Merge branch 'pr-framework-processor' into pr-framework-processor-round-02

Author: verdimrc

src/sagemaker/processing.py

@@ -23,6 +23,7 @@
 import logging
 from textwrap import dedent
 from typing import Dict, List, Optional
+
 import attr
 
 from six.moves.urllib.parse import urlparse

src/sagemaker/sklearn/processing.py

@@ -81,3 +81,64 @@ def __init__(
             tags,
             network_config,
         )
+
+
+class SKLearnProcessorAlt(FrameworkProcessor):
+    """Handles Amazon SageMaker processing tasks for jobs using scikit-learn containers."""
+
+    estimator_cls = SKLearn
+
+    def __init__(
+        self,
+        framework_version,  # New arg
+        s3_prefix,  # New arg
+        role,
+        instance_count,
+        instance_type,
+        py_version="py3",  # New kwarg
+        image_uri=None,
+        volume_size_in_gb=30,
+        volume_kms_key=None,
+        output_kms_key=None,
+        max_runtime_in_seconds=None,
+        base_job_name=None,
+        sagemaker_session=None,
+        env=None,
+        tags=None,
+        network_config=None,
+    ):
+        """This processor executes a Python script in a scikit-learn execution environment.
+
+        This class has an 'Alt' suffix to denote it as an alternative to built-in
+        ``sagemaker.sklearn.processing.SKLearnProcessor``.
+
+        Unless ``image_uri`` is specified, the scikit-learn environment is an
+        Amazon-built Docker container that executes functions defined in the supplied
+        ``entry_point`` Python script.
+
+        The arguments have the exact same meaning as in ``FrameworkProcessor``.
+
+        .. tip::
+
+            You can find additional parameters for initializing this class at
+            :class:`~smallmatter.ds.FrameworkProcessor`.
+        """
+        super().__init__(
+            self.estimator_cls,
+            framework_version,
+            s3_prefix,
+            role,
+            instance_count,
+            instance_type,
+            py_version,
+            image_uri,
+            volume_size_in_gb,
+            volume_kms_key,
+            output_kms_key,
+            max_runtime_in_seconds,
+            base_job_name,
+            sagemaker_session,
+            env,
+            tags,
+            network_config,
+        )