Merge branch 'zwei' into fix-bytes-deserializer

Author: nadiaya

src/sagemaker/algorithm.py

@@ -35,11 +35,11 @@ def __init__(
         self,
         algorithm_arn,
         role,
-        train_instance_count,
-        train_instance_type,
-        train_volume_size=30,
-        train_volume_kms_key=None,
-        train_max_run=24 * 60 * 60,
+        instance_count,
+        instance_type,
+        volume_size=30,
+        volume_kms_key=None,
+        max_run=24 * 60 * 60,
         input_mode="File",
         output_path=None,
         output_kms_key=None,
@@ -65,15 +65,15 @@ def __init__(
                 access training data and model artifacts. After the endpoint
                 is created, the inference code might use the IAM role, if it
                 needs to access an AWS resource.
-            train_instance_count (int): Number of Amazon EC2 instances to
-                use for training. train_instance_type (str): Type of EC2
+            instance_count (int): Number of Amazon EC2 instances to
+                use for training. instance_type (str): Type of EC2
                 instance to use for training, for example, 'ml.c4.xlarge'.
-            train_volume_size (int): Size in GB of the EBS volume to use for
+            volume_size (int): Size in GB of the EBS volume to use for
                 storing input data during training (default: 30). Must be large enough to store
                 training data if File Mode is used (which is the default).
-            train_volume_kms_key (str): Optional. KMS key ID for encrypting EBS volume attached
+            volume_kms_key (str): Optional. KMS key ID for encrypting EBS volume attached
                 to the training instance (default: None).
-            train_max_run (int): Timeout in seconds for training (default: 24 * 60 * 60).
+            max_run (int): Timeout in seconds for training (default: 24 * 60 * 60).
                 After this amount of time Amazon SageMaker terminates the
                 job regardless of its current status.
             input_mode (str): The input mode that the algorithm supports
@@ -131,11 +131,11 @@ def __init__(
         self.algorithm_arn = algorithm_arn
         super(AlgorithmEstimator, self).__init__(
             role,
-            train_instance_count,
-            train_instance_type,
-            train_volume_size,
-            train_volume_kms_key,
-            train_max_run,
+            instance_count,
+            instance_type,
+            volume_size,
+            volume_kms_key,
+            max_run,
             input_mode,
             output_path,
             output_kms_key,
@@ -167,30 +167,30 @@ def validate_train_spec(self):
 
         # Check that the input mode provided is compatible with the training input modes for the
         # algorithm.
-        train_input_modes = self._algorithm_training_input_modes(train_spec["TrainingChannels"])
-        if self.input_mode not in train_input_modes:
+        input_modes = self._algorithm_training_input_modes(train_spec["TrainingChannels"])
+        if self.input_mode not in input_modes:
             raise ValueError(
                 "Invalid input mode: %s. %s only supports: %s"
-                % (self.input_mode, algorithm_name, train_input_modes)
+                % (self.input_mode, algorithm_name, input_modes)
             )
 
         # Check that the training instance type is compatible with the algorithm.
         supported_instances = train_spec["SupportedTrainingInstanceTypes"]
-        if self.train_instance_type not in supported_instances:
+        if self.instance_type not in supported_instances:
             raise ValueError(
-                "Invalid train_instance_type: %s. %s supports the following instance types: %s"
-                % (self.train_instance_type, algorithm_name, supported_instances)
+                "Invalid instance_type: %s. %s supports the following instance types: %s"
+                % (self.instance_type, algorithm_name, supported_instances)
             )
 
         # Verify if distributed training is supported by the algorithm
         if (
-            self.train_instance_count > 1
+            self.instance_count > 1
             and "SupportsDistributedTraining" in train_spec
             and not train_spec["SupportsDistributedTraining"]
         ):
             raise ValueError(
                 "Distributed training is not supported by %s. "
-                "Please set train_instance_count=1" % algorithm_name
+                "Please set instance_count=1" % algorithm_name
             )
 
     def set_hyperparameters(self, **kwargs):

src/sagemaker/amazon/README.rst

@@ -34,7 +34,7 @@ Please find an example code snippet for illustration:
 .. code:: python
 
     from sagemaker import PCA
-    pca_estimator = PCA(role='SageMakerRole', train_instance_count=1, train_instance_type='ml.m4.xlarge', num_components=3)
+    pca_estimator = PCA(role='SageMakerRole', instance_count=1, instance_type='ml.m4.xlarge', num_components=3)
 
