Don't try to invoke str() on Python 2 unicode strings (aws#42)

Author: laurenyu

src/sagemaker/tuner.py

@@ -20,7 +20,7 @@
 from sagemaker.estimator import Framework
 from sagemaker.job import _Job
 from sagemaker.session import Session
-from sagemaker.utils import base_name_from_image, name_from_base
+from sagemaker.utils import base_name_from_image, name_from_base, to_str
 
 # TODO: probably move these somewhere to Amazon Estimator land after
 # the circular dependency issue is resolved
@@ -45,8 +45,8 @@ def __init__(self, min_value, max_value):
 
     def as_tuning_range(self, name):
         return {'Name': name,
-                'MinValue': str(self.min_value),
-                'MaxValue': str(self.max_value)}
+                'MinValue': to_str(self.min_value),
+                'MaxValue': to_str(self.max_value)}
 
 
 class ContinuousParameter(_ParameterRange):
@@ -61,9 +61,9 @@ class CategoricalParameter(_ParameterRange):
 
     def __init__(self, values):
         if isinstance(values, list):
-            self.values = [str(v) for v in values]
+            self.values = [to_str(v) for v in values]
         else:
-            self.values = [str(values)]
+            self.values = [to_str(values)]
 
     def as_tuning_range(self, name):
         return {'Name': name,
@@ -108,8 +108,7 @@ def __init__(self, estimator, objective_metric_name, hyperparameter_ranges, metr
         self._validate_parameter_ranges()
 
     def prepare_for_training(self):
-        # TODO: Change this so that it can handle unicode in Python 2
-        self.static_hyperparameters = {str(k): str(v) for (k, v) in self.estimator.hyperparameters().items()}
+        self.static_hyperparameters = {to_str(k): to_str(v) for (k, v) in self.estimator.hyperparameters().items()}
         for hyperparameter_name in self._hyperparameter_ranges.keys():
             self.static_hyperparameters.pop(hyperparameter_name, None)
 

src/sagemaker/utils.py

@@ -12,6 +12,7 @@
 # language governing permissions and limitations under the License.
 from __future__ import absolute_import
 
+import sys
 import time
 
 import re
@@ -100,6 +101,25 @@ def get_config_value(key_path, config):
     return current_section
 
 
+def to_str(value):
+    """Convert the input to a string, unless it is a unicode string in Python 2.
+
+    Unicode strings are supported as native strings in Python 3, but ``str()`` cannot be
+    invoked on unicode strings in Python 2, so we need to check for that case when
+    converting user-specified values to strings.
+
+    Args:
+        value: The value to convert to a string.
+
+    Returns:
+        str or unicode: The string representation of the value or the unicode string itself.
+    """
+    if sys.version_info.major < 3 and isinstance(value, unicode):  # noqa: F821
+        return value
+    else:
+        return str(value)
+
+
 class DeferredError(object):
     """Stores an exception and raises it at a later time anytime this
     object is accessed in any way.  Useful to allow soft-dependencies on imports,

tests/unit/test_utils.py

@@ -1,3 +1,5 @@
+# -*- coding: utf-8 -*-
+
 # Copyright 2018 Amazon.com, Inc. or its affiliates. All Rights Reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License"). You
@@ -15,7 +17,7 @@
 import pytest
 from mock import patch
 
-from sagemaker.utils import get_config_value, name_from_base, DeferredError
+from sagemaker.utils import get_config_value, name_from_base, to_str, DeferredError
 
 NAME = 'base_name'
 
@@ -65,3 +67,13 @@ def test_name_from_base(sagemaker_timestamp):
 def test_name_from_base_short(sagemaker_short_timestamp):
     name_from_base(NAME, short=True)
     assert sagemaker_short_timestamp.called_once
+
+
+def test_to_str_with_native_string():
+    value = 'some string'
+    assert to_str(value) == value
+
+
+def test_to_str_with_unicode_string():
+    value = u'åñøthér strîng'
+    assert to_str(value) == value