This is an automated email from the ASF dual-hosted git repository.
gurwls223 pushed a commit to branch branch-3.1
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/branch-3.1 by this push:
new 3b2c1b916a2 [SPARK-39252][PYSPARK][TESTS] Remove flaky test_df_is_empty
3b2c1b916a2 is described below
commit 3b2c1b916a29fef0463dc3a6d9df2e46a91cf446
Author: Ivan Sadikov <ivan.sadi...@databricks.com>
AuthorDate: Wed May 25 11:39:54 2022 +0900
[SPARK-39252][PYSPARK][TESTS] Remove flaky test_df_is_empty
This PR removes flaky `test_df_is_empty` as reported in
https://issues.apache.org/jira/browse/SPARK-39252. I will open a follow-up PR
to reintroduce the test and fix the flakiness (or see if it was a regression).
No.
Existing unit tests.
Closes #36656 from sadikovi/SPARK-39252.
Authored-by: Ivan Sadikov <ivan.sadi...@databricks.com>
Signed-off-by: Hyukjin Kwon <gurwls...@apache.org>
(cherry picked from commit 9823bb385cd6dca7c4fb5a6315721420ad42f80a)
Signed-off-by: Hyukjin Kwon <gurwls...@apache.org>
---
python/pyspark/sql/tests/test_dataframe.py | 46 +++++++++++++++++++++++++++++-
1 file changed, 45 insertions(+), 1 deletion(-)
diff --git a/python/pyspark/sql/tests/test_dataframe.py
b/python/pyspark/sql/tests/test_dataframe.py
index 6b9ac24d8c1..72fed2856a6 100644
--- a/python/pyspark/sql/tests/test_dataframe.py
+++ b/python/pyspark/sql/tests/test_dataframe.py
@@ -21,7 +21,7 @@ import shutil
import tempfile
import time
import unittest
-import uuid
+from typing import cast
from pyspark.sql import SparkSession, Row
from pyspark.sql.types import StringType, IntegerType, DoubleType, StructType,
StructField, \
@@ -838,6 +838,7 @@ class DataFrameTests(ReusedSQLTestCase):
finally:
shutil.rmtree(tpath)
+<<<<<<< HEAD
def test_df_is_empty(self):
# SPARK-39084: Fix df.rdd.isEmpty() resulting in JVM crash.
@@ -872,6 +873,49 @@ class DataFrameTests(ReusedSQLTestCase):
self.assertFalse(res.rdd.isEmpty())
finally:
shutil.rmtree(tmpPath)
+=======
+ def test_df_show(self):
+ # SPARK-35408: ensure better diagnostics if incorrect parameters are
passed
+ # to DataFrame.show
+
+ df = self.spark.createDataFrame([("foo",)])
+ df.show(5)
+ df.show(5, True)
+ df.show(5, 1, True)
+ df.show(n=5, truncate="1", vertical=False)
+ df.show(n=5, truncate=1.5, vertical=False)
+
+ with self.assertRaisesRegex(TypeError, "Parameter 'n'"):
+ df.show(True)
+ with self.assertRaisesRegex(TypeError, "Parameter 'vertical'"):
+ df.show(vertical="foo")
+ with self.assertRaisesRegex(TypeError, "Parameter 'truncate=foo'"):
+ df.show(truncate="foo")
+
+ @unittest.skipIf(
+ not have_pandas or not have_pyarrow,
+ cast(str, pandas_requirement_message or pyarrow_requirement_message),
+ )
+ def test_pandas_api(self):
+ import pandas as pd
+ from pandas.testing import assert_frame_equal
+
+ sdf = self.spark.createDataFrame([("a", 1), ("b", 2), ("c", 3)],
["Col1", "Col2"])
+ psdf_from_sdf = sdf.pandas_api()
+ psdf_from_sdf_with_index = sdf.pandas_api(index_col="Col1")
+ pdf = pd.DataFrame({"Col1": ["a", "b", "c"], "Col2": [1, 2, 3]})
+ pdf_with_index = pdf.set_index("Col1")
+
+ assert_frame_equal(pdf, psdf_from_sdf.to_pandas())
+ assert_frame_equal(pdf_with_index,
psdf_from_sdf_with_index.to_pandas())
+
+ # test for SPARK-36337
+ def test_create_nan_decimal_dataframe(self):
+ self.assertEqual(
+ self.spark.createDataFrame(data=[Decimal("NaN")],
schema="decimal").collect(),
+ [Row(value=None)],
+ )
+>>>>>>> 9823bb385cd ([SPARK-39252][PYSPARK][TESTS] Remove flaky
test_df_is_empty)
class QueryExecutionListenerTests(unittest.TestCase, SQLTestUtils):
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org
For additional commands, e-mail: commits-h...@spark.apache.org
