[spark] branch master updated: [SPARK-25351][PYTHON][TEST][FOLLOWUP] Fix test assertions to be consistent

[gu...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

gurwls223 pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git


The following commit(s) were added to refs/heads/master by this push:
     new 8bbb666  [SPARK-25351][PYTHON][TEST][FOLLOWUP] Fix test assertions to be consistent
8bbb666 is described below

commit 8bbb666622e042c1533da294ac7b504b6aaa694a
Author: Bryan Cutler <cu...@gmail.com>
AuthorDate: Thu May 28 10:27:15 2020 +0900

    [SPARK-25351][PYTHON][TEST][FOLLOWUP] Fix test assertions to be consistent
    
    ### What changes were proposed in this pull request?
    Followup to make assertions from recent test consistent with the rest of the module
    
    ### Why are the changes needed?
    
    Better to use assertions from `unittest` and be consistent
    
    ### Does this PR introduce _any_ user-facing change?
    
    No
    
    ### How was this patch tested?
    
    Existing tests
    
    Closes #28659 from BryanCutler/arrow-category-test-fix-SPARK-25351.
    
    Authored-by: Bryan Cutler <cu...@gmail.com>
    Signed-off-by: HyukjinKwon <gu...@apache.org>
---
 python/pyspark/sql/tests/test_arrow.py             | 9 +++++----
 python/pyspark/sql/tests/test_pandas_udf_scalar.py | 9 +++------
 2 files changed, 8 insertions(+), 10 deletions(-)

diff --git a/python/pyspark/sql/tests/test_arrow.py b/python/pyspark/sql/tests/test_arrow.py
index c3c9fb0..c59765d 100644
--- a/python/pyspark/sql/tests/test_arrow.py
+++ b/python/pyspark/sql/tests/test_arrow.py
@@ -435,11 +435,12 @@ class ArrowTests(ReusedSQLTestCase):
         assert_frame_equal(result_spark, result_arrow)
 
         # ensure original category elements are string
-        assert isinstance(category_first_element, str)
+        self.assertIsInstance(category_first_element, str)
         # spark data frame and arrow execution mode enabled data frame type must match pandas
-        assert spark_type == arrow_type == 'string'
-        assert isinstance(arrow_first_category_element, str)
-        assert isinstance(spark_first_category_element, str)
+        self.assertEqual(spark_type, 'string')
+        self.assertEqual(arrow_type, 'string')
+        self.assertIsInstance(arrow_first_category_element, str)
+        self.assertIsInstance(spark_first_category_element, str)
 
 
 @unittest.skipIf(
diff --git a/python/pyspark/sql/tests/test_pandas_udf_scalar.py b/python/pyspark/sql/tests/test_pandas_udf_scalar.py
index ae6b8d5..2d38efd 100644
--- a/python/pyspark/sql/tests/test_pandas_udf_scalar.py
+++ b/python/pyspark/sql/tests/test_pandas_udf_scalar.py
@@ -910,13 +910,10 @@ class ScalarPandasUDFTests(ReusedSQLTestCase):
 
         spark_type = df.dtypes[1][1]
         # spark data frame and arrow execution mode enabled data frame type must match pandas
-        assert spark_type == 'string'
+        self.assertEqual(spark_type, 'string')
 
-        # Check result value of column 'B' must be equal to column 'A'
-        for i in range(0, len(result_spark["A"])):
-            assert result_spark["A"][i] == result_spark["B"][i]
-            assert isinstance(result_spark["A"][i], str)
-            assert isinstance(result_spark["B"][i], str)
+        # Check result of column 'B' must be equal to column 'A' in type and values
+        pd.testing.assert_series_equal(result_spark["A"], result_spark["B"], check_names=False)
 
     @unittest.skipIf(sys.version_info[:2] < (3, 5), "Type hints are supported from Python 3.5.")
     def test_type_annotation(self):


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org