Add a check for S3 paths being incorrectly passed as an entry point (#500)

Author: laurenyu

src/sagemaker/estimator.py

@@ -740,7 +740,7 @@ def __init__(self, entry_point, source_dir=None, hyperparameters=None, enable_cl
         """Base class initializer. Subclasses which override ``__init__`` should invoke ``super()``
 
         Args:
-            entry_point (str): Path (absolute or relative) to the Python source file which should be executed
+            entry_point (str): Path (absolute or relative) to the local Python source file which should be executed
                 as the entry point to training. This should be compatible with either Python 2.7 or Python 3.5.
             source_dir (str): Path (absolute or relative) to a directory with any other training
                 source code dependencies aside from tne entry point file (default: None). Structure within this
@@ -779,9 +779,11 @@ def __init__(self, entry_point, source_dir=None, hyperparameters=None, enable_cl
             **kwargs: Additional kwargs passed to the ``EstimatorBase`` constructor.
         """
         super(Framework, self).__init__(**kwargs)
+        if entry_point.startswith('s3://'):
+            raise ValueError('Invalid entry point script: {}. Must be a path to a local file.'.format(entry_point))
+        self.entry_point = entry_point
         self.source_dir = source_dir
         self.dependencies = dependencies or []
-        self.entry_point = entry_point
         if enable_cloudwatch_metrics:
             warnings.warn('enable_cloudwatch_metrics is now deprecated and will be removed in the future.',
                           DeprecationWarning)

tests/unit/test_estimator.py

@@ -171,6 +171,14 @@ def test_framework_all_init_args(sagemaker_session):
                     'metric_definitions': [{'Name': 'validation-rmse', 'Regex': 'validation-rmse=(\\d+)'}]}
 
 
+def test_framework_init_s3_entry_point_invalid(sagemaker_session):
+    with pytest.raises(ValueError) as error:
+        DummyFramework('s3://remote-script-because-im-mistaken', role=ROLE,
+                       sagemaker_session=sagemaker_session, train_instance_count=INSTANCE_COUNT,
+                       train_instance_type=INSTANCE_TYPE)
+    assert 'Must be a path to a local file' in str(error)
+
+
 def test_sagemaker_s3_uri_invalid(sagemaker_session):
     with pytest.raises(ValueError) as error:
         t = DummyFramework(entry_point=SCRIPT_PATH, role=ROLE, sagemaker_session=sagemaker_session,