This is an automated email from the ASF dual-hosted git repository.
ruifengz 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 8cd0d1854da0 [SPARK-46896][PS][TESTS] Clean up the imports in
`pyspark.pandas.tests.{frame, series, groupby}.*`
8cd0d1854da0 is described below
commit 8cd0d1854da04334aff3188e4eca08a48f734579
Author: Ruifeng Zheng <ruife...@apache.org>
AuthorDate: Mon Jan 29 12:00:18 2024 +0800
[SPARK-46896][PS][TESTS] Clean up the imports in
`pyspark.pandas.tests.{frame, series, groupby}.*`
### What changes were proposed in this pull request?
1, remove unused imports;
2, only define the test datasets once in the vanilla side, so that won't
need to define it again in the parity tests;
### Why are the changes needed?
code clean up
### Does this PR introduce _any_ user-facing change?
no, test-only
### How was this patch tested?
ci
### Was this patch authored or co-authored using generative AI tooling?
no
Closes #44922 from zhengruifeng/ps_test_frame_ser_cleanup.
Authored-by: Ruifeng Zheng <ruife...@apache.org>
Signed-off-by: Ruifeng Zheng <ruife...@apache.org>
---
.../pyspark/pandas/tests/connect/frame/test_parity_attrs.py | 11 ++++++-----
.../pyspark/pandas/tests/connect/frame/test_parity_axis.py | 6 +++++-
.../pandas/tests/connect/frame/test_parity_constructor.py | 4 +++-
.../pandas/tests/connect/frame/test_parity_conversion.py | 9 ++++-----
.../pandas/tests/connect/frame/test_parity_reindexing.py | 9 ++++-----
.../pandas/tests/connect/frame/test_parity_reshaping.py | 6 +++++-
.../pyspark/pandas/tests/connect/frame/test_parity_spark.py | 11 ++++++-----
.../pandas/tests/connect/frame/test_parity_time_series.py | 9 ++++-----
.../pandas/tests/connect/frame/test_parity_truncate.py | 11 ++++++-----
.../pandas/tests/connect/groupby/test_parity_aggregate.py | 4 +++-
.../pandas/tests/connect/groupby/test_parity_apply_func.py | 4 +++-
.../pandas/tests/connect/groupby/test_parity_cumulative.py | 4 +++-
.../pandas/tests/connect/groupby/test_parity_describe.py | 4 +++-
.../pandas/tests/connect/groupby/test_parity_groupby.py | 5 ++++-
.../pandas/tests/connect/groupby/test_parity_head_tail.py | 4 +++-
.../pandas/tests/connect/groupby/test_parity_index.py | 6 +++++-
.../pandas/tests/connect/groupby/test_parity_missing_data.py | 4 +++-
.../pandas/tests/connect/series/test_parity_all_any.py | 6 +++++-
.../pandas/tests/connect/series/test_parity_arg_ops.py | 6 +++++-
.../pyspark/pandas/tests/connect/series/test_parity_as_of.py | 6 +++++-
.../pandas/tests/connect/series/test_parity_as_type.py | 6 +++++-
.../pandas/tests/connect/series/test_parity_compute.py | 6 +++++-
.../pandas/tests/connect/series/test_parity_conversion.py | 4 +++-
.../pandas/tests/connect/series/test_parity_cumulative.py | 4 +++-
.../pyspark/pandas/tests/connect/series/test_parity_index.py | 6 +++++-
.../pandas/tests/connect/series/test_parity_missing_data.py | 4 +++-
.../pandas/tests/connect/series/test_parity_series.py | 6 +++++-
.../pyspark/pandas/tests/connect/series/test_parity_sort.py | 6 +++++-
.../pyspark/pandas/tests/connect/series/test_parity_stat.py | 6 +++++-
.../tests/connect/series/test_parity_string_ops_adv.py | 4 +++-
.../tests/connect/series/test_parity_string_ops_basic.py | 4 +++-
python/pyspark/pandas/tests/frame/test_attrs.py | 12 ++++++++++--
python/pyspark/pandas/tests/frame/test_axis.py | 8 ++++++--
python/pyspark/pandas/tests/frame/test_constructor.py | 8 ++++++--
python/pyspark/pandas/tests/frame/test_conversion.py | 12 ++++++++++--
python/pyspark/pandas/tests/frame/test_interpolate.py | 6 +++++-
python/pyspark/pandas/tests/frame/test_reindexing.py | 8 ++++++--
python/pyspark/pandas/tests/frame/test_reshaping.py | 8 ++++++--
python/pyspark/pandas/tests/frame/test_spark.py | 12 ++++++++++--
python/pyspark/pandas/tests/frame/test_time_series.py | 8 ++++++--
python/pyspark/pandas/tests/frame/test_truncate.py | 4 ++--
python/pyspark/pandas/tests/groupby/test_aggregate.py | 8 ++++++--
python/pyspark/pandas/tests/groupby/test_apply_func.py | 8 ++++++--
python/pyspark/pandas/tests/groupby/test_cumulative.py | 8 ++++++--
python/pyspark/pandas/tests/groupby/test_describe.py | 8 ++++++--
python/pyspark/pandas/tests/groupby/test_groupby.py | 12 +++++-------
python/pyspark/pandas/tests/groupby/test_grouping.py | 5 ++++-
python/pyspark/pandas/tests/groupby/test_head_tail.py | 8 ++++++--
python/pyspark/pandas/tests/groupby/test_index.py | 8 ++++++--
python/pyspark/pandas/tests/groupby/test_missing.py | 5 ++++-
python/pyspark/pandas/tests/groupby/test_missing_data.py | 8 ++++++--
.../pyspark/pandas/tests/groupby/test_nlargest_nsmallest.py | 5 ++++-
python/pyspark/pandas/tests/groupby/test_raises.py | 5 ++++-
python/pyspark/pandas/tests/groupby/test_rank.py | 5 ++++-
python/pyspark/pandas/tests/groupby/test_size.py | 5 ++++-
python/pyspark/pandas/tests/groupby/test_value_counts.py | 5 ++++-
python/pyspark/pandas/tests/series/test_all_any.py | 8 ++++++--
python/pyspark/pandas/tests/series/test_arg_ops.py | 8 ++++++--
python/pyspark/pandas/tests/series/test_as_of.py | 8 ++++++--
python/pyspark/pandas/tests/series/test_as_type.py | 8 ++++++--
python/pyspark/pandas/tests/series/test_compute.py | 8 ++++++--
python/pyspark/pandas/tests/series/test_conversion.py | 8 ++++++--
python/pyspark/pandas/tests/series/test_cumulative.py | 8 ++++++--
python/pyspark/pandas/tests/series/test_index.py | 8 ++++++--
python/pyspark/pandas/tests/series/test_missing_data.py | 8 ++++++--
python/pyspark/pandas/tests/series/test_series.py | 6 +++++-
python/pyspark/pandas/tests/series/test_sort.py | 8 ++++++--
python/pyspark/pandas/tests/series/test_stat.py | 8 ++++++--
python/pyspark/pandas/tests/series/test_string_ops_adv.py | 6 +++++-
python/pyspark/pandas/tests/series/test_string_ops_basic.py | 6 +++++-
70 files changed, 353 insertions(+), 127 deletions(-)
diff --git a/python/pyspark/pandas/tests/connect/frame/test_parity_attrs.py
b/python/pyspark/pandas/tests/connect/frame/test_parity_attrs.py
index 2f13601b53bb..a7b0c986107f 100644
--- a/python/pyspark/pandas/tests/connect/frame/test_parity_attrs.py
+++ b/python/pyspark/pandas/tests/connect/frame/test_parity_attrs.py
@@ -16,16 +16,17 @@
#
import unittest
-from pyspark import pandas as ps
from pyspark.pandas.tests.frame.test_attrs import FrameAttrsMixin
from pyspark.testing.connectutils import ReusedConnectTestCase
from pyspark.testing.pandasutils import PandasOnSparkTestUtils
-class FrameParityAttrsTests(FrameAttrsMixin, PandasOnSparkTestUtils,
ReusedConnectTestCase):
- @property
- def psdf(self):
- return ps.from_pandas(self.pdf)
+class FrameParityAttrsTests(
+ FrameAttrsMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
+):
+ pass
if __name__ == "__main__":
diff --git a/python/pyspark/pandas/tests/connect/frame/test_parity_axis.py
b/python/pyspark/pandas/tests/connect/frame/test_parity_axis.py
index 804ed97fa31c..c02e0b4fddd9 100644
--- a/python/pyspark/pandas/tests/connect/frame/test_parity_axis.py
+++ b/python/pyspark/pandas/tests/connect/frame/test_parity_axis.py
@@ -21,7 +21,11 @@ from pyspark.testing.connectutils import
ReusedConnectTestCase
from pyspark.testing.pandasutils import PandasOnSparkTestUtils
-class FrameParityAxisTests(FrameAxisMixin, PandasOnSparkTestUtils,
