def __init__(
self,
trainingInstanceType,
trainingInstanceCount,
endpointInstanceType,
endpointInitialInstanceCount,
sagemakerRole=IAMRoleFromConfig(),
requestRowSerializer=ProtobufRequestRowSerializer(),
responseRowDeserializer=LinearLearnerBinaryClassifierProtobufResponseRowDeserializer(),
trainingInputS3DataPath=S3AutoCreatePath(),
trainingOutputS3DataPath=S3AutoCreatePath(),
trainingInstanceVolumeSizeInGB=1024,
trainingProjectedColumns=None,
trainingChannelName="train",
trainingContentType=None,
trainingS3DataDistribution="ShardedByS3Key",
trainingSparkDataFormat="sagemaker",
trainingSparkDataFormatOptions=None,
trainingInputMode="File",
trainingCompressionCodec=None,
trainingMaxRuntimeInSeconds=24*60*60,
trainingKmsKeyId=None,
modelEnvironmentVariables=None,
endpointCreationPolicy=EndpointCreationPolicy.CREATE_ON_CONSTRUCT,
sagemakerClient=SageMakerClients.create_sagemaker_client(),
region=None,
s3Client=SageMakerClients.create_s3_default_client(),
stsClient=SageMakerClients.create_sts_default_client(),
modelPrependInputRowsToTransformationRows=True,
deleteStagingDataAfterTraining=True,
namePolicyFactory=RandomNamePolicyFactory(),
uid=None,
javaObject=None):
if trainingSparkDataFormatOptions is None:
trainingSparkDataFormatOptions = {}
if modelEnvironmentVariables is None:
modelEnvironmentVariables = {}
if uid is None:
uid = Identifiable._randomUID()
kwargs = locals().copy()
del kwargs['self']
super(LinearLearnerBinaryClassifier, self).__init__(**kwargs)
default_params = {
'predictor_type': 'binary_classifier'
}
self._setDefault(**default_params)
def test_sagemakermodel_passes_correct_params_to_scala():
model_image = "model-abc-123"
model_path = S3DataPath("my-bucket", "model-abc-123")
role_arn = "role-789"
endpoint_instance_type = "c4.8xlarge"
model = SageMakerModel(
endpointInstanceType=endpoint_instance_type,
endpointInitialInstanceCount=2,
requestRowSerializer=ProtobufRequestRowSerializer(),
responseRowDeserializer=KMeansProtobufResponseRowDeserializer(),
modelImage=model_image,
modelPath=model_path,
modelEnvironmentVariables=None,
modelExecutionRoleARN=role_arn,
endpointCreationPolicy=EndpointCreationPolicy.DO_NOT_CREATE,
sagemakerClient=SageMakerClients.create_sagemaker_client(),
prependResultRows=False,
namePolicy=None,
uid="uid")
assert model.modelImage == model_image
assert model.modelPath.bucket == model_path.bucket
assert model.modelExecutionRoleARN == role_arn
assert model.endpointInstanceType == endpoint_instance_type
assert model.existingEndpointName is None
def test_sagemakermodel_can_do_resource_cleanup():
endpoint_name = "my-existing-endpoint-123"
model = SageMakerModel(
endpointInstanceType="x1.128xlarge",
endpointInitialInstanceCount=2,
requestRowSerializer=ProtobufRequestRowSerializer(),
responseRowDeserializer=KMeansProtobufResponseRowDeserializer(),
existingEndpointName=endpoint_name,
modelImage="some_image",
modelPath=S3DataPath("a", "b"),
modelEnvironmentVariables=None,
modelExecutionRoleARN="role",
endpointCreationPolicy=EndpointCreationPolicy.DO_NOT_CREATE,
sagemakerClient=SageMakerClients.create_sagemaker_client(),
prependResultRows=False,
namePolicy=None,
uid="uid")
sm = model.sagemakerClient
assert sm is not None
resource_cleanup = SageMakerResourceCleanup(sm)
assert resource_cleanup is not None
created_resources = model.getCreatedResources()
assert created_resources is not None
resource_cleanup.deleteResources(created_resources)
def test_linearLearnerBinaryClassifier_passes_correct_params_to_scala():
