Github user HyukjinKwon commented on a diff in the pull request:
https://github.com/apache/spark/pull/20487#discussion_r165795135
--- Diff: python/pyspark/sql/tests.py ---
@@ -2858,14 +2855,16 @@ def
test_create_dataframe_from_pandas_with_timestamp(self):
self.assertTrue(isinstance(df.schema['ts'].dataType,
TimestampType))
self.assertTrue(isinstance(df.schema['d'].dataType, DateType))
- @unittest.skipIf(not _have_old_pandas, "Old Pandas not installed")
- def test_create_dataframe_from_old_pandas(self):
- import pandas as pd
- from datetime import datetime
- pdf = pd.DataFrame({"ts": [datetime(2017, 10, 31, 1, 1, 1)],
- "d": [pd.Timestamp.now().date()]})
+ @unittest.skipIf(_have_pandas, "Required Pandas was found.")
+ def test_create_dataframe_required_pandas_not_found(self):
with QuietTest(self.sc):
- with self.assertRaisesRegexp(ImportError, 'Pandas >= .* must
be installed'):
+ with self.assertRaisesRegexp(
+ ImportError,
+ '(Pandas >= .* must be installed|No module named
pandas)'):
--- End diff --
If Pandas is lower then we have, it throws `Pandas >= .* must be
installed`. It Pandas is not installed `import pandas as pd` in the test throws
an exception, "No module named pandas".
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