ReusedConnectTestCase):
+class FrameParityAxisTests(
+ FrameAxisMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
+):
pass
diff --git
a/python/pyspark/pandas/tests/connect/frame/test_parity_constructor.py
b/python/pyspark/pandas/tests/connect/frame/test_parity_constructor.py
index 19af61c0cef2..fef7632e3ead 100644
--- a/python/pyspark/pandas/tests/connect/frame/test_parity_constructor.py
+++ b/python/pyspark/pandas/tests/connect/frame/test_parity_constructor.py
@@ -22,7 +22,9 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils
class FrameParityConstructorTests(
- FrameConstructorMixin, PandasOnSparkTestUtils, ReusedConnectTestCase
+ FrameConstructorMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
):
pass
diff --git
a/python/pyspark/pandas/tests/connect/frame/test_parity_conversion.py
b/python/pyspark/pandas/tests/connect/frame/test_parity_conversion.py
index a580254b45ce..495b98689ccc 100644
--- a/python/pyspark/pandas/tests/connect/frame/test_parity_conversion.py
+++ b/python/pyspark/pandas/tests/connect/frame/test_parity_conversion.py
@@ -16,18 +16,17 @@
#
import unittest
-from pyspark import pandas as ps
from pyspark.pandas.tests.frame.test_conversion import FrameConversionMixin
from pyspark.testing.connectutils import ReusedConnectTestCase
from pyspark.testing.pandasutils import PandasOnSparkTestUtils
class FrameParityConversionTests(
- FrameConversionMixin, PandasOnSparkTestUtils, ReusedConnectTestCase
+ FrameConversionMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
):
- @property
- def psdf(self):
- return ps.from_pandas(self.pdf)
+ pass
if __name__ == "__main__":
diff --git
a/python/pyspark/pandas/tests/connect/frame/test_parity_reindexing.py
b/python/pyspark/pandas/tests/connect/frame/test_parity_reindexing.py
index 0caa6c32cf8b..ff4f3dc3b57a 100644
--- a/python/pyspark/pandas/tests/connect/frame/test_parity_reindexing.py
+++ b/python/pyspark/pandas/tests/connect/frame/test_parity_reindexing.py
@@ -16,18 +16,17 @@
#
import unittest
-from pyspark import pandas as ps
from pyspark.pandas.tests.frame.test_reindexing import FrameReindexingMixin
from pyspark.testing.connectutils import ReusedConnectTestCase
from pyspark.testing.pandasutils import PandasOnSparkTestUtils
class FrameParityReindexingTests(
- FrameReindexingMixin, PandasOnSparkTestUtils, ReusedConnectTestCase
+ FrameReindexingMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
):
- @property
- def psdf(self):
- return ps.from_pandas(self.pdf)
+ pass
if __name__ == "__main__":
diff --git a/python/pyspark/pandas/tests/connect/frame/test_parity_reshaping.py
b/python/pyspark/pandas/tests/connect/frame/test_parity_reshaping.py
index e4bac7b078e6..7905359be138 100644
--- a/python/pyspark/pandas/tests/connect/frame/test_parity_reshaping.py
+++ b/python/pyspark/pandas/tests/connect/frame/test_parity_reshaping.py
@@ -21,7 +21,11 @@ from pyspark.testing.connectutils import
ReusedConnectTestCase
from pyspark.testing.pandasutils import PandasOnSparkTestUtils
-class FrameParityReshapingTests(FrameReshapingMixin, PandasOnSparkTestUtils,
ReusedConnectTestCase):
+class FrameParityReshapingTests(
+ FrameReshapingMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
+):
pass
diff --git a/python/pyspark/pandas/tests/connect/frame/test_parity_spark.py
b/python/pyspark/pandas/tests/connect/frame/test_parity_spark.py
index 09de0f102863..d96f9467bf9b 100644
--- a/python/pyspark/pandas/tests/connect/frame/test_parity_spark.py
+++ b/python/pyspark/pandas/tests/connect/frame/test_parity_spark.py
@@ -16,16 +16,17 @@
#
import unittest
-from pyspark import pandas as ps
from pyspark.pandas.tests.frame.test_spark import FrameSparkMixin
from pyspark.testing.connectutils import ReusedConnectTestCase
from pyspark.testing.pandasutils import PandasOnSparkTestUtils
-class FrameParitySparkTests(FrameSparkMixin, PandasOnSparkTestUtils,
ReusedConnectTestCase):
- @property
- def psdf(self):
- return ps.from_pandas(self.pdf)
+class FrameParitySparkTests(
+ FrameSparkMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
+):
+ pass
if __name__ == "__main__":
diff --git
a/python/pyspark/pandas/tests/connect/frame/test_parity_time_series.py
b/python/pyspark/pandas/tests/connect/frame/test_parity_time_series.py
index 6b8a93f895e6..7fdde579a91a 100644
--- a/python/pyspark/pandas/tests/connect/frame/test_parity_time_series.py
+++ b/python/pyspark/pandas/tests/connect/frame/test_parity_time_series.py
@@ -16,18 +16,17 @@
#
import unittest
-from pyspark import pandas as ps
from pyspark.pandas.tests.frame.test_time_series import FrameTimeSeriesMixin
from pyspark.testing.connectutils import ReusedConnectTestCase
from pyspark.testing.pandasutils import PandasOnSparkTestUtils
class FrameParityTimeSeriesTests(
- FrameTimeSeriesMixin, PandasOnSparkTestUtils, ReusedConnectTestCase
+ FrameTimeSeriesMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
):
- @property
- def psdf(self):
- return ps.from_pandas(self.pdf)
+ pass
if __name__ == "__main__":
diff --git a/python/pyspark/pandas/tests/connect/frame/test_parity_truncate.py
b/python/pyspark/pandas/tests/connect/frame/test_parity_truncate.py
index 32adbf312fdd..5b4b4166e990 100644
--- a/python/pyspark/pandas/tests/connect/frame/test_parity_truncate.py
+++ b/python/pyspark/pandas/tests/connect/frame/test_parity_truncate.py
@@ -16,16 +16,17 @@
#
import unittest
-from pyspark import pandas as ps
from pyspark.pandas.tests.frame.test_truncate import FrameTruncateMixin
from pyspark.testing.connectutils import ReusedConnectTestCase
from pyspark.testing.pandasutils import PandasOnSparkTestUtils
-class FrameParityTruncateTests(FrameTruncateMixin, PandasOnSparkTestUtils,
ReusedConnectTestCase):
- @property
- def psdf(self):
- return ps.from_pandas(self.pdf)
+class FrameParityTruncateTests(
+ FrameTruncateMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
+):
+ pass
if __name__ == "__main__":
diff --git
a/python/pyspark/pandas/tests/connect/groupby/test_parity_aggregate.py
b/python/pyspark/pandas/tests/connect/groupby/test_parity_aggregate.py
index 758266cc56b7..f73a8320411d 100644
--- a/python/pyspark/pandas/tests/connect/groupby/test_parity_aggregate.py
+++ b/python/pyspark/pandas/tests/connect/groupby/test_parity_aggregate.py
@@ -22,7 +22,9 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils
class GroupbyParityAggregateTests(
- GroupbyAggregateMixin, PandasOnSparkTestUtils, ReusedConnectTestCase
+ GroupbyAggregateMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
):
pass
diff --git
a/python/pyspark/pandas/tests/connect/groupby/test_parity_apply_func.py
b/python/pyspark/pandas/tests/connect/groupby/test_parity_apply_func.py
index 4daf84bd1b50..0c223c34103b 100644
--- a/python/pyspark/pandas/tests/connect/groupby/test_parity_apply_func.py
+++ b/python/pyspark/pandas/tests/connect/groupby/test_parity_apply_func.py
@@ -22,7 +22,9 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils
class GroupbyParityApplyFuncTests(
- GroupbyApplyFuncMixin, PandasOnSparkTestUtils, ReusedConnectTestCase
+ GroupbyApplyFuncMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
):
@unittest.skip("Test depends on SparkContext which is not supported from
Spark Connect.")
