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 58ce4b755c0 [SPARK-42065][PYTHON][CONNECT][TESTS] Remove duplicated
`test_freqItems` test
58ce4b755c0 is described below
commit 58ce4b755c09b5a85812179e3e99eac74b78253a
Author: bjornjorgensen <[email protected]>
AuthorDate: Sun Jan 15 20:10:11 2023 +0900
[SPARK-42065][PYTHON][CONNECT][TESTS] Remove duplicated `test_freqItems`
test
### What changes were proposed in this pull request?
Remove one of the `test_freqItems` functions.
### Why are the changes needed?
The same code have be copied.
https://github.com/apache/spark/blob/e6c01cedbecebdc40863e552862beee1bd959710/python/pyspark/sql/tests/connect/test_connect_plan.py#L316
https://github.com/apache/spark/blob/e6c01cedbecebdc40863e552862beee1bd959710/python/pyspark/sql/tests/connect/test_connect_plan.py#L334
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Pass GA
Closes #39573 from bjornjorgensen/remove_test_freqItems.
Authored-by: bjornjorgensen <[email protected]>
Signed-off-by: Hyukjin Kwon <[email protected]>
---
python/pyspark/sql/tests/connect/test_connect_plan.py | 18 ------------------
1 file changed, 18 deletions(-)
diff --git a/python/pyspark/sql/tests/connect/test_connect_plan.py
b/python/pyspark/sql/tests/connect/test_connect_plan.py
index e698566c2bd..731160bd15d 100644
--- a/python/pyspark/sql/tests/connect/test_connect_plan.py
+++ b/python/pyspark/sql/tests/connect/test_connect_plan.py
@@ -331,24 +331,6 @@ class SparkConnectPlanTests(PlanOnlyTestFixture):
self.assertEqual(plan.root.freq_items.cols, ["col_a", "col_b"])
self.assertEqual(plan.root.freq_items.support, 0.01)
- def test_freqItems(self):
- df = self.connect.readTable(table_name=self.tbl_name)
- plan = (
- df.filter(df.col_name > 3).freqItems(["col_a", "col_b"],
1)._plan.to_proto(self.connect)
- )
- self.assertEqual(plan.root.freq_items.cols, ["col_a", "col_b"])
- self.assertEqual(plan.root.freq_items.support, 1)
- plan = df.filter(df.col_name > 3).freqItems(["col_a",
"col_b"])._plan.to_proto(self.connect)
- self.assertEqual(plan.root.freq_items.cols, ["col_a", "col_b"])
- self.assertEqual(plan.root.freq_items.support, 0.01)
-
- plan = df.stat.freqItems(["col_a", "col_b"],
1)._plan.to_proto(self.connect)
- self.assertEqual(plan.root.freq_items.cols, ["col_a", "col_b"])
- self.assertEqual(plan.root.freq_items.support, 1)
- plan = df.stat.freqItems(["col_a",
"col_b"])._plan.to_proto(self.connect)
- self.assertEqual(plan.root.freq_items.cols, ["col_a", "col_b"])
- self.assertEqual(plan.root.freq_items.support, 0.01)
-
def test_limit(self):
df = self.connect.readTable(table_name=self.tbl_name)
limit_plan = df.limit(10)._plan.to_proto(self.connect)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
