Skip to content

[SPARK-46651][PS][TESTS] Split FrameTakeTests #44656

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
zhengruifeng wants to merge 1 commit into from
Closed

[SPARK-46651][PS][TESTS] Split FrameTakeTests #44656

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions dev/sparktestsupport/modules.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -865,6 +865,7 @@ def __hash__(self):
"pyspark.pandas.tests.frame.test_reshaping",
"pyspark.pandas.tests.frame.test_spark",
"pyspark.pandas.tests.frame.test_take",
"pyspark.pandas.tests.frame.test_take_adv",
"pyspark.pandas.tests.frame.test_time_series",
"pyspark.pandas.tests.frame.test_truncate",
"pyspark.pandas.tests.io.test_io",
Expand Down Expand Up @@ -1165,6 +1166,7 @@ def __hash__(self):
"pyspark.pandas.tests.connect.frame.test_parity_reshaping",
"pyspark.pandas.tests.connect.frame.test_parity_spark",
"pyspark.pandas.tests.connect.frame.test_parity_take",
"pyspark.pandas.tests.connect.frame.test_parity_take_adv",
"pyspark.pandas.tests.connect.frame.test_parity_time_series",
"pyspark.pandas.tests.connect.frame.test_parity_truncate",
"pyspark.pandas.tests.connect.groupby.test_parity_aggregate",
Expand Down
11 changes: 6 additions & 5 deletions python/pyspark/pandas/tests/connect/frame/test_parity_take.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,16 +16,17 @@
#
import unittest

from pyspark import pandas as ps
from pyspark.pandas.tests.frame.test_take import FrameTakeMixin
from pyspark.testing.connectutils import ReusedConnectTestCase
from pyspark.testing.pandasutils import PandasOnSparkTestUtils


class FrameParityTakeTests(FrameTakeMixin, PandasOnSparkTestUtils, ReusedConnectTestCase):
@property
def psdf(self):
return ps.from_pandas(self.pdf)
class FrameTakeParityTests(
FrameTakeMixin,
PandasOnSparkTestUtils,
ReusedConnectTestCase,
):
pass


if __name__ == "__main__":
Expand Down
41 changes: 41 additions & 0 deletions python/pyspark/pandas/tests/connect/frame/test_parity_take_adv.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,41 @@
#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
import unittest

from pyspark.pandas.tests.frame.test_take_adv import FrameTakeAdvMixin
from pyspark.testing.connectutils import ReusedConnectTestCase
from pyspark.testing.pandasutils import PandasOnSparkTestUtils


class FrameTakeAdvParityTests(
FrameTakeAdvMixin,
PandasOnSparkTestUtils,
ReusedConnectTestCase,
):
pass


if __name__ == "__main__":
from pyspark.pandas.tests.connect.frame.test_parity_take_adv import * # noqa: F401

try:
import xmlrunner # type: ignore[import]

testRunner = xmlrunner.XMLTestRunner(output="target/test-reports", verbosity=2)
except ImportError:
testRunner = None
unittest.main(testRunner=testRunner, verbosity=2)
61 changes: 6 additions & 55 deletions python/pyspark/pandas/tests/frame/test_take.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@
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


Expand Down Expand Up @@ -72,61 +72,12 @@ def test_take(self):
pdf.take([-1, -2], axis=1).sort_index(),
)

# MultiIndex columns
columns = pd.MultiIndex.from_tuples([("A", "Z"), ("B", "X"), ("C", "C")])
psdf.columns = columns
pdf.columns = columns

# MultiIndex columns with axis=0 (default)
self.assert_eq(psdf.take([1, 2]).sort_index(), pdf.take([1, 2]).sort_index())
self.assert_eq(psdf.take([-1, -2]).sort_index(), pdf.take([-1, -2]).sort_index())
self.assert_eq(
psdf.take(range(100, 110)).sort_index(), pdf.take(range(100, 110)).sort_index()
)
self.assert_eq(
psdf.take(range(-110, -100)).sort_index(), pdf.take(range(-110, -100)).sort_index()
)
self.assert_eq(
psdf.take([10, 100, 1000, 10000]).sort_index(),
pdf.take([10, 100, 1000, 10000]).sort_index(),
)
self.assert_eq(
psdf.take([-10, -100, -1000, -10000]).sort_index(),
pdf.take([-10, -100, -1000, -10000]).sort_index(),
)