     import numpy as np
     records = pca_estimator.record_set(np.arange(10).reshape(2,5))

src/sagemaker/amazon/amazon_estimator.py

@@ -52,8 +52,8 @@ class AmazonAlgorithmEstimatorBase(EstimatorBase):
     def __init__(
         self,
         role,
-        train_instance_count,
-        train_instance_type,
+        instance_count,
+        instance_type,
         data_location=None,
         enable_network_isolation=False,
         **kwargs
@@ -66,9 +66,9 @@ def __init__(
                 endpoints use this role to access training data and model
                 artifacts. After the endpoint is created, the inference code
                 might use the IAM role, if it needs to access an AWS resource.
-            train_instance_count (int): Number of Amazon EC2 instances to use
+            instance_count (int): Number of Amazon EC2 instances to use
                 for training.
-            train_instance_type (str): Type of EC2 instance to use for training,
+            instance_type (str): Type of EC2 instance to use for training,
                 for example, 'ml.c4.xlarge'.
             data_location (str or None): The s3 prefix to upload RecordSet
                 objects to, expressed as an S3 url. For example
@@ -89,8 +89,8 @@ def __init__(
         """
         super(AmazonAlgorithmEstimatorBase, self).__init__(
             role,
-            train_instance_count,
-            train_instance_type,
+            instance_count,
+            instance_type,
             enable_network_isolation=enable_network_isolation,
             **kwargs
         )
@@ -266,7 +266,7 @@ def record_set(self, train, labels=None, channel="train", encrypt=False):
         the list of objects created and also stored in S3.
 
         The number of S3 objects created is controlled by the
-        ``train_instance_count`` property on this Estimator. One S3 object is
+        ``instance_count`` property on this Estimator. One S3 object is
         created per training instance.
 
         Args:
@@ -291,7 +291,7 @@ def record_set(self, train, labels=None, channel="train", encrypt=False):
         key_prefix = key_prefix.lstrip("/")
         logger.debug("Uploading to bucket %s and key_prefix %s", bucket, key_prefix)
         manifest_s3_file = upload_numpy_to_s3_shards(
-            self.train_instance_count, s3, bucket, key_prefix, train, labels, encrypt
+            self.instance_count, s3, bucket, key_prefix, train, labels, encrypt
         )
         logger.debug("Created manifest file %s", manifest_s3_file)
         return RecordSet(

src/sagemaker/amazon/factorization_machines.py

@@ -77,8 +77,8 @@ class FactorizationMachines(AmazonAlgorithmEstimatorBase):
     def __init__(
         self,
         role,
-        train_instance_count,
-        train_instance_type,
+        instance_count,
+        instance_type,
         num_factors,
         predictor_type,
         epochs=None,
@@ -150,9 +150,9 @@ def __init__(
                 endpoints use this role to access training data and model
                 artifacts. After the endpoint is created, the inference code
                 might use the IAM role, if accessing AWS resource.
-            train_instance_count (int): Number of Amazon EC2 instances to use
+            instance_count (int): Number of Amazon EC2 instances to use
                 for training.
-            train_instance_type (str): Type of EC2 instance to use for training,
+            instance_type (str): Type of EC2 instance to use for training,
                 for example, 'ml.c4.xlarge'.
             num_factors (int): Dimensionality of factorization.
             predictor_type (str): Type of predictor 'binary_classifier' or
@@ -212,9 +212,7 @@ def __init__(
             :class:`~sagemaker.estimator.amazon_estimator.AmazonAlgorithmEstimatorBase` and
             :class:`~sagemaker.estimator.EstimatorBase`.
         """
-        super(FactorizationMachines, self).__init__(
-            role, train_instance_count, train_instance_type, **kwargs
-        )
+        super(FactorizationMachines, self).__init__(role, instance_count, instance_type, **kwargs)
 