training_instance_type = "c4.8xlarge"
training_instance_count = 3
endpoint_instance_type = "c4.8xlarge"
endpoint_initial_instance_count = 3
training_bucket = "random-bucket"
input_prefix = "linear-learner-binary-classifier-training"
output_prefix = "linear-learner-binary-classifier-out"
integTestingRole = "arn:aws:iam::123456789:role/SageMakerRole"
estimator = LinearLearnerBinaryClassifier(
trainingInstanceType=training_instance_type,
trainingInstanceCount=training_instance_count,
endpointInstanceType=endpoint_instance_type,
endpointInitialInstanceCount=endpoint_initial_instance_count,
sagemakerRole=IAMRole(integTestingRole),
requestRowSerializer=ProtobufRequestRowSerializer(),
responseRowDeserializer=
LinearLearnerBinaryClassifierProtobufResponseRowDeserializer(),
trainingInstanceVolumeSizeInGB=2048,
trainingInputS3DataPath=S3DataPath(training_bucket, input_prefix),
trainingOutputS3DataPath=S3DataPath(training_bucket, output_prefix),
trainingMaxRuntimeInSeconds=1,
endpointCreationPolicy=EndpointCreationPolicy.CREATE_ON_TRANSFORM,
sagemakerClient=SageMakerClients.create_sagemaker_client(),
s3Client=SageMakerClients.create_s3_default_client(),
stsClient=SageMakerClients.create_sts_default_client(),
modelPrependInputRowsToTransformationRows=True,
namePolicyFactory=RandomNamePolicyFactory(),
uid="sagemaker")
assert estimator.trainingInputS3DataPath.bucket == training_bucket
assert estimator.trainingInputS3DataPath.objectPath == input_prefix
assert estimator.trainingInstanceCount == training_instance_count
assert estimator.trainingInstanceType == training_instance_type
assert estimator.endpointInstanceType == endpoint_instance_type
assert estimator.endpointInitialInstanceCount == endpoint_initial_instance_count
assert estimator.trainingInstanceVolumeSizeInGB == 2048
assert estimator.trainingMaxRuntimeInSeconds == 1
assert estimator.trainingKmsKeyId is None
def fromEndpoint(
cls,
endpointName,
requestRowSerializer,
responseRowDeserializer,
modelEnvironmentVariables=None,
sagemakerClient=SageMakerClients.create_sagemaker_client(),
prependResultRows=True,
namePolicy=RandomNamePolicy(),
uid="sagemaker"):
""" Creates a JavaSageMakerModel from existing model data in S3.
The returned JavaSageMakerModel can be used to transform Dataframes.
Args:
endpointName (str): The name of an endpoint that is currently in service.
requestRowSerializer (RequestRowSerializer): Serializes a row to an array of bytes.
responseRowDeserializer (ResponseRowDeserializer): Deserializes an array of bytes to a
series of rows.
modelEnvironmentVariables: The environment variables that SageMaker will set on the
model container during execution.
sagemakerClient (AmazonSageMaker) Amazon SageMaker client. Used to send
CreateTrainingJob, CreateModel, and CreateEndpoint requests.
prependResultRows (bool): Whether the transformation result should also include the
input Rows. If true, each output Row is formed by a concatenation of the input Row
with the corresponding Row produced by SageMaker invocation, produced by
responseRowDeserializer. If false, each output Row is just taken from
responseRowDeserializer.
namePolicy (NamePolicy): The NamePolicy to use when naming SageMaker entities created
during usage of the returned model.
uid (String): The unique identifier of the SageMakerModel. Used to represent the stage
in Spark ML pipelines.
Returns:
JavaSageMakerModel:
A JavaSageMakerModel that sends InvokeEndpoint requests to an endpoint hosting
the training job's model.