# axis=1
self.assert_eq(
psdf.take([1, 2], axis=1).sort_index(), pdf.take([1, 2], axis=1).sort_index()
)
self.assert_eq(
psdf.take([-1, -2], axis=1).sort_index(), pdf.take([-1, -2], axis=1).sort_index()
)
self.assert_eq(
psdf.take(range(1, 3), axis=1).sort_index(),
pdf.take(range(1, 3), axis=1).sort_index(),
)
self.assert_eq(
psdf.take(range(-1, -3), axis=1).sort_index(),
pdf.take(range(-1, -3), axis=1).sort_index(),
)
self.assert_eq(
psdf.take([2, 1], axis=1).sort_index(),
pdf.take([2, 1], axis=1).sort_index(),
)
self.assert_eq(
psdf.take([-1, -2], axis=1).sort_index(),
pdf.take([-1, -2], axis=1).sort_index(),
)

# Checking the type of indices.
self.assertRaises(TypeError, lambda: psdf.take(1))
self.assertRaises(TypeError, lambda: psdf.take("1"))
self.assertRaises(TypeError, lambda: psdf.take({1, 2}))
self.assertRaises(TypeError, lambda: psdf.take({1: None, 2: None}))


class FrameTakeTests(FrameTakeMixin, ComparisonTestBase, SQLTestUtils):
class FrameTakeTests(
FrameTakeMixin,
PandasOnSparkTestCase,
SQLTestUtils,
):
pass


Expand Down
104 changes: 104 additions & 0 deletions python/pyspark/pandas/tests/frame/test_take_adv.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,104 @@
#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
import unittest

import pandas as pd

from pyspark import pandas as ps
from pyspark.testing.pandasutils import PandasOnSparkTestCase
from pyspark.testing.sqlutils import SQLTestUtils


class FrameTakeAdvMixin:
def test_take_adv(self):
pdf = pd.DataFrame(
{"A": range(0, 50000), "B": range(100000, 0, -2), "C": range(100000, 50000, -1)}
)
psdf = ps.from_pandas(pdf)

# MultiIndex columns
columns = pd.MultiIndex.from_tuples([("A", "Z"), ("B", "X"), ("C", "C")])
psdf.columns = columns
pdf.columns = columns

# MultiIndex columns with axis=0 (default)
self.assert_eq(psdf.take([1, 2]).sort_index(), pdf.take([1, 2]).sort_index())
self.assert_eq(psdf.take([-1, -2]).sort_index(), pdf.take([-1, -2]).sort_index())
self.assert_eq(
psdf.take(range(100, 110)).sort_index(), pdf.take(range(100, 110)).sort_index()
)
self.assert_eq(
psdf.take(range(-110, -100)).sort_index(), pdf.take(range(-110, -100)).sort_index()
)
self.assert_eq(
psdf.take([10, 100, 1000, 10000]).sort_index(),
pdf.take([10, 100, 1000, 10000]).sort_index(),
)
self.assert_eq(
psdf.take([-10, -100, -1000, -10000]).sort_index(),
pdf.take([-10, -100, -1000, -10000]).sort_index(),
)

# axis=1
self.assert_eq(
psdf.take([1, 2], axis=1).sort_index(), pdf.take([1, 2], axis=1).sort_index()
)
self.assert_eq(
psdf.take([-1, -2], axis=1).sort_index(), pdf.take([-1, -2], axis=1).sort_index()
)
self.assert_eq(
psdf.take(range(1, 3), axis=1).sort_index(),
pdf.take(range(1, 3), axis=1).sort_index(),
)
self.assert_eq(
psdf.take(range(-1, -3), axis=1).sort_index(),
pdf.take(range(-1, -3), axis=1).sort_index(),
)
self.assert_eq(
psdf.take([2, 1], axis=1).sort_index(),
pdf.take([2, 1], axis=1).sort_index(),
)
self.assert_eq(
psdf.take([-1, -2], axis=1).sort_index(),
pdf.take([-1, -2], axis=1).sort_index(),
)

# Checking the type of indices.
self.assertRaises(TypeError, lambda: psdf.take(1))
self.assertRaises(TypeError, lambda: psdf.take("1"))
self.assertRaises(TypeError, lambda: psdf.take({1, 2}))
self.assertRaises(TypeError, lambda: psdf.take({1: None, 2: None}))


class FrameTakeAdvTests(
FrameTakeAdvMixin,
PandasOnSparkTestCase,
SQLTestUtils,
):
pass


if __name__ == "__main__":
from pyspark.pandas.tests.frame.test_take_adv import * # noqa: F401

try:
import xmlrunner

testRunner = xmlrunner.XMLTestRunner(output="target/test-reports", verbosity=2)
except ImportError:
testRunner = None
unittest.main(testRunner=testRunner, verbosity=2)