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 d85ad1c14182 [SPARK-46500][PS][TESTS] Reorganize
`FrameParityPivotTests`
d85ad1c14182 is described below
commit d85ad1c14182d847e8a5d5d49cf21cd9079b284f
Author: Ruifeng Zheng <[email protected]>
AuthorDate: Mon Dec 25 17:43:57 2023 +0800
[SPARK-46500][PS][TESTS] Reorganize `FrameParityPivotTests`
### What changes were proposed in this pull request?
Reorganize `FrameParityPivotTests`: break `test_pivot_table` into mutiple
tests
### Why are the changes needed?
this test is slow
```
Starting test(python3.9):
pyspark.pandas.tests.connect.computation.test_parity_pivot (temp output:
/__w/spark/spark/python/target/5f37e442-9037-47cc-8c6b-e9a273299d0d/python3.9__pyspark.pandas.tests.connect.computation.test_parity_pivot__ozvdx_ay.log)
Finished test(python3.9):
pyspark.pandas.tests.connect.computation.test_parity_pivot (524s)
```
### 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 #44478 from zhengruifeng/ps_test_pivot_multi.
Authored-by: Ruifeng Zheng <[email protected]>
Signed-off-by: Ruifeng Zheng <[email protected]>
---
dev/sparktestsupport/modules.py | 8 ++
.../pyspark/pandas/tests/computation/test_pivot.py | 149 +--------------------
.../pandas/tests/computation/test_pivot_table.py | 93 +++++++++++++
.../tests/computation/test_pivot_table_adv.py | 93 +++++++++++++
.../computation/test_pivot_table_multi_idx.py | 91 +++++++++++++
.../computation/test_pivot_table_multi_idx_adv.py | 93 +++++++++++++
.../tests/connect/computation/test_parity_pivot.py | 6 +-
..._parity_pivot.py => test_parity_pivot_table.py} | 10 +-
...ity_pivot.py => test_parity_pivot_table_adv.py} | 10 +-
...vot.py => test_parity_pivot_table_multi_idx.py} | 10 +-
...py => test_parity_pivot_table_multi_idx_adv.py} | 12 +-
11 files changed, 418 insertions(+), 157 deletions(-)
diff --git a/dev/sparktestsupport/modules.py b/dev/sparktestsupport/modules.py
index e4e3803a8f87..6f41b6f0eddf 100644
--- a/dev/sparktestsupport/modules.py
+++ b/dev/sparktestsupport/modules.py
@@ -824,6 +824,10 @@ pyspark_pandas_slow = Module(
"pyspark.pandas.tests.computation.test_melt",
"pyspark.pandas.tests.computation.test_missing_data",
"pyspark.pandas.tests.computation.test_pivot",
+ "pyspark.pandas.tests.computation.test_pivot_table",
+ "pyspark.pandas.tests.computation.test_pivot_table_adv",
+ "pyspark.pandas.tests.computation.test_pivot_table_multi_idx",
+ "pyspark.pandas.tests.computation.test_pivot_table_multi_idx_adv",
"pyspark.pandas.tests.computation.test_stats",
"pyspark.pandas.tests.frame.test_attrs",
"pyspark.pandas.tests.frame.test_axis",
@@ -1162,6 +1166,10 @@ pyspark_pandas_connect_part2 = Module(
python_test_goals=[
# pandas-on-Spark unittests
"pyspark.pandas.tests.connect.computation.test_parity_pivot",
+ "pyspark.pandas.tests.connect.computation.test_parity_pivot_table",
+ "pyspark.pandas.tests.connect.computation.test_parity_pivot_table_adv",
+
"pyspark.pandas.tests.connect.computation.test_parity_pivot_table_multi_idx",
+
"pyspark.pandas.tests.connect.computation.test_parity_pivot_table_multi_idx_adv",
"pyspark.pandas.tests.connect.computation.test_parity_stats",
"pyspark.pandas.tests.connect.indexes.test_parity_base_slow",
"pyspark.pandas.tests.connect.frame.test_parity_interpolate",
diff --git a/python/pyspark/pandas/tests/computation/test_pivot.py
