feat: remove D205 to enable PEP257 Docstring Conventions (#2045)

* doc: update docstrings to comply with PEP257

* Remove/Edit docstrings to be compatible with PEP257

* doc: modified docstrings to comply with PEP257 standards

* doc: modified docstrings to comply with PEP257 standards

* doc: modified docstrings to comply with PEP257 standards

* doc: modified docstrings to comply with PEP257 standards

* fix: fixed conflicts to comply with latest version

* fix: edited according to the changes requested

* doc: edit docstrings to add blank line

* fix: addessed changes

Co-authored-by: Ahsan <[email protected]>

Author: ahsan-z-khan

.pydocstylerc

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

src/sagemaker/algorithm.py

@@ -25,8 +25,9 @@
 
 
 class AlgorithmEstimator(EstimatorBase):
-    """A generic Estimator to train using any algorithm object (with an
-    ``algorithm_arn``). The Algorithm can be your own, or any Algorithm from AWS
+    """A generic Estimator to train using any algorithm object (with an ``algorithm_arn``).
+
+    The Algorithm can be your own, or any Algorithm from AWS
     Marketplace that you have a valid subscription for. This class will perform
     client-side validation on all the inputs.
     """
@@ -212,10 +213,7 @@ def validate_train_spec(self):
             )
 
     def set_hyperparameters(self, **kwargs):
-        """
-        Args:
-            **kwargs:
-        """
+        """Placeholder docstring"""
         for k, v in kwargs.items():
             value = self._validate_and_cast_hyperparameter(k, v)
             self.hyperparam_dict[k] = value
@@ -330,9 +328,9 @@ def transformer(
         role=None,
         volume_kms_key=None,
     ):
-        """Return a ``Transformer`` that uses a SageMaker Model based on the
-        training job. It reuses the SageMaker Session and base job name used by
-        the Estimator.
+        """Return a ``Transformer`` that uses a SageMaker Model based on the  training job.
+
+        It reuses the SageMaker Session and base job name used by the Estimator.
 
         Args:
             instance_count (int): Number of EC2 instances to use.
@@ -413,32 +411,19 @@ def _prepare_for_training(self, job_name=None):
         # Validate hyperparameters
         # an explicit call to set_hyperparameters() will also validate the hyperparameters
         # but it is possible that the user never called it.
-        """
-        Args:
-            job_name:
-        """
         self._validate_and_set_default_hyperparameters()
 
         super(AlgorithmEstimator, self)._prepare_for_training(job_name)
 
     def fit(self, inputs=None, wait=True, logs=True, job_name=None):
-        """
-        Args:
-            inputs:
-            wait:
-            logs:
-            job_name:
-        """
+        """Placeholder docstring"""
         if inputs:
             self._validate_input_channels(inputs)
 
         super(AlgorithmEstimator, self).fit(inputs, wait, logs, job_name)
 
     def _validate_input_channels(self, channels):
-        """
-        Args:
-            channels:
-        """
+        """Placeholder docstring"""
         train_spec = self.algorithm_spec["TrainingSpecification"]
         algorithm_name = self.algorithm_spec["AlgorithmName"]
         training_channels = {c["Name"]: c for c in train_spec["TrainingChannels"]}
@@ -456,11 +441,7 @@ def _validate_input_channels(self, channels):
                 raise ValueError("Required input channel: %s Was not provided." % (name))
 
     def _validate_and_cast_hyperparameter(self, name, v):
-        """
-        Args:
-            name:
-            v:
-        """
+        """Placeholder docstring"""
         algorithm_name = self.algorithm_spec["AlgorithmName"]
 
         if name not in self.hyperparameter_definitions:
@@ -514,11 +495,7 @@ def _parse_hyperparameters(self):
         return definitions
 
     def _hyperparameter_range_and_class(self, parameter_type, hyperparameter):
-        """
-        Args:
-            parameter_type:
-            hyperparameter:
-        """
+        """Placeholder docstring."""
         if parameter_type in self._hyperpameters_with_range:
             range_name = parameter_type + "ParameterRangeSpecification"
 
@@ -559,10 +536,7 @@ def _hyperparameter_range_and_class(self, parameter_type, hyperparameter):
         return parameter_class, parameter_range
 
     def _algorithm_training_input_modes(self, training_channels):
-        """
-        Args:
-            training_channels:
-        """
+        """Placeholder docstring"""
         current_input_modes = {"File", "Pipe"}
         for channel in training_channels:
             supported_input_modes = set(channel["SupportedInputModes"])
@@ -572,8 +546,7 @@ def _algorithm_training_input_modes(self, training_channels):
 
     @classmethod
     def _prepare_init_params_from_job_description(cls, job_details, model_channel_name=None):
-        """Convert the job description to init params that can be handled by the
-        class constructor
+        """Convert the job description to init params that can be handled by the class constructor.
 