         self.num_factors = num_factors
         self.predictor_type = predictor_type

src/sagemaker/amazon/ipinsights.py

@@ -53,8 +53,8 @@ class IPInsights(AmazonAlgorithmEstimatorBase):
     def __init__(
         self,
         role,
-        train_instance_count,
-        train_instance_type,
+        instance_count,
+        instance_type,
         num_entity_vectors,
         vector_dim,
         batch_metrics_publish_interval=None,
@@ -94,9 +94,9 @@ def __init__(
                 endpoints use this role to access training data and model
                 artifacts. After the endpoint is created, the inference code
                 might use the IAM role, if accessing AWS resource.
-            train_instance_count (int): Number of Amazon EC2 instances to use
+            instance_count (int): Number of Amazon EC2 instances to use
                 for training.
-            train_instance_type (str): Type of EC2 instance to use for training,
+            instance_type (str): Type of EC2 instance to use for training,
                 for example, 'ml.m5.xlarge'.
             num_entity_vectors (int): Required. The number of embeddings to
                 train for entities accessing online resources. We recommend 2x
@@ -126,7 +126,7 @@ def __init__(
             :class:`~sagemaker.estimator.amazon_estimator.AmazonAlgorithmEstimatorBase` and
             :class:`~sagemaker.estimator.EstimatorBase`.
         """
-        super(IPInsights, self).__init__(role, train_instance_count, train_instance_type, **kwargs)
+        super(IPInsights, self).__init__(role, instance_count, instance_type, **kwargs)
         self.num_entity_vectors = num_entity_vectors
         self.vector_dim = vector_dim
         self.batch_metrics_publish_interval = batch_metrics_publish_interval

src/sagemaker/amazon/kmeans.py

@@ -51,8 +51,8 @@ class KMeans(AmazonAlgorithmEstimatorBase):
     def __init__(
         self,
         role,
-        train_instance_count,
-        train_instance_type,
+        instance_count,
+        instance_type,
         k,
         init_method=None,
         max_iterations=None,
@@ -103,9 +103,9 @@ def __init__(
                 endpoints use this role to access training data and model
                 artifacts. After the endpoint is created, the inference code
                 might use the IAM role, if accessing AWS resource.
-            train_instance_count (int): Number of Amazon EC2 instances to use
+            instance_count (int): Number of Amazon EC2 instances to use
                 for training.
-            train_instance_type (str): Type of EC2 instance to use for training,
+            instance_type (str): Type of EC2 instance to use for training,
                 for example, 'ml.c4.xlarge'.
             k (int): The number of clusters to produce.
             init_method (str): How to initialize cluster locations. One of
@@ -142,7 +142,7 @@ def __init__(
             :class:`~sagemaker.estimator.amazon_estimator.AmazonAlgorithmEstimatorBase` and
             :class:`~sagemaker.estimator.EstimatorBase`.
         """
-        super(KMeans, self).__init__(role, train_instance_count, train_instance_type, **kwargs)
+        super(KMeans, self).__init__(role, instance_count, instance_type, **kwargs)
         self.k = k
         self.init_method = init_method
         self.max_iterations = max_iterations

src/sagemaker/amazon/knn.py

@@ -63,8 +63,8 @@ class KNN(AmazonAlgorithmEstimatorBase):
     def __init__(
         self,
         role,
-        train_instance_count,
-        train_instance_type,
+        instance_count,
+        instance_type,
         k,
         sample_size,
         predictor_type,
@@ -105,8 +105,8 @@ def __init__(
                 endpoints use this role to access training data and model
                 artifacts. After the endpoint is created, the inference code
                 might use the IAM role, if accessing AWS resource.
-            train_instance_count:
-            train_instance_type (str): Type of EC2 instance to use for training,
+            instance_count:
+            instance_type (str): Type of EC2 instance to use for training,
                 for example, 'ml.c4.xlarge'.
             k (int): Required. Number of nearest neighbors.
             sample_size (int): Required. Number of data points to be sampled
@@ -136,7 +136,7 @@ def __init__(
             :class:`~sagemaker.estimator.EstimatorBase`.
         """
 
-        super(KNN, self).__init__(role, train_instance_count, train_instance_type, **kwargs)
+        super(KNN, self).__init__(role, instance_count, instance_type, **kwargs)
         self.k = k
         self.sample_size = sample_size
         self.predictor_type = predictor_type