def test_apply_with_side_effect(self):
diff --git
a/python/pyspark/pandas/tests/connect/groupby/test_parity_cumulative.py
b/python/pyspark/pandas/tests/connect/groupby/test_parity_cumulative.py
index 696c283b648a..2565f5393b14 100644
--- a/python/pyspark/pandas/tests/connect/groupby/test_parity_cumulative.py
+++ b/python/pyspark/pandas/tests/connect/groupby/test_parity_cumulative.py
@@ -22,7 +22,9 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils
class GroupbyParityCumulativeTests(
- GroupbyCumulativeMixin, PandasOnSparkTestUtils, ReusedConnectTestCase
+ GroupbyCumulativeMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
):
pass
diff --git
a/python/pyspark/pandas/tests/connect/groupby/test_parity_describe.py
b/python/pyspark/pandas/tests/connect/groupby/test_parity_describe.py
index 21777715312e..2513fae6d1d6 100644
--- a/python/pyspark/pandas/tests/connect/groupby/test_parity_describe.py
+++ b/python/pyspark/pandas/tests/connect/groupby/test_parity_describe.py
@@ -22,7 +22,9 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils
class GroupbyParityDescribeTests(
- GroupbyDescribeMixin, PandasOnSparkTestUtils, ReusedConnectTestCase
+ GroupbyDescribeMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
):
pass
diff --git a/python/pyspark/pandas/tests/connect/groupby/test_parity_groupby.py
b/python/pyspark/pandas/tests/connect/groupby/test_parity_groupby.py
index 8293652b476d..cdca70b7c430 100644
--- a/python/pyspark/pandas/tests/connect/groupby/test_parity_groupby.py
+++ b/python/pyspark/pandas/tests/connect/groupby/test_parity_groupby.py
@@ -22,7 +22,10 @@ from pyspark.testing.pandasutils import
PandasOnSparkTestUtils, TestUtils
class GroupByParityTests(
- GroupByTestsMixin, PandasOnSparkTestUtils, TestUtils, ReusedConnectTestCase
+ GroupByTestsMixin,
+ PandasOnSparkTestUtils,
+ TestUtils,
+ ReusedConnectTestCase,
):
pass
diff --git
a/python/pyspark/pandas/tests/connect/groupby/test_parity_head_tail.py
b/python/pyspark/pandas/tests/connect/groupby/test_parity_head_tail.py
index f8aef7e6482b..bfb624c19a2c 100644
--- a/python/pyspark/pandas/tests/connect/groupby/test_parity_head_tail.py
+++ b/python/pyspark/pandas/tests/connect/groupby/test_parity_head_tail.py
@@ -22,7 +22,9 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils
class GroupbyParityHeadTailTests(
- GroupbyHeadTailMixin, PandasOnSparkTestUtils, ReusedConnectTestCase
+ GroupbyHeadTailMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
):
pass
diff --git a/python/pyspark/pandas/tests/connect/groupby/test_parity_index.py
b/python/pyspark/pandas/tests/connect/groupby/test_parity_index.py
index 307a1182f616..f01085faf845 100644
--- a/python/pyspark/pandas/tests/connect/groupby/test_parity_index.py
+++ b/python/pyspark/pandas/tests/connect/groupby/test_parity_index.py
@@ -21,7 +21,11 @@ from pyspark.testing.connectutils import
ReusedConnectTestCase
from pyspark.testing.pandasutils import PandasOnSparkTestUtils
-class GroupbyParityIndexTests(GroupbyIndexMixin, PandasOnSparkTestUtils,
ReusedConnectTestCase):
+class GroupbyParityIndexTests(
+ GroupbyIndexMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
+):
pass
diff --git
a/python/pyspark/pandas/tests/connect/groupby/test_parity_missing_data.py
b/python/pyspark/pandas/tests/connect/groupby/test_parity_missing_data.py
index 752e8568fbd5..bc16259c8a5e 100644
--- a/python/pyspark/pandas/tests/connect/groupby/test_parity_missing_data.py
+++ b/python/pyspark/pandas/tests/connect/groupby/test_parity_missing_data.py
@@ -22,7 +22,9 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils
class GroupbyParityMissingDataTests(
- GroupbyMissingDataMixin, PandasOnSparkTestUtils, ReusedConnectTestCase
+ GroupbyMissingDataMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
):
pass
diff --git a/python/pyspark/pandas/tests/connect/series/test_parity_all_any.py
b/python/pyspark/pandas/tests/connect/series/test_parity_all_any.py
index 7edde505445c..1e2291950cee 100644
--- a/python/pyspark/pandas/tests/connect/series/test_parity_all_any.py
+++ b/python/pyspark/pandas/tests/connect/series/test_parity_all_any.py
@@ -21,7 +21,11 @@ from pyspark.testing.connectutils import
ReusedConnectTestCase
from pyspark.testing.pandasutils import PandasOnSparkTestUtils
-class SeriesParityAllAnyTests(SeriesAllAnyMixin, PandasOnSparkTestUtils,
ReusedConnectTestCase):
+class SeriesParityAllAnyTests(
+ SeriesAllAnyMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
+):
pass
diff --git a/python/pyspark/pandas/tests/connect/series/test_parity_arg_ops.py
b/python/pyspark/pandas/tests/connect/series/test_parity_arg_ops.py
index bd17521dd840..f8285dde54e1 100644
--- a/python/pyspark/pandas/tests/connect/series/test_parity_arg_ops.py
+++ b/python/pyspark/pandas/tests/connect/series/test_parity_arg_ops.py
@@ -21,7 +21,11 @@ from pyspark.testing.connectutils import
ReusedConnectTestCase
from pyspark.testing.pandasutils import PandasOnSparkTestUtils
-class SeriesParityArgOpsTests(SeriesArgOpsMixin, PandasOnSparkTestUtils,
ReusedConnectTestCase):
+class SeriesParityArgOpsTests(
+ SeriesArgOpsMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
+):
pass
diff --git a/python/pyspark/pandas/tests/connect/series/test_parity_as_of.py
b/python/pyspark/pandas/tests/connect/series/test_parity_as_of.py
index ad4faed230c0..75249177c2bc 100644
--- a/python/pyspark/pandas/tests/connect/series/test_parity_as_of.py
+++ b/python/pyspark/pandas/tests/connect/series/test_parity_as_of.py
@@ -21,7 +21,11 @@ from pyspark.testing.connectutils import
ReusedConnectTestCase
from pyspark.testing.pandasutils import PandasOnSparkTestUtils
-class SeriesParityArgOpsTests(SeriesAsOfMixin, PandasOnSparkTestUtils,
ReusedConnectTestCase):
+class SeriesParityArgOpsTests(
+ SeriesAsOfMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
+):
pass
diff --git a/python/pyspark/pandas/tests/connect/series/test_parity_as_type.py
b/python/pyspark/pandas/tests/connect/series/test_parity_as_type.py
index 8fcbe2aa95b3..165a7150590d 100644
--- a/python/pyspark/pandas/tests/connect/series/test_parity_as_type.py
+++ b/python/pyspark/pandas/tests/connect/series/test_parity_as_type.py
@@ -21,7 +21,11 @@ from pyspark.testing.connectutils import
ReusedConnectTestCase
from pyspark.testing.pandasutils import PandasOnSparkTestUtils
-class SeriesParityAsTypeTests(SeriesAsTypeMixin, PandasOnSparkTestUtils,
ReusedConnectTestCase):
+class SeriesParityAsTypeTests(
+ SeriesAsTypeMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
+):
pass
diff --git a/python/pyspark/pandas/tests/connect/series/test_parity_compute.py
b/python/pyspark/pandas/tests/connect/series/test_parity_compute.py
index 8876fcb13988..7d6616867215 100644
--- a/python/pyspark/pandas/tests/connect/series/test_parity_compute.py
+++ b/python/pyspark/pandas/tests/connect/series/test_parity_compute.py
