Add deploy (aws#36)

Author: ChoiByungWook

src/sagemaker/tuner.py

@@ -119,6 +119,34 @@ def fit(self, inputs, job_name=None, **kwargs):
         self.prepare_for_training()
         self.latest_tuning_job = _TuningJob.start_new(self, inputs)
 
+    def deploy(self, initial_instance_count, instance_type, endpoint_name=None, **kwargs):
+        """Deploy the best trained or user specified model to an Amazon SageMaker endpoint and return a
+        ``sagemaker.RealTimePredictor``
+        object.
+
+                More information:
+                http://docs.aws.amazon.com/sagemaker/latest/dg/how-it-works-training.html
+
+                Args:
+                    initial_instance_count (int): Minimum number of EC2 instances to deploy to an endpoint for
+                    prediction.
+                    instance_type (str): Type of EC2 instance to deploy to an endpoint for prediction,
+                        for example, 'ml.c4.xlarge'.
+                    endpoint_name (str): Name to use for creating an Amazon SageMaker endpoint. If not specified,
+                    the name of the training job is used.
+                    **kwargs: Passed to invocation of ``create_model()``. Implementations may customize
+                        ``create_model()`` to accept ``**kwargs`` to customize model creation during deploy.
+                        For more, see the implementation docs.
+
+                Returns:
+                    sagemaker.predictor.RealTimePredictor: A predictor that provides a ``predict()`` method,
+                        which can be used to send requests to the Amazon SageMaker endpoint and obtain inferences.
+                """
+        endpoint_name = endpoint_name or self.best_training_job()
+        best_estimator = self.estimator.attach(self.best_training_job(),
+                                               sagemaker_session=self.estimator.sagemaker_session)
+        return best_estimator.deploy(initial_instance_count, instance_type, endpoint_name=endpoint_name, **kwargs)
+
     def stop_tuning_job(self):
         """Stop latest running tuning job.
         """

tests/unit/test_tuner.py

@@ -15,12 +15,14 @@
 import pytest
 from mock import Mock
 
+from sagemaker import RealTimePredictor
 from sagemaker.amazon.pca import PCA
 from sagemaker.amazon.amazon_estimator import RecordSet
 from sagemaker.estimator import Estimator
 from sagemaker.tuner import _ParameterRange, ContinuousParameter, IntegerParameter, CategoricalParameter, \
     HyperparameterTuner, _TuningJob
 from sagemaker.mxnet import MXNet
+MODEL_DATA = "s3://bucket/model.tar.gz"
 
 JOB_NAME = 'tuning_job'
 REGION = 'us-west-2'
@@ -211,6 +213,68 @@ def test_best_tuning_job_no_best_job(tuner):
     assert 'Best training job not available for tuning job:' in str(e)
 
 
+def test_deploy_default(tuner):
+    returned_training_job_description = {
+        'AlgorithmSpecification': {
+            'TrainingInputMode': 'File',
+            'TrainingImage': IMAGE_NAME
+        },
+        'HyperParameters': {
+            'sagemaker_submit_directory': '"s3://some/sourcedir.tar.gz"',
+            'checkpoint_path': '"s3://other/1508872349"',
+            'sagemaker_program': '"iris-dnn-classifier.py"',
+            'sagemaker_enable_cloudwatch_metrics': 'false',
+            'sagemaker_container_log_level': '"logging.INFO"',
+            'sagemaker_job_name': '"neo"',
+            'training_steps': '100',
+            '_tuning_objective_metric': 'Validation-accuracy',
+        },
+
+        'RoleArn': ROLE,
+        'ResourceConfig': {
+            'VolumeSizeInGB': 30,
+            'InstanceCount': 1,
+            'InstanceType': 'ml.c4.xlarge'
+        },
+        'StoppingCondition': {
+            'MaxRuntimeInSeconds': 24 * 60 * 60
+        },
+        'TrainingJobName': 'neo',
+        'TrainingJobStatus': 'Completed',
+        'OutputDataConfig': {
+            'KmsKeyId': '',
+            'S3OutputPath': 's3://place/output/neo'
+        },
+        'TrainingJobOutput': {
+            'S3TrainingJobOutput': 's3://here/output.tar.gz'
+        },
+        'ModelArtifacts': {
+            'S3ModelArtifacts': MODEL_DATA
+        }
+    }
+    tuning_job_description = {'BestTrainingJob': {'TrainingJobName': JOB_NAME}}
+
+    tuner.estimator.sagemaker_session.sagemaker_client.describe_training_job = \
+        Mock(name='describe_training_job', return_value=returned_training_job_description)
+    tuner.estimator.sagemaker_session.sagemaker_client.describe_hyper_parameter_tuning_job = Mock(
+        name='describe_hyper_parameter_tuning_job', return_value=tuning_job_description)
+    tuner.estimator.sagemaker_session.log_for_jobs = Mock(name='log_for_jobs')
+
+    tuner.latest_tuning_job = _TuningJob(tuner.estimator.sagemaker_session, JOB_NAME)
+    predictor = tuner.deploy(TRAIN_INSTANCE_COUNT, TRAIN_INSTANCE_TYPE)
+
+    tuner.estimator.sagemaker_session.create_model.assert_called_once()
+    args = tuner.estimator.sagemaker_session.create_model.call_args[0]
+    assert args[0].startswith(IMAGE_NAME)
+    assert args[1] == ROLE
+    assert args[2]['Image'] == IMAGE_NAME
+    assert args[2]['ModelDataUrl'] == MODEL_DATA
+
+    assert isinstance(predictor, RealTimePredictor)
+    assert predictor.endpoint.startswith(JOB_NAME)
+    assert predictor.sagemaker_session == tuner.estimator.sagemaker_session
+
+
 #################################################################################
 # _ParameterRange Tests