src/sagemaker/amazon/lda.py

@@ -38,7 +38,7 @@ class LDA(AmazonAlgorithmEstimatorBase):
     def __init__(
         self,
         role,
-        train_instance_type,
+        instance_type,
         num_topics,
         alpha0=None,
         max_restarts=None,
@@ -92,7 +92,7 @@ def __init__(
                 endpoints use this role to access training data and model
                 artifacts. After the endpoint is created, the inference code
                 might use the IAM role, if accessing AWS resource.
-            train_instance_type (str): Type of EC2 instance to use for training,
+            instance_type (str): Type of EC2 instance to use for training,
                 for example, 'ml.c4.xlarge'.
             num_topics (int): The number of topics for LDA to find within the
                 data.
@@ -114,14 +114,14 @@ def __init__(
             :class:`~sagemaker.estimator.EstimatorBase`.
         """
         # this algorithm only supports single instance training
-        if kwargs.pop("train_instance_count", 1) != 1:
+        if kwargs.pop("instance_count", 1) != 1:
             print(
                 "LDA only supports single instance training. Defaulting to 1 {}.".format(
-                    train_instance_type
+                    instance_type
                 )
             )
 
-        super(LDA, self).__init__(role, 1, train_instance_type, **kwargs)
+        super(LDA, self).__init__(role, 1, instance_type, **kwargs)
         self.num_topics = num_topics
         self.alpha0 = alpha0
         self.max_restarts = max_restarts

src/sagemaker/amazon/linear_learner.py

@@ -120,8 +120,8 @@ class LinearLearner(AmazonAlgorithmEstimatorBase):
     def __init__(
         self,
         role,
-        train_instance_count,
-        train_instance_type,
+        instance_count,
+        instance_type,
         predictor_type,
         binary_classifier_model_selection_criteria=None,
         target_recall=None,
@@ -214,9 +214,9 @@ def __init__(
                 endpoints use this role to access training data and model
                 artifacts. After the endpoint is created, the inference code
                 might use the IAM role, if accessing AWS resource.
-            train_instance_count (int): Number of Amazon EC2 instances to use
+            instance_count (int): Number of Amazon EC2 instances to use
                 for training.
-            train_instance_type (str): Type of EC2 instance to use for training,
+            instance_type (str): Type of EC2 instance to use for training,
                 for example, 'ml.c4.xlarge'.
             predictor_type (str): The type of predictor to learn. Either
                 "binary_classifier" or "multiclass_classifier" or "regressor".
@@ -325,9 +325,7 @@ def __init__(
             :class:`~sagemaker.estimator.amazon_estimator.AmazonAlgorithmEstimatorBase` and
             :class:`~sagemaker.estimator.EstimatorBase`.
         """
-        super(LinearLearner, self).__init__(
-            role, train_instance_count, train_instance_type, **kwargs
-        )
+        super(LinearLearner, self).__init__(role, instance_count, instance_type, **kwargs)
         self.predictor_type = predictor_type
         self.binary_classifier_model_selection_criteria = binary_classifier_model_selection_criteria
         self.target_recall = target_recall
@@ -418,7 +416,7 @@ def _prepare_for_training(self, records, mini_batch_size=None, job_name=None):
 
         # mini_batch_size can't be greater than number of records or training job fails
         default_mini_batch_size = min(
-            self.DEFAULT_MINI_BATCH_SIZE, max(1, int(num_records / self.train_instance_count))
+            self.DEFAULT_MINI_BATCH_SIZE, max(1, int(num_records / self.instance_count))
         )
         mini_batch_size = mini_batch_size or default_mini_batch_size
         super(LinearLearner, self)._prepare_for_training(

src/sagemaker/amazon/ntm.py

@@ -59,8 +59,8 @@ class NTM(AmazonAlgorithmEstimatorBase):
     def __init__(
         self,
         role,
-        train_instance_count,
-        train_instance_type,
+        instance_count,
+        instance_type,
         num_topics,
         encoder_layers=None,
         epochs=None,
@@ -113,8 +113,8 @@ def __init__(
                 endpoints use this role to access training data and model
                 artifacts. After the endpoint is created, the inference code
                 might use the IAM role, if accessing AWS resource.
-            train_instance_count:
-            train_instance_type (str): Type of EC2 instance to use for training,
+            instance_count:
+            instance_type (str): Type of EC2 instance to use for training,
                 for example, 'ml.c4.xlarge'.
             num_topics (int): Required. The number of topics for NTM to find
                 within the data.
@@ -147,7 +147,7 @@ def __init__(
             :class:`~sagemaker.estimator.EstimatorBase`.
         """
 
-        super(NTM, self).__init__(role, train_instance_count, train_instance_type, **kwargs)
+        super(NTM, self).__init__(role, instance_count, instance_type, **kwargs)
         self.num_topics = num_topics
         self.encoder_layers = encoder_layers
         self.epochs = epochs