         Args:
             job_details (dict): the returned job details from a DescribeTrainingJob

src/sagemaker/amazon/amazon_estimator.py

@@ -32,8 +32,9 @@
 
 
 class AmazonAlgorithmEstimatorBase(EstimatorBase):
-    """Base class for Amazon first-party Estimator implementations. This class
-    isn't intended to be instantiated directly.
+    """Base class for Amazon first-party Estimator implementations.
+
+    This class isn't intended to be instantiated directly.
     """
 
     feature_dim = hp("feature_dim", validation.gt(0), data_type=int)
@@ -110,10 +111,7 @@ def data_location(self):
 
     @data_location.setter
     def data_location(self, data_location):
-        """
-        Args:
-            data_location:
-        """
+        """Placeholder docstring"""
         if not data_location.startswith("s3://"):
             raise ValueError(
                 'Expecting an S3 URL beginning with "s3://". Got "{}"'.format(data_location)
@@ -124,8 +122,7 @@ def data_location(self, data_location):
 
     @classmethod
     def _prepare_init_params_from_job_description(cls, job_details, model_channel_name=None):
-        """Convert the job description to init params that can be handled by the
-        class constructor
+        """Convert the job description to init params that can be handled by the class constructor.
 
         Args:
             job_details: the returned job details from a describe_training_job
@@ -245,8 +242,7 @@ def fit(
             self.latest_training_job.wait(logs=logs)
 
     def record_set(self, train, labels=None, channel="train", encrypt=False):
-        """Build a :class:`~RecordSet` from a numpy :class:`~ndarray` matrix and
-        label vector.
+        """Build a :class:`~RecordSet` from a numpy :class:`~ndarray` matrix and label vector.
 
         For the 2D ``ndarray`` ``train``, each row is converted to a
         :class:`~Record` object. The vector is stored in the "values" entry of
@@ -301,8 +297,7 @@ class RecordSet(object):
     def __init__(
         self, s3_data, num_records, feature_dim, s3_data_type="ManifestFile", channel="train"
     ):
-        """A collection of Amazon :class:~`Record` objects serialized and stored
-        in S3.
+        """A collection of Amazon :class:~`Record` objects serialized and stored in S3.
 
         Args:
             s3_data (str): The S3 location of the training data
@@ -328,9 +323,8 @@ def __repr__(self):
         return str((RecordSet, self.__dict__))
 
     def data_channel(self):
-        """Return a dictionary to represent the training data in a channel for
-        use with ``fit()``
-        """
+        """Returns dictionary to represent the training data in a channel to use with ``fit()``."""
+
         return {self.channel: self.records_s3_input()}
 
     def records_s3_input(self):
@@ -341,9 +335,7 @@ def records_s3_input(self):
 
 
 class FileSystemRecordSet(object):
-    """Amazon SageMaker channel configuration for a file system data source
-    for Amazon algorithms.
-    """
+    """Amazon SageMaker channel configuration for file system data source for Amazon algorithms."""
 
     def __init__(
         self,
@@ -390,11 +382,7 @@ def data_channel(self):
 
 
 def _build_shards(num_shards, array):
-    """
-    Args:
-        num_shards:
-        array:
-    """
+    """Placeholder docstring"""
     if num_shards < 1:
         raise ValueError("num_shards must be >= 1")
     shard_size = int(array.shape[0] / num_shards)
@@ -408,8 +396,9 @@ def _build_shards(num_shards, array):
 def upload_numpy_to_s3_shards(
     num_shards, s3, bucket, key_prefix, array, labels=None, encrypt=False
 ):
-    """Upload the training ``array`` and ``labels`` arrays to ``num_shards`` S3
-    objects, stored in "s3:// ``bucket`` / ``key_prefix`` /". Optionally
+    """Upload the training ``array`` and ``labels`` arrays to ``num_shards``.
+
+    S3 objects, stored in "s3:// ``bucket`` / ``key_prefix`` /". Optionally
     ``encrypt`` the S3 objects using AES-256.
 