"""
scala_function = "%s.fromEndpoint" % SageMakerModel._wrapped_class
if modelEnvironmentVariables is None:
modelEnvironmentVariables = {}
return SageMakerJavaWrapper()._new_java_obj(
scala_function, endpointName, requestRowSerializer,
responseRowDeserializer, modelEnvironmentVariables,
sagemakerClient, prependResultRows, namePolicy, uid)
def __init__(self,
endpointInstanceType,
endpointInitialInstanceCount,
requestRowSerializer,
responseRowDeserializer,
existingEndpointName=None,
modelImage=None,
modelPath=None,
modelEnvironmentVariables=None,
modelExecutionRoleARN=None,
endpointCreationPolicy=EndpointCreationPolicy.CREATE_ON_CONSTRUCT,
sagemakerClient=SageMakerClients.create_sagemaker_client(),
prependResultRows=True,
namePolicy=RandomNamePolicy(),
uid=None,
javaObject=None):
super(SageMakerModel, self).__init__()
if modelEnvironmentVariables is None:
modelEnvironmentVariables = {}
if javaObject:
self._java_obj = javaObject
else:
if uid is None:
uid = Identifiable._randomUID()
self._java_obj = self._new_java_obj(
SageMakerModel._wrapped_class,
Option(endpointInstanceType),
Option(endpointInitialInstanceCount),
requestRowSerializer,
responseRowDeserializer,
Option(existingEndpointName),
Option(modelImage),
Option(modelPath),
modelEnvironmentVariables,
Option(modelExecutionRoleARN),
endpointCreationPolicy,
sagemakerClient,
prependResultRows,
namePolicy,
uid
)
self._resetUid(self._call_java("uid"))
def test_sagemakermodel_can_be_created_from_java_obj():
endpoint_name = "my-existing-endpoint-123"
model = SageMakerModel(
endpointInstanceType="x1.128xlarge",
endpointInitialInstanceCount=2,
requestRowSerializer=ProtobufRequestRowSerializer(),
responseRowDeserializer=KMeansProtobufResponseRowDeserializer(),
existingEndpointName=endpoint_name,
modelImage="some_image",
modelPath=S3DataPath("a", "b"),
modelEnvironmentVariables=None,
modelExecutionRoleARN="role",
endpointCreationPolicy=EndpointCreationPolicy.DO_NOT_CREATE,
sagemakerClient=SageMakerClients.create_sagemaker_client(),
prependResultRows=False,
namePolicy=None,
uid="uid")
new_model = SageMakerModel._from_java(model._to_java())
assert new_model.uid == model.uid
def fromModelS3Path(
cls,
modelPath,
modelImage,
modelExecutionRoleARN,
endpointInstanceType,
endpointInitialInstanceCount,
requestRowSerializer,
responseRowDeserializer,
modelEnvironmentVariables=None,
endpointCreationPolicy=EndpointCreationPolicy.CREATE_ON_CONSTRUCT,
sagemakerClient=SageMakerClients.create_sagemaker_client(),
prependResultRows=True,
namePolicy=RandomNamePolicy(),
uid="sagemaker"):
""" Creates a JavaSageMakerModel from existing model data in S3.
The returned JavaSageMakerModel can be used to transform Dataframes.
Args:
modelPath (str): The S3 URI to the model data to host.
modelImage (str): The URI of the image that will serve model inferences.
modelExecutionRoleARN (str): The IAM Role used by SageMaker when running the hosted
Model and to download model data from S3.
endpointInstanceType (str): The instance type used to run the model container.
endpointInitialInstanceCount (int): The initial number of instances used to host the
model.
requestRowSerializer (RequestRowSerializer): Serializes a row to an array of bytes.
responseRowDeserializer (ResponseRowDeserializer): Deserializes an array of bytes to a
series of rows.
modelEnvironmentVariables: The environment variables that SageMaker will set on the
model container during execution.
endpointCreationPolicy (EndpointCreationPolicy): Whether the endpoint is created upon
SageMakerModel construction, transformation, or not at all.
sagemakerClient (AmazonSageMaker) Amazon SageMaker client. Used to send
CreateTrainingJob, CreateModel, and CreateEndpoint requests.
prependResultRows (bool): Whether the transformation result should also include the
input Rows. If true, each output Row is formed by a concatenation of the input Row
with the corresponding Row produced by SageMaker invocation, produced by
responseRowDeserializer. If false, each output Row is just taken from
responseRowDeserializer.
namePolicy (NamePolicy): The NamePolicy to use when naming SageMaker entities created
during usage of the returned model.
uid (String): The unique identifier of the SageMakerModel. Used to represent the stage
in Spark ML pipelines.
Returns:
JavaSageMakerModel:
A JavaSageMakerModel that sends InvokeEndpoint requests to an endpoint hosting
the training job's model.
"""
scala_function = "%s.fromModelS3Path" % SageMakerModel._wrapped_class
if modelEnvironmentVariables is None:
modelEnvironmentVariables = {}
return SageMakerJavaWrapper()._new_java_obj(
scala_function, modelPath, modelImage, modelExecutionRoleARN,
endpointInstanceType, endpointInitialInstanceCount,
requestRowSerializer, responseRowDeserializer,
modelEnvironmentVariables, endpointCreationPolicy, sagemakerClient,
prependResultRows, namePolicy, uid)