change: include additional docstyle improvements (#1889)

Co-authored-by: Ajay Karpur <[email protected]>

Author: metrizable

.pydocstylerc

@@ -1,4 +1,4 @@
 [pydocstyle]
 inherit = false
-ignore = D104,D107,D202,D203,D205,D209,D212,D213,D214,D400,D401,D404,D406,D407,D411,D413,D414,D415,D417
+ignore = D104,D107,D202,D203,D205,D212,D213,D214,D400,D401,D404,D406,D407,D411,D413,D414,D415,D417
 match = (?!record_pb2).*\.py

src/sagemaker/amazon/factorization_machines.py

@@ -30,7 +30,8 @@ class FactorizationMachines(AmazonAlgorithmEstimatorBase):
     Factorization Machines combine the advantages of Support Vector Machines
     with factorization models. It is an extension of a linear model that is
     designed to capture interactions between features within high dimensional
-    sparse datasets economically."""
+    sparse datasets economically.
+    """
 
     repo_name = "factorization-machines"
     repo_version = 1

src/sagemaker/amazon/ipinsights.py

@@ -29,7 +29,8 @@ class IPInsights(AmazonAlgorithmEstimatorBase):
     """An unsupervised learning algorithm that learns the usage patterns for IPv4 addresses.
 
     It is designed to capture associations between IPv4 addresses and various entities, such
-    as user IDs or account numbers."""
+    as user IDs or account numbers.
+    """
 
     repo_name = "ipinsights"
     repo_version = 1

src/sagemaker/amazon/kmeans.py

@@ -29,7 +29,8 @@ class KMeans(AmazonAlgorithmEstimatorBase):
 
     As the result of KMeans, members of a group are as similar as possible to one another and as
     different as possible from members of other groups. You define the attributes that you want
-    the algorithm to use to determine similarity."""
+    the algorithm to use to determine similarity.
+    """
 
     repo_name = "kmeans"
     repo_version = 1

src/sagemaker/amazon/knn.py

@@ -30,7 +30,8 @@ class KNN(AmazonAlgorithmEstimatorBase):
     For classification problems, the algorithm queries the k points that are closest to the sample
     point and returns the most frequently used label of their class as the predicted label. For
     regression problems, the algorithm queries the k closest points to the sample point and returns
-    the average of their feature values as the predicted value."""
+    the average of their feature values as the predicted value.
+    """
 
     repo_name = "knn"
     repo_version = 1

src/sagemaker/amazon/lda.py

@@ -30,7 +30,8 @@ class LDA(AmazonAlgorithmEstimatorBase):
     LDA is most commonly used to discover a
     user-specified number of topics shared by documents within a text corpus. Here each
     observation is a document, the features are the presence (or occurrence count) of each
-    word, and the categories are the topics."""
+    word, and the categories are the topics.
+    """
 
     repo_name = "lda"
     repo_version = 1

src/sagemaker/amazon/linear_learner.py

@@ -32,7 +32,8 @@ class LinearLearner(AmazonAlgorithmEstimatorBase):
     For multiclass classification problems, the labels must be from 0 to num_classes - 1. For
     regression problems, y is a real number. The algorithm learns a linear function, or, for
     classification problems, a linear threshold function, and maps a vector x to an approximation
-    of the label y."""
+    of the label y.
+    """
 
     repo_name = "linear-learner"
     repo_version = 1

src/sagemaker/amazon/ntm.py

@@ -25,11 +25,12 @@
 
 
 class NTM(AmazonAlgorithmEstimatorBase):
-    """An unsupervised learning algorithm used to organize a corpus of documents into topics
+    """An unsupervised learning algorithm used to organize a corpus of documents into topics.
 
     The resulting topics contain word groupings based on their statistical distribution.
     Documents that contain frequent occurrences of words such as "bike", "car", "train",
-    "mileage", and "speed" are likely to share a topic on "transportation" for example."""
+    "mileage", and "speed" are likely to share a topic on "transportation" for example.
+    """
 
     repo_name = "ntm"
     repo_version = 1

src/sagemaker/amazon/object2vec.py

@@ -24,7 +24,8 @@
 
 
 def _list_check_subset(valid_super_list):
-    """
+    """Provides a function to check validity of list subset.
+
     Args:
         valid_super_list:
     """
@@ -45,7 +46,8 @@ class Object2Vec(AmazonAlgorithmEstimatorBase):
 
     It can learn low-dimensional dense embeddings of high-dimensional objects. The embeddings
     are learned in a way that preserves the semantics of the relationship between pairs of
-    objects in the original space in the embedding space."""
+    objects in the original space in the embedding space.
+    """
 
     repo_name = "object2vec"
     repo_version = 1

src/sagemaker/amazon/pca.py

@@ -28,7 +28,8 @@ class PCA(AmazonAlgorithmEstimatorBase):
     """An unsupervised machine learning algorithm to reduce feature dimensionality.
 