@@ -21,7 +21,11 @@ from pyspark.testing.connectutils import
ReusedConnectTestCase
from pyspark.testing.pandasutils import PandasOnSparkTestUtils
-class SeriesParityComputeTests(SeriesComputeMixin, PandasOnSparkTestUtils,
ReusedConnectTestCase):
+class SeriesParityComputeTests(
+ SeriesComputeMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
+):
pass
diff --git
a/python/pyspark/pandas/tests/connect/series/test_parity_conversion.py
b/python/pyspark/pandas/tests/connect/series/test_parity_conversion.py
index bf5d0eebdd9d..e05a1a48260b 100644
--- a/python/pyspark/pandas/tests/connect/series/test_parity_conversion.py
+++ b/python/pyspark/pandas/tests/connect/series/test_parity_conversion.py
@@ -22,7 +22,9 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils
class SeriesParityConversionTests(
- SeriesConversionMixin, PandasOnSparkTestUtils, ReusedConnectTestCase
+ SeriesConversionMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
):
pass
diff --git
a/python/pyspark/pandas/tests/connect/series/test_parity_cumulative.py
b/python/pyspark/pandas/tests/connect/series/test_parity_cumulative.py
index a4978dca6faa..6163568df87a 100644
--- a/python/pyspark/pandas/tests/connect/series/test_parity_cumulative.py
+++ b/python/pyspark/pandas/tests/connect/series/test_parity_cumulative.py
@@ -22,7 +22,9 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils
class SeriesParityCumulativeTests(
- SeriesCumulativeMixin, PandasOnSparkTestUtils, ReusedConnectTestCase
+ SeriesCumulativeMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
):
pass
diff --git a/python/pyspark/pandas/tests/connect/series/test_parity_index.py
b/python/pyspark/pandas/tests/connect/series/test_parity_index.py
index 06b8051e2561..d074ddc245da 100644
--- a/python/pyspark/pandas/tests/connect/series/test_parity_index.py
+++ b/python/pyspark/pandas/tests/connect/series/test_parity_index.py
@@ -21,7 +21,11 @@ from pyspark.testing.connectutils import
ReusedConnectTestCase
from pyspark.testing.pandasutils import PandasOnSparkTestUtils
-class SeriesParityIndexTests(SeriesIndexMixin, PandasOnSparkTestUtils,
ReusedConnectTestCase):
+class SeriesParityIndexTests(
+ SeriesIndexMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
+):
pass
diff --git
a/python/pyspark/pandas/tests/connect/series/test_parity_missing_data.py
b/python/pyspark/pandas/tests/connect/series/test_parity_missing_data.py
index e756b2e887d4..342c84ff544a 100644
--- a/python/pyspark/pandas/tests/connect/series/test_parity_missing_data.py
+++ b/python/pyspark/pandas/tests/connect/series/test_parity_missing_data.py
@@ -22,7 +22,9 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils
class SeriesParityMissingDataTests(
- SeriesMissingDataMixin, PandasOnSparkTestUtils, ReusedConnectTestCase
+ SeriesMissingDataMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
):
pass
diff --git a/python/pyspark/pandas/tests/connect/series/test_parity_series.py
b/python/pyspark/pandas/tests/connect/series/test_parity_series.py
index 5f1d0d1569ec..05d8016c11ac 100644
--- a/python/pyspark/pandas/tests/connect/series/test_parity_series.py
+++ b/python/pyspark/pandas/tests/connect/series/test_parity_series.py
@@ -21,7 +21,11 @@ from pyspark.testing.connectutils import
ReusedConnectTestCase
from pyspark.testing.pandasutils import PandasOnSparkTestUtils
-class SeriesParityTests(SeriesTestsMixin, PandasOnSparkTestUtils,
ReusedConnectTestCase):
+class SeriesParityTests(
+ SeriesTestsMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
+):
pass
diff --git a/python/pyspark/pandas/tests/connect/series/test_parity_sort.py
b/python/pyspark/pandas/tests/connect/series/test_parity_sort.py
index 359c19f05675..4b1430a14067 100644
--- a/python/pyspark/pandas/tests/connect/series/test_parity_sort.py
+++ b/python/pyspark/pandas/tests/connect/series/test_parity_sort.py
@@ -21,7 +21,11 @@ from pyspark.testing.connectutils import
ReusedConnectTestCase
from pyspark.testing.pandasutils import PandasOnSparkTestUtils
-class SeriesParitySortTests(SeriesSortMixin, PandasOnSparkTestUtils,
ReusedConnectTestCase):
+class SeriesParitySortTests(
+ SeriesSortMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
+):
pass
diff --git a/python/pyspark/pandas/tests/connect/series/test_parity_stat.py
b/python/pyspark/pandas/tests/connect/series/test_parity_stat.py
index f598fe0255be..1716cc686943 100644
--- a/python/pyspark/pandas/tests/connect/series/test_parity_stat.py
+++ b/python/pyspark/pandas/tests/connect/series/test_parity_stat.py
@@ -21,7 +21,11 @@ from pyspark.testing.connectutils import
ReusedConnectTestCase
from pyspark.testing.pandasutils import PandasOnSparkTestUtils
-class SeriesParityStatTests(SeriesStatMixin, PandasOnSparkTestUtils,
ReusedConnectTestCase):
+class SeriesParityStatTests(
+ SeriesStatMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
+):
pass
diff --git
a/python/pyspark/pandas/tests/connect/series/test_parity_string_ops_adv.py
b/python/pyspark/pandas/tests/connect/series/test_parity_string_ops_adv.py
index 1213ae073cf5..6e313b4d4f3c 100644
--- a/python/pyspark/pandas/tests/connect/series/test_parity_string_ops_adv.py
+++ b/python/pyspark/pandas/tests/connect/series/test_parity_string_ops_adv.py
@@ -22,7 +22,9 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils
class SeriesParityStringOpsAdvTests(
- SeriesStringOpsAdvMixin, PandasOnSparkTestUtils, ReusedConnectTestCase
+ SeriesStringOpsAdvMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
):
pass
diff --git
a/python/pyspark/pandas/tests/connect/series/test_parity_string_ops_basic.py
b/python/pyspark/pandas/tests/connect/series/test_parity_string_ops_basic.py
index 58f10fa505b0..c834a29baeb6 100644
--- a/python/pyspark/pandas/tests/connect/series/test_parity_string_ops_basic.py
+++ b/python/pyspark/pandas/tests/connect/series/test_parity_string_ops_basic.py
@@ -22,7 +22,9 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils
class SeriesStringOpsParityTests(
- SeriesStringOpsMixin, PandasOnSparkTestUtils, ReusedConnectTestCase
+ SeriesStringOpsMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
):
pass
diff --git a/python/pyspark/pandas/tests/frame/test_attrs.py
b/python/pyspark/pandas/tests/frame/test_attrs.py
index c75ed9955239..ff511c0438f2 100644
--- a/python/pyspark/pandas/tests/frame/test_attrs.py
+++ b/python/pyspark/pandas/tests/frame/test_attrs.py
@@ -21,7 +21,7 @@ import numpy as np
import pandas as pd
from pyspark import pandas as ps
-from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.pandasutils import PandasOnSparkTestCase
from pyspark.testing.sqlutils import SQLTestUtils
@@ -35,6 +35,10 @@ class FrameAttrsMixin:
index=np.random.rand(9),
)
+ @property
+ def psdf(self):
+ return ps.from_pandas(self.pdf)
+
@property
def df_pair(self):
pdf = self.pdf
