doc: modified docstrings to comply with PEP257 standards

Author: ahsan-z-khan

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/analytics.py

@@ -10,7 +10,7 @@
 # distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF
 # ANY KIND, either express or implied. See the License for the specific
 # language governing permissions and limitations under the License.
-"""Placeholder docstring."""
+"""Placeholder docstring"""
 from __future__ import print_function, absolute_import
 
 from abc import ABCMeta, abstractmethod
@@ -38,6 +38,7 @@
 
 class AnalyticsMetricsBase(with_metaclass(ABCMeta, object)):
     """Base class for tuning job or training job analytics classes.
+
     Understands common functionality like persistence and caching.
     """
 
@@ -54,8 +55,9 @@ def export_csv(self, filename):
 
     def dataframe(self, force_refresh=False):
         """A pandas dataframe with lots of interesting results about this object.
-        Created by calling SageMaker List and Describe APIs and
-        converting them into a convenient tabular summary.
+
+        Created by calling SageMaker List and Describe APIs and converting them into a
+        convenient tabular summary.
 
         Args:
             force_refresh (bool): Set to True to fetch the latest data from
@@ -73,8 +75,8 @@ def _fetch_dataframe(self):
 
     def clear_cache(self):
         """Clear the object of all local caches of API methods.
-        So that the next time any properties are accessed they will be refreshed from the
-        service.
+
+        So that the next time any properties are accessed they will be refreshed from the service.
         """
         self._dataframe = None
 
@@ -103,7 +105,7 @@ def __init__(self, hyperparameter_tuning_job_name, sagemaker_session=None):
 
     @property
     def name(self):
-        """Name of the HyperparameterTuningJob being analyzed."""
+        """Name of the HyperparameterTuningJob being analyzed"""
         return self._tuning_job_name
 
     def __repr__(self):
@@ -156,6 +158,7 @@ def reshape(training_summary):
     @property
     def tuning_ranges(self):
         """A dictionary describing the ranges of all tuned hyperparameters.
+
         The keys are the names of the hyperparameter, and the values are the ranges.
 
         The output can take one of two forms:
@@ -207,7 +210,7 @@ def tuning_ranges(self):
         }
 
     def _prepare_parameter_ranges(self, parameter_ranges):
-        """Convert parameter ranges a dictionary using the parameter range names as the keys."""
+        """Convert parameter ranges a dictionary using the parameter range names as the keys"""
         out = {}
         for _, ranges in parameter_ranges.items():
             for param in ranges:
@@ -313,7 +316,7 @@ def __init__(
 
     @property
     def name(self):
-        """Name of the TrainingJob being analyzed."""
+        """Name of the TrainingJob being analyzed"""
         return self._training_job_name
 
     def __repr__(self):
@@ -360,7 +363,7 @@ def _fetch_dataframe(self):
         return pd.DataFrame(self._data)
 
     def _fetch_metric(self, metric_name):
-        """Fetch all the values of a named metric, and add them to _data.
+        """Fetch all the values of a named metric, and add them to _data
 
         Args:
             metric_name: The metric name to fetch.
@@ -564,6 +567,7 @@ def clear_cache(self):
 
     def _reshape_parameters(self, parameters):
         """Reshape trial component parameters to a pandas column.
+
         Args:
             parameters: trial component parameters
         Returns:
@@ -578,6 +582,7 @@ def _reshape_parameters(self, parameters):
 
     def _reshape_metrics(self, metrics):
         """Reshape trial component metrics to a pandas column.
+
         Args:
             metrics: trial component metrics
         Returns:
@@ -598,6 +603,7 @@ def _reshape_metrics(self, metrics):
 
     def _reshape_artifacts(self, artifacts, _artifact_names):
         """Reshape trial component input/output artifacts to a pandas column.
+
         Args:
             artifacts: trial component input/output artifacts
         Returns:
@@ -631,6 +637,7 @@ def _reshape_parents(self, parents):
 
     def _reshape(self, trial_component):
         """Reshape trial component data to pandas columns.
+
         Args:
             trial_component: dict representing a trial component
         Returns:
@@ -660,9 +667,8 @@ def _reshape(self, trial_component):
         return out
 
     def _fetch_dataframe(self):
-        """Return a pandas dataframe with all the trial_components,
-        along with their parameters and metrics.
-        """
+        """Return a pandas dataframe includes all the trial_components."""
+
         df = pd.DataFrame([self._reshape(component) for component in self._get_trial_components()])
         return df