     As a result, number of features within a dataset is reduced but the dataset still
-    retain as much information as possible."""
+    retain as much information as possible.
+    """
 
     repo_name = "pca"
     repo_version = 1

src/sagemaker/amazon/randomcutforest.py

@@ -29,7 +29,8 @@ class RandomCutForest(AmazonAlgorithmEstimatorBase):
 
     These are observations which diverge from otherwise well-structured or patterned data.
     Anomalies can manifest as unexpected spikes in time series data, breaks in periodicity,
-    or unclassifiable data points."""
+    or unclassifiable data points.
+    """
 
     repo_name = "randomcutforest"
     repo_version = 1

src/sagemaker/automl/automl.py

@@ -26,7 +26,7 @@
 
 
 class AutoML(object):
-    """A class for creating and interacting with SageMaker AutoML jobs"""
+    """A class for creating and interacting with SageMaker AutoML jobs."""
 
     def __init__(
         self,
@@ -178,14 +178,14 @@ def describe_auto_ml_job(self, job_name=None):
         return self._auto_ml_job_desc
 
     def best_candidate(self, job_name=None):
-        """Returns the best candidate of an AutoML job for a given name
+        """Returns the best candidate of an AutoML job for a given name.
 
         Args:
             job_name (str): The name of the AutoML job. If None, will use object's
                 _current_auto_ml_job_name.
 
         Returns:
-            dict: a dictionary with information of the best candidate
+            dict: A dictionary with information of the best candidate.
         """
         if self._best_candidate:
             return self._best_candidate
@@ -229,7 +229,7 @@ def list_candidates(
                 between 1 to 100. Default to None. If None, will return all the candidates.
 
         Returns:
-            list: A list of dictionaries with candidates information
+            list: A list of dictionaries with candidates information.
         """
         if job_name is None:
             job_name = self.current_job_name
@@ -262,8 +262,7 @@ def create_model(
         predictor_cls=None,
         inference_response_keys=None,
     ):
-        """Creates a model from a given candidate or the best candidate
-        from the automl job
+        """Creates a model from a given candidate or the best candidate from the job.
 
         Args:
             name (str): The pipeline model name.
@@ -289,7 +288,7 @@ def create_model(
                 keys will dictate the content order in the response.
 
         Returns:
-            PipelineModel object
+            PipelineModel object.
         """
         sagemaker_session = sagemaker_session or self.sagemaker_session
 
@@ -351,7 +350,7 @@ def deploy(
         predictor_cls=None,
         inference_response_keys=None,
     ):
-        """Deploy a candidate to a SageMaker Inference Pipeline and return a Predictor
+        """Deploy a candidate to a SageMaker Inference Pipeline.
 
         Args:
             initial_instance_count (int): The initial number of instances to run
@@ -490,12 +489,14 @@ def _get_supported_inference_keys(cls, container, default=None):
 
     @classmethod
     def _check_inference_keys(cls, inference_response_keys, containers):
-        """Given an inference container list, checks if the pipeline supports the
-        requested inference keys
+        """Checks if the pipeline supports the inference keys for the containers.
+
+        Given inference response keys and list of containers, determines whether
+        the keys are supported.
 
         Args:
-            inference_response_keys (list): List of keys for inference response content
-            containers (list): list of inference container
+            inference_response_keys (list): List of keys for inference response content.
+            containers (list): list of inference container.
 
         Raises:
             ValueError, if one or more keys in inference_response_keys are not supported
@@ -527,8 +528,10 @@ def _check_inference_keys(cls, inference_response_keys, containers):
 
     @classmethod
     def validate_and_update_inference_response(cls, inference_containers, inference_response_keys):
-        """Validates the requested inference keys and updates inference containers to emit the
-        requested content in the inference response.
+        """Validates the requested inference keys and updates response content.
+
+        On validation, also updates the inference containers to emit appropriate response
+        content in the inference response.
 
         Args:
             inference_containers (list): list of inference containers
@@ -570,8 +573,10 @@ def validate_and_update_inference_response(cls, inference_containers, inference_
 
 
 class AutoMLInput(object):
-    """Accepts parameters that specify an S3 input for an auto ml job and provides
-    a method to turn those parameters into a dictionary."""
+    """Accepts parameters that specify an S3 input for an auto ml job
+
+    Provides a method to turn those parameters into a dictionary.
+    """
 
     def __init__(self, inputs, target_attribute_name, compression=None):
         """Convert an S3 Uri or a list of S3 Uri to an AutoMLInput object.

src/sagemaker/debugger.py

@@ -320,11 +320,15 @@ def _to_request_dict(self):
 
 
 class TensorBoardOutputConfig(object):
-    """TensorBoardOutputConfig provides options to customize
-    debugging visualization using TensorBoard."""
+    """A configuration object to provide debugging customizations.
+
+    A configuration specific to TensorBoard output, that provides options
+    to customize debugging visualizations using TensorBoard.
+    """
 
     def __init__(self, s3_output_path, container_local_output_path=None):
         """Initialize an instance of TensorBoardOutputConfig.
+
         TensorBoardOutputConfig provides options to customize
         debugging visualization using TensorBoard.
 
@@ -336,8 +340,7 @@ def __init__(self, s3_output_path, container_local_output_path=None):
         self.container_local_output_path = container_local_output_path
 
     def _to_request_dict(self):
-        """Generates a request dictionary using the parameters provided
-        when initializing the object.
+        """Generates a request dictionary using the instances attributes.
 
         Returns:
             dict: An portion of an API request as a dictionary.