     Args:

src/sagemaker/amazon/common.py

@@ -92,12 +92,7 @@ def deserialize(self, data, content_type):
 
 
 def _write_feature_tensor(resolved_type, record, vector):
-    """
-    Args:
-        resolved_type:
-        record:
-        vector:
-    """
+    """Placeholder Docstring"""
     if resolved_type == "Int32":
         record.features["values"].int32_tensor.values.extend(vector)
     elif resolved_type == "Float64":
@@ -107,12 +102,7 @@ def _write_feature_tensor(resolved_type, record, vector):
 
 
 def _write_label_tensor(resolved_type, record, scalar):
-    """
-    Args:
-        resolved_type:
-        record:
-        scalar:
-    """
+    """Placeholder Docstring"""
     if resolved_type == "Int32":
         record.label["values"].int32_tensor.values.extend([scalar])
     elif resolved_type == "Float64":
@@ -122,12 +112,7 @@ def _write_label_tensor(resolved_type, record, scalar):
 
 
 def _write_keys_tensor(resolved_type, record, vector):
-    """
-    Args:
-        resolved_type:
-        record:
-        vector:
-    """
+    """Placeholder Docstring"""
     if resolved_type == "Int32":
         record.features["values"].int32_tensor.keys.extend(vector)
     elif resolved_type == "Float64":
@@ -137,12 +122,7 @@ def _write_keys_tensor(resolved_type, record, vector):
 
 
 def _write_shape(resolved_type, record, scalar):
-    """
-    Args:
-        resolved_type:
-        record:
-        scalar:
-    """
+    """Placeholder Docstring"""
     if resolved_type == "Int32":
         record.features["values"].int32_tensor.shape.extend([scalar])
     elif resolved_type == "Float64":
@@ -285,10 +265,7 @@ def _write_recordio(f, data):
 
 
 def read_recordio(f):
-    """
-    Args:
-        f:
-    """
+    """Placeholder Docstring"""
     while True:
         try:
             (read_kmagic,) = struct.unpack("I", f.read(4))
@@ -303,10 +280,7 @@ def read_recordio(f):
 
 
 def _resolve_type(dtype):
-    """
-    Args:
-        dtype:
-    """
+    """Placeholder Docstring"""
     if dtype == np.dtype(int):
         return "Int32"
     if dtype == np.dtype(float):

src/sagemaker/amazon/factorization_machines.py

@@ -112,8 +112,7 @@ def __init__(
         factors_init_value=None,
         **kwargs
     ):
-        """Factorization Machines is :class:`Estimator` for general-purpose
-        supervised learning.
+        """Factorization Machines is :class:`Estimator` for general-purpose supervised learning.
 
         Amazon SageMaker Factorization Machines is a general-purpose
         supervised learning algorithm that you can use for both classification
@@ -247,8 +246,9 @@ def __init__(
         self.factors_init_value = factors_init_value
 
     def create_model(self, vpc_config_override=VPC_CONFIG_DEFAULT, **kwargs):
-        """Return a :class:`~sagemaker.amazon.FactorizationMachinesModel`
-        referencing the latest s3 model data produced by this Estimator.
+        """Return a :class:`~sagemaker.amazon.FactorizationMachinesModel`.
+
+        It references the latest s3 model data produced by this Estimator.
 
         Args:
             vpc_config_override (dict[str, list[str]]): Optional override for VpcConfig set on
@@ -267,8 +267,7 @@ def create_model(self, vpc_config_override=VPC_CONFIG_DEFAULT, **kwargs):
 
 
 class FactorizationMachinesPredictor(Predictor):
-    """Performs binary-classification or regression prediction from input
-    vectors.
+    """Performs binary-classification or regression prediction from input vectors.
 
     The implementation of
     :meth:`~sagemaker.predictor.Predictor.predict` in this
@@ -292,6 +291,8 @@ def __init__(
         deserializer=RecordDeserializer(),
     ):
         """
+        Initialization for FactorizationMachinesPredictor class.
+
         Args:
             endpoint_name (str): Name of the Amazon SageMaker endpoint to which
                 requests are sent.
@@ -314,12 +315,15 @@ def __init__(
 
 class FactorizationMachinesModel(Model):
     """Reference S3 model data created by FactorizationMachines estimator.
+
     Calling :meth:`~sagemaker.model.Model.deploy` creates an Endpoint and
     returns :class:`FactorizationMachinesPredictor`.
     """
 
     def __init__(self, model_data, role, sagemaker_session=None, **kwargs):
         """
+        Initialization for FactorizationMachinesModel class.
+
         Args:
             model_data (str): The S3 location of a SageMaker model data
                 ``.tar.gz`` file.