@@ -341,7 +345,11 @@ class FrameAttrsMixin:
self.assert_eq(psdf[psdf["t"] != psdf["t"]].dtypes, pdf[pdf["t"] !=
pdf["t"]].dtypes)
-class FrameAttrsTests(FrameAttrsMixin, ComparisonTestBase, SQLTestUtils):
+class FrameAttrsTests(
+ FrameAttrsMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/frame/test_axis.py
b/python/pyspark/pandas/tests/frame/test_axis.py
index ee67cf1b55ed..b3ce390ca5d4 100644
--- a/python/pyspark/pandas/tests/frame/test_axis.py
+++ b/python/pyspark/pandas/tests/frame/test_axis.py
@@ -20,7 +20,7 @@ import unittest
import pandas as pd
from pyspark import pandas as ps
-from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.pandasutils import PandasOnSparkTestCase
from pyspark.testing.sqlutils import SQLTestUtils
@@ -119,7 +119,11 @@ class FrameAxisMixin:
)
-class FrameAxisTests(FrameAxisMixin, ComparisonTestBase, SQLTestUtils):
+class FrameAxisTests(
+ FrameAxisMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/frame/test_constructor.py
b/python/pyspark/pandas/tests/frame/test_constructor.py
index 1a8b1fed6d83..ee010d8f023d 100644
--- a/python/pyspark/pandas/tests/frame/test_constructor.py
+++ b/python/pyspark/pandas/tests/frame/test_constructor.py
@@ -28,7 +28,7 @@ from pyspark.pandas.typedef.typehints import (
)
from pyspark.pandas.utils import is_testing
-from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.pandasutils import PandasOnSparkTestCase
from pyspark.testing.sqlutils import SQLTestUtils
@@ -572,7 +572,11 @@ class FrameConstructorMixin:
self.assert_eq(psdf.astype(astype), pdf.astype(astype))
-class FrameConstructorTests(FrameConstructorMixin, ComparisonTestBase,
SQLTestUtils):
+class FrameConstructorTests(
+ FrameConstructorMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/frame/test_conversion.py
b/python/pyspark/pandas/tests/frame/test_conversion.py
index eefb461239e0..d31149f241c3 100644
--- a/python/pyspark/pandas/tests/frame/test_conversion.py
+++ b/python/pyspark/pandas/tests/frame/test_conversion.py
@@ -20,7 +20,7 @@ import numpy as np
import pandas as pd
from pyspark import pandas as ps
-from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.pandasutils import PandasOnSparkTestCase
from pyspark.testing.sqlutils import SQLTestUtils
@@ -34,6 +34,10 @@ class FrameConversionMixin:
index=np.random.rand(9),
)
+ @property
+ def psdf(self):
+ return ps.from_pandas(self.pdf)
+
def test_astype(self):
psdf = self.psdf
@@ -51,7 +55,11 @@ class FrameConversionMixin:
self.assert_eq(psdf.isnull(), pdf.isnull())
-class FrameConversionTests(FrameConversionMixin, ComparisonTestBase,
SQLTestUtils):
+class FrameConversionTests(
+ FrameConversionMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/frame/test_interpolate.py
b/python/pyspark/pandas/tests/frame/test_interpolate.py
index 441afa0582c3..a16d680c1880 100644
--- a/python/pyspark/pandas/tests/frame/test_interpolate.py
+++ b/python/pyspark/pandas/tests/frame/test_interpolate.py
@@ -70,7 +70,11 @@ class FrameInterpolateMixin:
self._test_interpolate(pdf)
-class FrameInterpolateTests(FrameInterpolateMixin, PandasOnSparkTestCase,
TestUtils):
+class FrameInterpolateTests(
+ FrameInterpolateMixin,
+ PandasOnSparkTestCase,
+ TestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/frame/test_reindexing.py
b/python/pyspark/pandas/tests/frame/test_reindexing.py
index b3639945391c..33f507c0e030 100644
--- a/python/pyspark/pandas/tests/frame/test_reindexing.py
+++ b/python/pyspark/pandas/tests/frame/test_reindexing.py
@@ -23,7 +23,7 @@ from pandas.tseries.offsets import DateOffset
from pyspark import pandas as ps
from pyspark.errors import PySparkValueError
from pyspark.pandas.config import option_context
-from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.pandasutils import PandasOnSparkTestCase
from pyspark.testing.sqlutils import SQLTestUtils
@@ -842,7 +842,11 @@ class FrameReindexingMixin:
psdf.sample(n=1)
-class FrameReidexingTests(FrameReindexingMixin, ComparisonTestBase,
SQLTestUtils):
+class FrameReidexingTests(
+ FrameReindexingMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/frame/test_reshaping.py
b/python/pyspark/pandas/tests/frame/test_reshaping.py
index 0a1c5e5b0987..b7c732f113d5 100644
--- a/python/pyspark/pandas/tests/frame/test_reshaping.py
+++ b/python/pyspark/pandas/tests/frame/test_reshaping.py
@@ -22,7 +22,7 @@ import pandas as pd
from pyspark import pandas as ps
from pyspark.pandas.config import option_context
-from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.pandasutils import PandasOnSparkTestCase
from pyspark.testing.sqlutils import SQLTestUtils
@@ -464,7 +464,11 @@ class FrameReshapingMixin:
self.assert_eq(pdf.squeeze(axis), psdf.squeeze(axis))
-class FrameReshapingTests(FrameReshapingMixin, ComparisonTestBase,
SQLTestUtils):
+class FrameReshapingTests(
+ FrameReshapingMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/frame/test_spark.py
b/python/pyspark/pandas/tests/frame/test_spark.py
index 36466695c30a..721d8372a960 100644
--- a/python/pyspark/pandas/tests/frame/test_spark.py
+++ b/python/pyspark/pandas/tests/frame/test_spark.py
@@ -29,7 +29,7 @@ from pyspark import pandas as ps
from pyspark.pandas.frame import CachedDataFrame
from pyspark.pandas.exceptions import PandasNotImplementedError
from pyspark.pandas.missing.frame import MissingPandasLikeDataFrame
-from pyspark.testing.pandasutils import ComparisonTestBase,
SPARK_CONF_ARROW_ENABLED
+from pyspark.testing.pandasutils import PandasOnSparkTestCase,
SPARK_CONF_ARROW_ENABLED
from pyspark.testing.sqlutils import SQLTestUtils
@@ -43,6 +43,10 @@ class FrameSparkMixin:
index=np.random.rand(9),
)
+ @property
+ def psdf(self):
+ return ps.from_pandas(self.pdf)
+
def test_empty_dataframe(self):
pdf = pd.DataFrame({"a": pd.Series([], dtype="i1"), "b": pd.Series([],
dtype="str")})
@@ -287,7 +291,11 @@ class FrameSparkMixin:
getattr(psdf, name)
-class FrameSparkTests(FrameSparkMixin, ComparisonTestBase, SQLTestUtils):
+class FrameSparkTests(
+ FrameSparkMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/frame/test_time_series.py
b/python/pyspark/pandas/tests/frame/test_time_series.py
index 61dc095d6ba6..88737b6df4bf 100644
--- a/python/pyspark/pandas/tests/frame/test_time_series.py
+++ b/python/pyspark/pandas/tests/frame/test_time_series.py
@@ -21,7 +21,7 @@ import numpy as np
import pandas as pd
from pyspark import pandas as ps
-from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.pandasutils import PandasOnSparkTestCase
from pyspark.testing.sqlutils import SQLTestUtils
@@ -120,7 +120,11 @@ class FrameTimeSeriesMixin:
self.assert_eq(pd.to_datetime(pdf), ps.to_datetime(psdf))
-class FrameTimeSeriesTests(FrameTimeSeriesMixin, ComparisonTestBase,
SQLTestUtils):
+class FrameTimeSeriesTests(
+ FrameTimeSeriesMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/frame/test_truncate.py
