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 999c1d74e0b [SPARK-42007][CONNECT][TESTS] Reuse
pyspark.sql.tests.test_group test cases
999c1d74e0b is described below
commit 999c1d74e0bcd436b241474db59c61d9bb92e69a
Author: Hyukjin Kwon <[email protected]>
AuthorDate: Thu Jan 12 17:01:05 2023 +0900
[SPARK-42007][CONNECT][TESTS] Reuse pyspark.sql.tests.test_group test cases
### What changes were proposed in this pull request?
This PR reuses PySpark `pyspark.sql.tests.test_group` tests in Spark
Connect that pass for now.
### Why are the changes needed?
To make sure on the test coverage.
### Does this PR introduce _any_ user-facing change?
No, test-only.
### How was this patch tested?
Manually ran it in my local.
Closes #39525 from HyukjinKwon/SPARK-42007.
Authored-by: Hyukjin Kwon <[email protected]>
Signed-off-by: Hyukjin Kwon <[email protected]>
---
dev/sparktestsupport/modules.py | 1 +
.../test_parity_group.py} | 25 ++++++----------------
python/pyspark/sql/tests/test_group.py | 6 +++++-
3 files changed, 12 insertions(+), 20 deletions(-)
diff --git a/dev/sparktestsupport/modules.py b/dev/sparktestsupport/modules.py
index 080b2ea0465..0bd82c7122d 100644
--- a/dev/sparktestsupport/modules.py
+++ b/dev/sparktestsupport/modules.py
@@ -520,6 +520,7 @@ pyspark_connect = Module(
"pyspark.sql.tests.connect.test_connect_column",
"pyspark.sql.tests.connect.test_parity_catalog",
"pyspark.sql.tests.connect.test_parity_functions",
+ "pyspark.sql.tests.connect.test_parity_group",
"pyspark.sql.tests.connect.test_parity_dataframe",
"pyspark.sql.tests.connect.test_parity_readwriter",
],
diff --git a/python/pyspark/sql/tests/test_group.py
b/python/pyspark/sql/tests/connect/test_parity_group.py
similarity index 55%
copy from python/pyspark/sql/tests/test_group.py
copy to python/pyspark/sql/tests/connect/test_parity_group.py
index 19e1228d250..1dba236a12d 100644
--- a/python/pyspark/sql/tests/test_group.py
+++ b/python/pyspark/sql/tests/connect/test_parity_group.py
@@ -15,33 +15,20 @@
# limitations under the License.
#
-from pyspark.sql import Row
-from pyspark.testing.sqlutils import ReusedSQLTestCase
+from pyspark.sql.tests.test_group import GroupTestsMixin
+from pyspark.testing.connectutils import ReusedConnectTestCase
-class GroupTests(ReusedSQLTestCase):
- def test_aggregator(self):
- df = self.df
- g = df.groupBy()
- self.assertEqual([99, 100], sorted(g.agg({"key": "max", "value":
"count"}).collect()[0]))
- self.assertEqual([Row(**{"AVG(key#0)": 49.5})], g.mean().collect())
-
- from pyspark.sql import functions
-
- self.assertEqual(
- (0, "99"), tuple(g.agg(functions.first(df.key),
functions.last(df.value)).first())
- )
- self.assertTrue(95 <
g.agg(functions.approx_count_distinct(df.key)).first()[0])
- # test deprecated countDistinct
- self.assertEqual(100,
g.agg(functions.countDistinct(df.value)).first()[0])
+class GroupParityTests(GroupTestsMixin, ReusedConnectTestCase):
+ pass
if __name__ == "__main__":
import unittest
- from pyspark.sql.tests.test_group import * # noqa: F401
+ from pyspark.sql.tests.connect.test_parity_group import * # noqa: F401
try:
- import xmlrunner
+ import xmlrunner # type: ignore[import]
testRunner = xmlrunner.XMLTestRunner(output="target/test-reports",
verbosity=2)
except ImportError:
diff --git a/python/pyspark/sql/tests/test_group.py
b/python/pyspark/sql/tests/test_group.py
index 19e1228d250..2715571a44d 100644
--- a/python/pyspark/sql/tests/test_group.py
+++ b/python/pyspark/sql/tests/test_group.py
@@ -19,7 +19,7 @@ from pyspark.sql import Row
from pyspark.testing.sqlutils import ReusedSQLTestCase
-class GroupTests(ReusedSQLTestCase):
+class GroupTestsMixin:
def test_aggregator(self):
df = self.df
g = df.groupBy()
@@ -36,6 +36,10 @@ class GroupTests(ReusedSQLTestCase):
self.assertEqual(100,
g.agg(functions.countDistinct(df.value)).first()[0])
+class GroupTests(GroupTestsMixin, ReusedSQLTestCase):
+ pass
+
+
if __name__ == "__main__":
import unittest
from pyspark.sql.tests.test_group import * # noqa: F401
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
