בנה זרימת עבודה של MLOps חוצה חשבונות באמצעות רישום המודלים של Amazon SageMaker

#Data Science account's policy to access Shared Services' S3 bucket
 {
    'Version': '2012-10-17',
    'Statement': [{
        'Sid': 'AddPerm',
        'Effect': 'Allow',
        'Principal': {
            'AWS': 'arn:aws:iam:::root'
        }, 
        "Action": [ 
            's3:PutObject', 
            's3:PutObjectAcl',
            's3:GetObject', 
            's3:GetObjectVersion'
        ], #read/write
        'Resource': 'arn:aws:s3:::/*'
    }]
}

#Deployment account's policy to access Shared Services' S3 bucket
 {
    'Version': '2012-10-17',
    'Statement': [{
        'Sid': 'AddPerm',
        'Effect': 'Allow',
        'Principal': {
            'AWS': 'arn:aws:iam:::root'
        },
        'Action': [ 
            's3:GetObject', 
            's3:GetObjectVersion'
        ], #read
        'Resource': 'arn:aws:s3:::/*'
    }]
}

{
  "Version": "2012-10-17",
  "Statement": [{
    "Sid": "AddPerm",
    "Effect": "Allow",
    "Principal": {
      "AWS": "arn:aws:iam:::root"    
    },
    "Action": [
      "s3:PutObject",
      "s3:PutObjectAcl",
      "s3:GetObject",
      "s3:GetObjectVersion"    ],
    "Resource": "arn:aws:s3:::/*"  
    },
    {
      "Sid": "AddPermDeployment",
      "Effect": "Allow",
      "Principal": {
        "AWS": "arn:aws:iam:::root"      
      },
      "Action": [
        "s3:GetObject",
        "s3:GetObjectVersion"      ], 
      "Resource": "arn:aws:s3:::/*"    
    }
  ]
}

model_package_group_name = "cross-account-example-model"
sm_client = boto3.Session().client("sagemaker")

create_model_package_group_response = sm_client.create_model_package_group(
    ModelPackageGroupName=model_package_group_name,
    ModelPackageGroupDescription="Cross account model package group",
    Tags=[
          {
              'Key': 'Name',
              'Value': 'cross_account_test'
          },
      ]

)

print('ModelPackageGroup Arn : {}'.format(create_model_package_group_response['ModelPackageGroupArn']))

{
  "Version": "2012-10-17",
  "Statement": [
    {
      "Sid": "AddPermModelPackageGroupCrossAccount",
      "Effect": "Allow",
      "Principal": {
        "AWS": "arn:aws:iam:::root"      
      },
      "Action": [
        "sagemaker:DescribeModelPackageGroup"      
        ],
      "Resource": "arn:aws:sagemaker:::model-package-group/"    
    },
    {
      "Sid": "AddPermModelPackageVersionCrossAccount",
      "Effect": "Allow",
      "Principal": {
        "AWS": "arn:aws:iam:::root"      
      },
      "Action": [
        "sagemaker:DescribeModelPackage",
        "sagemaker:ListModelPackages",
        "sagemaker:UpdateModelPackage",
        "sagemaker:CreateModelPackage",
        "sagemaker:CreateModel"      
      ],
      "Resource": "arn:aws:sagemaker:::model-package//*"    
    }
  ]
}

# Convert the policy from JSON dict to string
model_package_group_policy = dict( )
model_package_group_policy = json.dumps(model_package_group_policy)

# Set the new policy
sm_client = boto3.Session().client("sagemaker")
response = sm_client.put_model_package_group_policy(
    ModelPackageGroupName = model_package_group_name,
    ResourcePolicy = model_package_group_policy)

{
    "Version": "2012-10-17",
    "Statement": [
        {
            "Effect": "Allow",
            "Action": "s3:GetObject",
            "Resource": "arn:aws:s3:::/sagemaker//output/model.tar.gz"
        }
    ]
}