b/python/pyspark/pandas/tests/frame/test_truncate.py
index c6813de4a5f1..b4351fb799b3 100644
--- a/python/pyspark/pandas/tests/frame/test_truncate.py
+++ b/python/pyspark/pandas/tests/frame/test_truncate.py
@@ -19,7 +19,7 @@ import unittest
import pandas as pd
from pyspark import pandas as ps
-from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.pandasutils import PandasOnSparkTestCase
from pyspark.testing.sqlutils import SQLTestUtils
@@ -117,7 +117,7 @@ class FrameTruncateMixin:
psdf.truncate("C", "B", axis=1)
-class FrameTruncateTests(FrameTruncateMixin, ComparisonTestBase, SQLTestUtils):
+class FrameTruncateTests(FrameTruncateMixin, PandasOnSparkTestCase,
SQLTestUtils):
pass
diff --git a/python/pyspark/pandas/tests/groupby/test_aggregate.py
b/python/pyspark/pandas/tests/groupby/test_aggregate.py
index f6fb37aa9824..7b72e2476e95 100644
--- a/python/pyspark/pandas/tests/groupby/test_aggregate.py
+++ b/python/pyspark/pandas/tests/groupby/test_aggregate.py
@@ -19,7 +19,7 @@ import unittest
import pandas as pd
from pyspark import pandas as ps
-from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.pandasutils import PandasOnSparkTestCase
from pyspark.testing.sqlutils import SQLTestUtils
@@ -270,7 +270,11 @@ class GroupbyAggregateMixin:
self.assert_eq(agg_pdf, agg_psdf)
-class GroupbyAggregateTests(GroupbyAggregateMixin, ComparisonTestBase,
SQLTestUtils):
+class GroupbyAggregateTests(
+ GroupbyAggregateMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/groupby/test_apply_func.py
b/python/pyspark/pandas/tests/groupby/test_apply_func.py
index d886d8799444..6f7e4155bbd8 100644
--- a/python/pyspark/pandas/tests/groupby/test_apply_func.py
+++ b/python/pyspark/pandas/tests/groupby/test_apply_func.py
@@ -21,7 +21,7 @@ import pandas as pd
from pyspark import pandas as ps
from pyspark.pandas.config import option_context
-from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.pandasutils import PandasOnSparkTestCase
from pyspark.testing.sqlutils import SQLTestUtils
@@ -487,7 +487,11 @@ class GroupbyApplyFuncMixin:
)
-class GroupbyApplyFuncTests(GroupbyApplyFuncMixin, ComparisonTestBase,
SQLTestUtils):
+class GroupbyApplyFuncTests(
+ GroupbyApplyFuncMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/groupby/test_cumulative.py
b/python/pyspark/pandas/tests/groupby/test_cumulative.py
index 2bcc1ade2d06..5f18d969e05a 100644
--- a/python/pyspark/pandas/tests/groupby/test_cumulative.py
+++ b/python/pyspark/pandas/tests/groupby/test_cumulative.py
@@ -21,7 +21,7 @@ import pandas as pd
from pyspark import pandas as ps
from pyspark.pandas.exceptions import DataError
-from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.pandasutils import PandasOnSparkTestCase
from pyspark.testing.sqlutils import SQLTestUtils
@@ -388,7 +388,11 @@ class GroupbyCumulativeMixin:
self.assertRaises(DataError, lambda:
psdf.groupby(["A"])["B"].cumprod())
-class GroupbyCumulativeTests(GroupbyCumulativeMixin, ComparisonTestBase,
SQLTestUtils):
+class GroupbyCumulativeTests(
+ GroupbyCumulativeMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/groupby/test_describe.py
b/python/pyspark/pandas/tests/groupby/test_describe.py
index ae12aae61ffc..a9ac050cb27b 100644
--- a/python/pyspark/pandas/tests/groupby/test_describe.py
+++ b/python/pyspark/pandas/tests/groupby/test_describe.py
@@ -20,7 +20,7 @@ from itertools import product
import pandas as pd
from pyspark import pandas as ps
-from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.pandasutils import PandasOnSparkTestCase
from pyspark.testing.sqlutils import SQLTestUtils
@@ -113,7 +113,11 @@ class GroupbyDescribeMixin:
)
-class GroupbyDescribeTests(GroupbyDescribeMixin, ComparisonTestBase,
SQLTestUtils):
+class GroupbyDescribeTests(
+ GroupbyDescribeMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/groupby/test_groupby.py
b/python/pyspark/pandas/tests/groupby/test_groupby.py
index 6e7a909aebdc..5867f7b62fa5 100644
--- a/python/pyspark/pandas/tests/groupby/test_groupby.py
+++ b/python/pyspark/pandas/tests/groupby/test_groupby.py
@@ -16,17 +16,11 @@
#
import unittest
-import inspect
import numpy as np
import pandas as pd
from pyspark import pandas as ps
-from pyspark.pandas.exceptions import PandasNotImplementedError
-from pyspark.pandas.missing.groupby import (
- MissingPandasLikeDataFrameGroupBy,
- MissingPandasLikeSeriesGroupBy,
-)
from pyspark.pandas.groupby import is_multi_agg_with_relabel, SeriesGroupBy
from pyspark.testing.pandasutils import PandasOnSparkTestCase, TestUtils
@@ -458,7 +452,11 @@ class GroupByTestsMixin:
)
-class GroupByTests(GroupByTestsMixin, PandasOnSparkTestCase, TestUtils):
+class GroupByTests(
+ GroupByTestsMixin,
+ PandasOnSparkTestCase,
+ TestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/groupby/test_grouping.py
b/python/pyspark/pandas/tests/groupby/test_grouping.py
index 13aa86ad9b4e..784e9e9befc3 100644
--- a/python/pyspark/pandas/tests/groupby/test_grouping.py
+++ b/python/pyspark/pandas/tests/groupby/test_grouping.py
@@ -155,7 +155,10 @@ class GroupingTestsMixin:
self.assertTrue(isinstance(psdf.groupby("a")["b"], SeriesGroupBy))
-class GroupingTests(GroupingTestsMixin, PandasOnSparkTestCase):
+class GroupingTests(
+ GroupingTestsMixin,
+ PandasOnSparkTestCase,
+):
pass
diff --git a/python/pyspark/pandas/tests/groupby/test_head_tail.py
b/python/pyspark/pandas/tests/groupby/test_head_tail.py
index 68a364103e06..3446670bf781 100644
--- a/python/pyspark/pandas/tests/groupby/test_head_tail.py
+++ b/python/pyspark/pandas/tests/groupby/test_head_tail.py
@@ -20,7 +20,7 @@ import numpy as np
import pandas as pd
from pyspark import pandas as ps
-from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.pandasutils import PandasOnSparkTestCase
from pyspark.testing.sqlutils import SQLTestUtils
@@ -202,7 +202,11 @@ class GroupbyHeadTailMixin:
)
-class GroupbyHeadTailTests(GroupbyHeadTailMixin, ComparisonTestBase,
SQLTestUtils):
+class GroupbyHeadTailTests(
+ GroupbyHeadTailMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/groupby/test_index.py
b/python/pyspark/pandas/tests/groupby/test_index.py
index f83ae615161f..747053551e31 100644
--- a/python/pyspark/pandas/tests/groupby/test_index.py
+++ b/python/pyspark/pandas/tests/groupby/test_index.py
@@ -19,7 +19,7 @@ import unittest
import pandas as pd
from pyspark import pandas as ps
-from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.pandasutils import PandasOnSparkTestCase
from pyspark.testing.sqlutils import SQLTestUtils
@@ -164,7 +164,11 @@ class GroupbyIndexMixin:
)
-class GroupbyIndexTests(GroupbyIndexMixin, ComparisonTestBase, SQLTestUtils):
+class GroupbyIndexTests(
+ GroupbyIndexMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/groupby/test_missing.py
b/python/pyspark/pandas/tests/groupby/test_missing.py
