fix: minor processing changes (instance_count + docs) (#279)

* fix: require instance_count
* fix: include output_name in generated ProcessingOutput s3 uri
* doc: clarify default s3 URIs

Author: knakad

src/sagemaker/processing.py

@@ -250,6 +250,7 @@ def _normalize_outputs(self, outputs=None):
                         self.sagemaker_session.default_bucket(),
                         self._current_job_name,
                         "output",
+                        output.output_name,
                     )
                     output.destination = s3_uri
                 normalized_outputs.append(output)
@@ -402,7 +403,7 @@ def _get_user_script_name(self, code):
         """
         if os.path.isdir(code) is None or not os.path.splitext(code)[1]:
             raise ValueError(
-                """You cannot provide a directory. Please package your code inside of a .whl
+                """code must be a file, not a directory. Please package your code inside of a .whl
                 file and pass that in, instead.
                 """
             )
@@ -593,7 +594,9 @@ def __init__(
         to turn those parameters into a dictionary.
 
         Args:
-            source (str): The source for the input.
+            source (str): The source for the input. If a local path is provided, it will
+                automatically be uploaded to s3 under:
+                "s3://<default-bucket-name>/<job-name>/input/<input-name>".
             destination (str): The destination of the input.
             input_name (str): The user-provided name for the input. If a name
                 is not provided, one will be generated (eg. "input-1").
@@ -647,7 +650,8 @@ def __init__(self, source, destination=None, output_name=None, s3_upload_mode="E
         Args:
             source (str): The source for the output.
             destination (str): The destination of the output. If a destination
-                is not provided, one will be generated (eg. "s3://bucket/job_name/output").
+                is not provided, one will be generated:
+                 "s3://<default-bucket-name>/<job-name>/output/<output-name>".
             output_name (str): The name of the output. If a name
                 is not provided, one will be generated (eg. "output-1").
             s3_upload_mode (str): Valid options are "EndOfJob" or "Continuous".

src/sagemaker/sklearn/processing.py

@@ -32,7 +32,7 @@ def __init__(
         role,
         command,
         instance_type,
-        instance_count=1,
+        instance_count,
         py_version="py3",
         volume_size_in_gb=30,
         volume_kms_key=None,

tests/integ/test_processing.py

@@ -66,6 +66,7 @@ def test_sklearn(sagemaker_session, sklearn_full_version, cpu_instance_type):
         framework_version=sklearn_full_version,
         role=ROLE,
         instance_type=cpu_instance_type,
+        instance_count=1,
         command=["python3"],
         sagemaker_session=sagemaker_session,
         max_runtime_in_seconds=3600,  # TODO-reinvent-2019: REMOVE
@@ -103,6 +104,7 @@ def test_sklearn_with_customizations(
         role=ROLE,
         command=["python3"],
         instance_type=cpu_instance_type,
+        instance_count=1,
         py_version="py3",
         volume_size_in_gb=100,
         volume_kms_key=None,
@@ -178,6 +180,7 @@ def test_sklearn_with_no_inputs_or_outputs(
         role=ROLE,
         command=["python3"],
         instance_type=cpu_instance_type,
+        instance_count=1,
         py_version="py3",
         volume_size_in_gb=100,
         volume_kms_key=None,

tests/unit/test_processing.py

@@ -49,6 +49,7 @@ def test_sklearn(sagemaker_session):
         command=["python3"],
         role=ROLE,
         instance_type="ml.m4.xlarge",
+        instance_count=1,
         sagemaker_session=sagemaker_session,
     )
 
@@ -117,6 +118,7 @@ def test_sklearn_with_no_inputs(sagemaker_session):
         role=ROLE,
         command=["python3"],
         instance_type="ml.m4.xlarge",
+        instance_count=1,
         sagemaker_session=sagemaker_session,
     )
 
@@ -169,6 +171,7 @@ def test_sklearn_with_all_customizations(sagemaker_session):
         role=ROLE,
         command=["python3"],
         instance_type="ml.m4.xlarge",
+        instance_count=1,
         py_version="py3",
         volume_size_in_gb=100,
         volume_kms_key=None,