{
    "Version": "2012-10-17",
    "Statement": [
        {
            "Sid": "AllowUseOfTheKey",
            "Effect": "Allow",
            "Action": [
                "kms:Decrypt"
            ],
            "Resource": [
                "arn:aws:kms:us-east-1::key/{xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx}"
            ]
        }
    ]
}

# Useful SageMaker variables - Create a Pipeline session which will lazy init resources
session = PipelineSession()

framework_version = "0.23-1"

# Create SKlearn processor object,
# The object contains information about what instance type to use, the IAM role to use etc.
# A managed processor comes with a preconfigured container, so only specifying version is required.
sklearn_processor = SKLearnProcessor(
    framework_version=framework_version,
    role=role,
    instance_type=processing_instance_type,
    instance_count=1,
    base_job_name="tf2-california-housing-processing-job",
    sagemaker_session=session
)

# Use the sklearn_processor in a SageMaker pipelines ProcessingStep
step_preprocess_data = ProcessingStep(
    name="Preprocess-California-Housing-Data",
    processor=sklearn_processor,
    inputs=[
        ProcessingInput(source=input_data, destination="/opt/ml/processing/input"),
    ],
    outputs=[
        ProcessingOutput(output_name="train", source="/opt/ml/processing/train"),
        ProcessingOutput(output_name="test", source="/opt/ml/processing/test"),
    ],
    code="preprocess.py",
)

kms_client = boto3.client('kms')
response = kms_client.describe_key(
    KeyId='alias/sagemaker/outkey',
)
key_id = response['KeyMetadata']['KeyId']

model_path = f"s3://{bucket}/{prefix}/model/"

hyperparameters = {"epochs": training_epochs}
tensorflow_version = "2.4.1"
python_version = "py37"

tf2_estimator = TensorFlow(
    source_dir="code",
    entry_point="train.py",
    instance_type=training_instance_type,
    instance_count=1,
    framework_version=tensorflow_version,
    role=role,
    base_job_name="tf2-california-housing-train",
    output_path=model_path,
    output_kms_key=key_id,
    hyperparameters=hyperparameters,
    py_version=python_version,
    sagemaker_session=session
)

# Use the tf2_estimator in a SageMaker pipelines ProcessingStep.
# NOTE how the input to the training job directly references the output of the previous step.
step_train_model = TrainingStep(
    name="Train-California-Housing-Model",
    estimator=tf2_estimator,
    inputs={
        "train": TrainingInput(
            s3_data=step_preprocess_data.properties.ProcessingOutputConfig.Outputs[
                "train"
            ].S3Output.S3Uri,
            content_type="text/csv",
        ),
        "test": TrainingInput(
            s3_data=step_preprocess_data.properties.ProcessingOutputConfig.Outputs[
                "test"
            ].S3Output.S3Uri,
            content_type="text/csv",
        ),
    },
)

from sagemaker.workflow.properties import PropertyFile

# Create SKLearnProcessor object.
# The object contains information about what container to use, what instance type etc.
evaluate_model_processor = SKLearnProcessor(
    framework_version=framework_version,
    instance_type=processing_instance_type,
    instance_count=1,
    base_job_name="tf2-california-housing-evaluate",
    role=role,
    sagemaker_session=session
)

# Create a PropertyFile
# A PropertyFile is used to be able to reference outputs from a processing step, for instance to use in a condition step.
# For more information, visit https://docs.aws.amazon.com/sagemaker/latest/dg/build-and-manage-propertyfile.html
evaluation_report = PropertyFile(
    name="EvaluationReport", output_name="evaluation", path="evaluation.json"
)