index d3c70aa1a985..47c4e4deeedc 100644
--- a/python/pyspark/pandas/tests/groupby/test_missing.py
+++ b/python/pyspark/pandas/tests/groupby/test_missing.py
@@ -128,7 +128,10 @@ class MissingTestsMixin:
getattr(psdf.a.groupby(psdf.a), name)
-class MissingTests(MissingTestsMixin, PandasOnSparkTestCase):
+class MissingTests(
+ MissingTestsMixin,
+ PandasOnSparkTestCase,
+):
pass
diff --git a/python/pyspark/pandas/tests/groupby/test_missing_data.py
b/python/pyspark/pandas/tests/groupby/test_missing_data.py
index 3d54baf7e84e..5d037da3b307 100644
--- a/python/pyspark/pandas/tests/groupby/test_missing_data.py
+++ b/python/pyspark/pandas/tests/groupby/test_missing_data.py
@@ -21,7 +21,7 @@ import numpy as np
import pandas as pd
from pyspark import pandas as ps
-from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.pandasutils import PandasOnSparkTestCase
from pyspark.testing.sqlutils import SQLTestUtils
@@ -303,7 +303,11 @@ class GroupbyMissingDataMixin:
self.assert_eq(sorted_stats_psdf, sorted_stats_pdf)
-class GroupbyMissingDataTests(GroupbyMissingDataMixin, ComparisonTestBase,
SQLTestUtils):
+class GroupbyMissingDataTests(
+ GroupbyMissingDataMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/groupby/test_nlargest_nsmallest.py
b/python/pyspark/pandas/tests/groupby/test_nlargest_nsmallest.py
index e74f880bce8d..0404950808a9 100644
--- a/python/pyspark/pandas/tests/groupby/test_nlargest_nsmallest.py
+++ b/python/pyspark/pandas/tests/groupby/test_nlargest_nsmallest.py
@@ -103,7 +103,10 @@ class NlargestNsmallestTestsMixin:
psdf.set_index(["a", "b"]).groupby(["c"])["d"].nsmallest(1)
-class NlargestNsmallestTests(NlargestNsmallestTestsMixin,
PandasOnSparkTestCase):
+class NlargestNsmallestTests(
+ NlargestNsmallestTestsMixin,
+ PandasOnSparkTestCase,
+):
pass
diff --git a/python/pyspark/pandas/tests/groupby/test_raises.py
b/python/pyspark/pandas/tests/groupby/test_raises.py
index 4fc134f5e06b..816f810b6ec3 100644
--- a/python/pyspark/pandas/tests/groupby/test_raises.py
+++ b/python/pyspark/pandas/tests/groupby/test_raises.py
@@ -36,7 +36,10 @@ class RaisesTestsMixin:
self.assertRaises(KeyError, lambda: psdf.groupby("a")[["b", "x"]])
-class RaisesTests(RaisesTestsMixin, PandasOnSparkTestCase):
+class RaisesTests(
+ RaisesTestsMixin,
+ PandasOnSparkTestCase,
+):
pass
diff --git a/python/pyspark/pandas/tests/groupby/test_rank.py
b/python/pyspark/pandas/tests/groupby/test_rank.py
index f1efbd3f8a4a..55c2db597028 100644
--- a/python/pyspark/pandas/tests/groupby/test_rank.py
+++ b/python/pyspark/pandas/tests/groupby/test_rank.py
@@ -75,7 +75,10 @@ class RankTestsMixin:
)
-class RankTests(RankTestsMixin, PandasOnSparkTestCase):
+class RankTests(
+ RankTestsMixin,
+ PandasOnSparkTestCase,
+):
pass
diff --git a/python/pyspark/pandas/tests/groupby/test_size.py
b/python/pyspark/pandas/tests/groupby/test_size.py
index 8d187ba377a3..495917fefaa6 100644
--- a/python/pyspark/pandas/tests/groupby/test_size.py
+++ b/python/pyspark/pandas/tests/groupby/test_size.py
@@ -54,7 +54,10 @@ class SizeTestsMixin:
)
-class SizeTests(SizeTestsMixin, PandasOnSparkTestCase):
+class SizeTests(
+ SizeTestsMixin,
+ PandasOnSparkTestCase,
+):
pass
diff --git a/python/pyspark/pandas/tests/groupby/test_value_counts.py
b/python/pyspark/pandas/tests/groupby/test_value_counts.py
index 5ed2d1b0583d..fa01de7466f7 100644
--- a/python/pyspark/pandas/tests/groupby/test_value_counts.py
+++ b/python/pyspark/pandas/tests/groupby/test_value_counts.py
@@ -88,7 +88,10 @@ class ValueCountsTestsMixin:
)
-class ValueCountsTests(ValueCountsTestsMixin, PandasOnSparkTestCase):
+class ValueCountsTests(
+ ValueCountsTestsMixin,
+ PandasOnSparkTestCase,
+):
pass
diff --git a/python/pyspark/pandas/tests/series/test_all_any.py
b/python/pyspark/pandas/tests/series/test_all_any.py
index 52ef5a26f4df..3329c098796c 100644
--- a/python/pyspark/pandas/tests/series/test_all_any.py
+++ b/python/pyspark/pandas/tests/series/test_all_any.py
@@ -20,7 +20,7 @@ import numpy as np
import pandas as pd
from pyspark import pandas as ps
-from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.pandasutils import PandasOnSparkTestCase
from pyspark.testing.sqlutils import SQLTestUtils
@@ -81,7 +81,11 @@ class SeriesAllAnyMixin:
psser.any(axis=1)
-class SeriesAllAnyTests(SeriesAllAnyMixin, ComparisonTestBase, SQLTestUtils):
+class SeriesAllAnyTests(
+ SeriesAllAnyMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/series/test_arg_ops.py
b/python/pyspark/pandas/tests/series/test_arg_ops.py
index 134296462c1b..4c00594ea666 100644
--- a/python/pyspark/pandas/tests/series/test_arg_ops.py
+++ b/python/pyspark/pandas/tests/series/test_arg_ops.py
@@ -20,7 +20,7 @@ import numpy as np
import pandas as pd
from pyspark import pandas as ps
-from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.pandasutils import PandasOnSparkTestCase
from pyspark.testing.sqlutils import SQLTestUtils
@@ -173,7 +173,11 @@ class SeriesArgOpsMixin:
psser.argmin(axis=1)
-class SeriesArgOpsTests(SeriesArgOpsMixin, ComparisonTestBase, SQLTestUtils):
+class SeriesArgOpsTests(
+ SeriesArgOpsMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/series/test_as_of.py
b/python/pyspark/pandas/tests/series/test_as_of.py
index ad3e2522b652..628c72c73d25 100644
--- a/python/pyspark/pandas/tests/series/test_as_of.py
+++ b/python/pyspark/pandas/tests/series/test_as_of.py
@@ -20,7 +20,7 @@ import numpy as np
import pandas as pd
from pyspark import pandas as ps
-from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.pandasutils import PandasOnSparkTestCase
from pyspark.testing.sqlutils import SQLTestUtils
@@ -113,7 +113,11 @@ class SeriesAsOfMixin:
self.assert_eq(psser.asof([10, np.nan]), pser.asof([10, np.nan]))
-class SeriesAsOfTests(SeriesAsOfMixin, ComparisonTestBase, SQLTestUtils):
+class SeriesAsOfTests(
+ SeriesAsOfMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/series/test_as_type.py
b/python/pyspark/pandas/tests/series/test_as_type.py
index 70352c34879f..ffe88e7404ae 100644
--- a/python/pyspark/pandas/tests/series/test_as_type.py
+++ b/python/pyspark/pandas/tests/series/test_as_type.py
@@ -20,7 +20,7 @@ import numpy as np
import pandas as pd
from pyspark import pandas as ps
-from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.pandasutils import PandasOnSparkTestCase
from pyspark.testing.sqlutils import SQLTestUtils
from pyspark.pandas.typedef.typehints import (
extension_dtypes_available,
@@ -160,7 +160,11 @@ class SeriesAsTypeMixin:
self.assert_eq(psser, pser)
-class SeriesAsTypeTests(SeriesAsTypeMixin, ComparisonTestBase, SQLTestUtils):
+class SeriesAsTypeTests(
+ SeriesAsTypeMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/series/test_compute.py
b/python/pyspark/pandas/tests/series/test_compute.py
index 05cd42fe4ed1..20c3c856c8e0 100644
