=_FactorizationMachineSerializer(),
deserializer=JSONDeserializer(),
)
result = predictor.predict(datasets.one_p_mnist()[0][:10])
assert len(result["predictions"]) == 10
for prediction in result["predictions"]:
assert prediction["score"] is not None
def kmeans_train_set(sagemaker_session):
return datasets.one_p_mnist()
def training_set():
return datasets.one_p_mnist()
def data_set():
return datasets.one_p_mnist()
def test_linearlearner_airflow_config_uploads_data_source_to_s3(
sagemaker_session, cpu_instance_type):
with timeout(seconds=AIRFLOW_CONFIG_TIMEOUT_IN_SECONDS):
training_set = datasets.one_p_mnist()
training_set[1][:100] = 1
training_set[1][100:200] = 0
training_set = training_set[0], training_set[1].astype(
np.dtype("float32"))
ll = LinearLearner(
ROLE,
1,
cpu_instance_type,
predictor_type="binary_classifier",
sagemaker_session=sagemaker_session,
)
ll.binary_classifier_model_selection_criteria = "accuracy"
ll.target_recall = 0.5
ll.target_precision = 0.5
ll.positive_example_weight_mult = 0.1
ll.epochs = 1
ll.use_bias = True
ll.num_models = 1
ll.num_calibration_samples = 1
ll.init_method = "uniform"
ll.init_scale = 0.5
ll.init_sigma = 0.2
ll.init_bias = 5
ll.optimizer = "adam"
ll.loss = "logistic"
ll.wd = 0.5
ll.l1 = 0.5
ll.momentum = 0.5
ll.learning_rate = 0.1
ll.beta_1 = 0.1
ll.beta_2 = 0.1
ll.use_lr_scheduler = True
ll.lr_scheduler_step = 2
ll.lr_scheduler_factor = 0.5
ll.lr_scheduler_minimum_lr = 0.1
ll.normalize_data = False
ll.normalize_label = False
ll.unbias_data = True
ll.unbias_label = False
ll.num_point_for_scaler = 10000
ll.margin = 1.0
ll.quantile = 0.5
ll.loss_insensitivity = 0.1
ll.huber_delta = 0.1
ll.early_stopping_tolerance = 0.0001
ll.early_stopping_patience = 3
records = ll.record_set(training_set[0][:200], training_set[1][:200])
training_config = _build_airflow_workflow(
estimator=ll, instance_type=cpu_instance_type, inputs=records)
_assert_that_s3_url_contains_data(
sagemaker_session,
training_config["InputDataConfig"][0]["DataSource"]["S3DataSource"]
["S3Uri"],
)