# Use the evaluate_model_processor in a SageMaker pipelines ProcessingStep.
step_evaluate_model = ProcessingStep(
    name="Evaluate-California-Housing-Model",
    processor=evaluate_model_processor,
    inputs=[
        ProcessingInput(
            source=step_train_model.properties.ModelArtifacts.S3ModelArtifacts,
            destination="/opt/ml/processing/model",
        ),
        ProcessingInput(
            source=step_preprocess_data.properties.ProcessingOutputConfig.Outputs[
                "test"
            ].S3Output.S3Uri,
            destination="/opt/ml/processing/test",
        ),
    ],
    outputs=[
        ProcessingOutput(output_name="evaluation", source="/opt/ml/processing/evaluation"),
    ],
    code="evaluate.py",
    property_files=[evaluation_report],
)

# Create ModelMetrics object using the evaluation report from the evaluation step
# A ModelMetrics object contains metrics captured from a model.
model_metrics = ModelMetrics(
    model_statistics=MetricsSource(
        s3_uri=evaluation_s3_uri,
        content_type="application/json",
    )
)

# Create a RegisterModel step, which registers the model with SageMaker Model Registry.
model = Model(
    image_uri=tf2_estimator.training_image_uri(),
    model_data=training_step.properties.ModelArtifacts.S3ModelArtifacts,
    source_dir=tf2_estimator.source_dir,
    entry_point=tf2_estimator.entry_point,
    role=role_arn,
    sagemaker_session=session
)

model_registry_args = model.register(
    content_types=['text/csv'],
    response_types=['application/json'],
    inference_instances=['ml.t2.medium', 'ml.m5.xlarge'],
    transform_instances=['ml.m5.xlarge'],
    model_package_group_name=model_package_group_name,
    approval_status='PendingManualApproval',
    model_metrics=model_metrics
)

 step_register_model= ModelStep(
    name='RegisterModel',
    step_args=model_registry_args
)

from sagemaker.inputs import CreateModelInput 
from sagemaker.workflow.model_step import ModelStep 
step_create_model = ModelStep( 
    name="Create-California-Housing-Model", 
    step_args=model.create(instance_type="ml.m5.large",accelerator_type="ml.eia1.medium"),
 )

from sagemaker.workflow.conditions import ConditionLessThanOrEqualTo
from sagemaker.workflow.condition_step import (
    ConditionStep,
    JsonGet,
)

# Create accuracy condition to ensure the model meets performance requirements.
# Models with a test accuracy lower than the condition will not be registered with the model registry.
cond_lte = ConditionLessThanOrEqualTo(
    left=JsonGet(
        step=step_evaluate_model,
        property_file=evaluation_report,
        json_path="regression_metrics.mse.value",
    ),
    right=accuracy_mse_threshold,
)

# Create a SageMaker Pipelines ConditionStep, using the preceding condition.
# Enter the steps to perform if the condition returns True / False.
step_cond = ConditionStep(
    name="MSE-Lower-Than-Threshold-Condition",
    conditions=[cond_lte],
    if_steps=[step_register_model, step_create_model],
    else_steps=[step_higher_mse_send_email_lambda],
)

from sagemaker.workflow.pipeline import Pipeline

# Create a SageMaker Pipeline.
# Each parameter for the pipeline must be set as a parameter explicitly when the pipeline is created.
# Also pass in each of the preceding steps.
# Note that the order of execution is determined from each step's dependencies on other steps,
# not on the order they are passed in.
pipeline = Pipeline(
    name=pipeline_name,
    parameters=[
        processing_instance_type,
        training_instance_type,
        input_data,
        training_epochs,
        accuracy_mse_threshold,
        endpoint_instance_type,
    ],
    steps=[step_preprocess_data, step_train_model, step_evaluate_model, step_cond],
)

from sagemaker import ModelPackage
from time import gmtime, strftime

sagemaker_session = sagemaker.Session(boto_session=sess)

model_package_arn = 'arn:aws:sagemaker:::/modeltest/version_number'
model = ModelPackage(role=role, 
                     model_package_arn=model_package_arn, 
                     sagemaker_session=sagemaker_session)
model.deploy(initial_instance_count=1, instance_type='ml.m5.xlarge')