--- a/python/pyspark/pandas/tests/series/test_compute.py
+++ b/python/pyspark/pandas/tests/series/test_compute.py
@@ -22,7 +22,7 @@ import pandas as pd
from pyspark import pandas as ps
from pyspark.errors import PySparkValueError
-from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.pandasutils import PandasOnSparkTestCase
from pyspark.testing.sqlutils import SQLTestUtils
@@ -575,7 +575,11 @@ class SeriesComputeMixin:
)
-class SeriesComputeTests(SeriesComputeMixin, ComparisonTestBase, SQLTestUtils):
+class SeriesComputeTests(
+ SeriesComputeMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/series/test_conversion.py
b/python/pyspark/pandas/tests/series/test_conversion.py
index 9d98d45ca74b..71ae858631d4 100644
--- a/python/pyspark/pandas/tests/series/test_conversion.py
+++ b/python/pyspark/pandas/tests/series/test_conversion.py
@@ -19,7 +19,7 @@ import unittest
import pandas as pd
from pyspark import pandas as ps
-from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.pandasutils import PandasOnSparkTestCase
from pyspark.testing.sqlutils import SQLTestUtils
from pyspark.testing.pandasutils import have_tabulate,
tabulate_requirement_message
@@ -72,7 +72,11 @@ class SeriesConversionMixin:
self.assert_eq(pser.to_markdown(), psser.to_markdown())
-class SeriesConversionTests(SeriesConversionMixin, ComparisonTestBase,
SQLTestUtils):
+class SeriesConversionTests(
+ SeriesConversionMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/series/test_cumulative.py
b/python/pyspark/pandas/tests/series/test_cumulative.py
index ee85b2f7d00a..923eda54e3e3 100644
--- a/python/pyspark/pandas/tests/series/test_cumulative.py
+++ b/python/pyspark/pandas/tests/series/test_cumulative.py
@@ -19,7 +19,7 @@ import unittest
import pandas as pd
from pyspark import pandas as ps
-from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.pandasutils import PandasOnSparkTestCase
from pyspark.testing.sqlutils import SQLTestUtils
@@ -114,7 +114,11 @@ class SeriesCumulativeMixin:
ps.Series(["a", "b", "c", "d"]).cumprod()
-class SeriesCumulativeTests(SeriesCumulativeMixin, ComparisonTestBase,
SQLTestUtils):
+class SeriesCumulativeTests(
+ SeriesCumulativeMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/series/test_index.py
b/python/pyspark/pandas/tests/series/test_index.py
index 6f3f98c56f4c..69e97bfde6c5 100644
--- a/python/pyspark/pandas/tests/series/test_index.py
+++ b/python/pyspark/pandas/tests/series/test_index.py
@@ -20,7 +20,7 @@ import numpy as np
import pandas as pd
from pyspark import pandas as ps
-from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.pandasutils import PandasOnSparkTestCase
from pyspark.testing.sqlutils import SQLTestUtils
@@ -451,7 +451,11 @@ class SeriesIndexMixin:
)
-class SeriesIndexTests(SeriesIndexMixin, ComparisonTestBase, SQLTestUtils):
+class SeriesIndexTests(
+ SeriesIndexMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/series/test_missing_data.py
b/python/pyspark/pandas/tests/series/test_missing_data.py
index 5d08c9a56eb6..7336ef23cc61 100644
--- a/python/pyspark/pandas/tests/series/test_missing_data.py
+++ b/python/pyspark/pandas/tests/series/test_missing_data.py
@@ -20,7 +20,7 @@ import numpy as np
import pandas as pd
from pyspark import pandas as ps
-from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.pandasutils import PandasOnSparkTestCase
from pyspark.testing.sqlutils import SQLTestUtils
@@ -224,7 +224,11 @@ class SeriesMissingDataMixin:
self.assert_eq(pdf, psdf)
-class SeriesMissingDataTests(SeriesMissingDataMixin, ComparisonTestBase,
SQLTestUtils):
+class SeriesMissingDataTests(
+ SeriesMissingDataMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/series/test_series.py
b/python/pyspark/pandas/tests/series/test_series.py
index 4d463fe775b7..2fdb91b5ca37 100644
--- a/python/pyspark/pandas/tests/series/test_series.py
+++ b/python/pyspark/pandas/tests/series/test_series.py
@@ -774,7 +774,11 @@ class SeriesTestsMixin:
psser.transform(lambda x: x + 1, axis=1)
-class SeriesTests(SeriesTestsMixin, PandasOnSparkTestCase, SQLTestUtils):
+class SeriesTests(
+ SeriesTestsMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/series/test_sort.py
b/python/pyspark/pandas/tests/series/test_sort.py
index a0b724a149b6..50217346a7ae 100644
--- a/python/pyspark/pandas/tests/series/test_sort.py
+++ b/python/pyspark/pandas/tests/series/test_sort.py
@@ -20,7 +20,7 @@ import numpy as np
import pandas as pd
from pyspark import pandas as ps
-from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.pandasutils import PandasOnSparkTestCase
from pyspark.testing.sqlutils import SQLTestUtils
@@ -138,7 +138,11 @@ class SeriesSortMixin:
ps.from_pandas(pser1).searchsorted(1.1, side="middle")
-class SeriesSortTests(SeriesSortMixin, ComparisonTestBase, SQLTestUtils):
+class SeriesSortTests(
+ SeriesSortMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/series/test_stat.py
b/python/pyspark/pandas/tests/series/test_stat.py
index b2f98544ba10..63484bff9d5b 100644
--- a/python/pyspark/pandas/tests/series/test_stat.py
+++ b/python/pyspark/pandas/tests/series/test_stat.py
@@ -21,7 +21,7 @@ import numpy as np
import pandas as pd
from pyspark import pandas as ps
-from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.pandasutils import PandasOnSparkTestCase
from pyspark.testing.sqlutils import SQLTestUtils
@@ -694,7 +694,11 @@ class SeriesStatMixin:
ps.Series(["a", "b", "c"]).sem()
-class SeriesStatTests(SeriesStatMixin, ComparisonTestBase, SQLTestUtils):
+class SeriesStatTests(
+ SeriesStatMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/series/test_string_ops_adv.py
b/python/pyspark/pandas/tests/series/test_string_ops_adv.py
index d1954cdf6dad..eeffd8fa7d0a 100644
--- a/python/pyspark/pandas/tests/series/test_string_ops_adv.py
+++ b/python/pyspark/pandas/tests/series/test_string_ops_adv.py
@@ -213,7 +213,11 @@ class SeriesStringOpsAdvMixin:
self.check_func(lambda x: x.str.get_dummies())
-class SeriesStringOpsAdvTests(SeriesStringOpsAdvMixin, PandasOnSparkTestCase,
SQLTestUtils):
+class SeriesStringOpsAdvTests(
+ SeriesStringOpsAdvMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/series/test_string_ops_basic.py
b/python/pyspark/pandas/tests/series/test_string_ops_basic.py
index bdb3bf74b098..329b3d3d7c02 100644
--- a/python/pyspark/pandas/tests/series/test_string_ops_basic.py
+++ b/python/pyspark/pandas/tests/series/test_string_ops_basic.py
@@ -167,7 +167,11 @@ class SeriesStringOpsMixin:
self.check_func(lambda x: x.str.count("WH", flags=re.IGNORECASE))
-class SeriesStringOpsTests(SeriesStringOpsMixin, PandasOnSparkTestCase,
SQLTestUtils):
+class SeriesStringOpsTests(
+ SeriesStringOpsMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
pass
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org
For additional commands, e-mail: commits-h...@spark.apache.org