b/python/pyspark/pandas/tests/computation/test_pivot.py
index 8a373108ddc8..2670fa384dc7 100644
--- a/python/pyspark/pandas/tests/computation/test_pivot.py
+++ b/python/pyspark/pandas/tests/computation/test_pivot.py
@@ -61,149 +61,6 @@ class FramePivotMixin:
# columns="a", values="b", fill_value=999).dtypes,
pdf.pivot_table(index=['e', 'c'],
# columns="a", values="b", fill_value=999).dtypes)
- def test_pivot_table(self):
- pdf = pd.DataFrame(
- {
- "a": [4, 2, 3, 4, 8, 6],
- "b": [1, 2, 2, 4, 2, 4],
- "e": [10, 20, 20, 40, 20, 40],
- "c": [1, 2, 9, 4, 7, 4],
- "d": [-1, -2, -3, -4, -5, -6],
- },
- index=np.random.rand(6),
- )
- psdf = ps.from_pandas(pdf)
-
- # Checking if both DataFrames have the same results
- self.assert_eq(
- psdf.pivot_table(columns="a", values="b").sort_index(),
- pdf.pivot_table(columns="a", values="b").sort_index(),
- almost=True,
- )
-
- self.assert_eq(
- psdf.pivot_table(index=["c"], columns="a",
values="b").sort_index(),
- pdf.pivot_table(index=["c"], columns="a", values="b").sort_index(),
- almost=True,
- )
-
- self.assert_eq(
- psdf.pivot_table(index=["c"], columns="a", values="b",
aggfunc="sum").sort_index(),
- pdf.pivot_table(index=["c"], columns="a", values="b",
aggfunc="sum").sort_index(),
- almost=True,
- )
-
- self.assert_eq(
- psdf.pivot_table(index=["c"], columns="a", values=["b"],
aggfunc="sum").sort_index(),
- pdf.pivot_table(index=["c"], columns="a", values=["b"],
aggfunc="sum").sort_index(),
- almost=True,
- )
-
- self.assert_eq(
- psdf.pivot_table(
- index=["c"], columns="a", values=["b", "e"], aggfunc="sum"
- ).sort_index(),
- pdf.pivot_table(
- index=["c"], columns="a", values=["b", "e"], aggfunc="sum"
- ).sort_index(),
- almost=True,
- )
-
- self.assert_eq(
- psdf.pivot_table(
- index=["c"], columns="a", values=["b", "e", "d"], aggfunc="sum"
- ).sort_index(),
- pdf.pivot_table(
- index=["c"], columns="a", values=["b", "e", "d"], aggfunc="sum"
- ).sort_index(),
- almost=True,
- )
-
- self.assert_eq(
- psdf.pivot_table(
- index=["c"], columns="a", values=["b", "e"], aggfunc={"b":
"mean", "e": "sum"}
- ).sort_index(),
- pdf.pivot_table(
- index=["c"], columns="a", values=["b", "e"], aggfunc={"b":
"mean", "e": "sum"}
- ).sort_index(),
- almost=True,
- )
-
- self.assert_eq(
- psdf.pivot_table(index=["e", "c"], columns="a",
values="b").sort_index(),
- pdf.pivot_table(index=["e", "c"], columns="a",
values="b").sort_index(),
- almost=True,
- )
-
- self.assert_eq(
- psdf.pivot_table(
- index=["e", "c"], columns="a", values="b", fill_value=999
- ).sort_index(),
- pdf.pivot_table(index=["e", "c"], columns="a", values="b",
fill_value=999).sort_index(),
- almost=True,
- )
-
- # multi-index columns
- columns = pd.MultiIndex.from_tuples(
- [("x", "a"), ("x", "b"), ("y", "e"), ("z", "c"), ("w", "d")]
- )
- pdf.columns = columns
- psdf.columns = columns
-
- self.assert_eq(
- psdf.pivot_table(columns=("x", "a"), values=("x",
"b")).sort_index(),
- pdf.pivot_table(columns=[("x", "a")], values=[("x",
"b")]).sort_index(),
- almost=True,
- )
-
- self.assert_eq(
- psdf.pivot_table(
- index=[("z", "c")], columns=("x", "a"), values=[("x", "b")]
- ).sort_index(),
- pdf.pivot_table(
- index=[("z", "c")], columns=[("x", "a")], values=[("x", "b")]
- ).sort_index(),
- almost=True,
- )
-
- self.assert_eq(
- psdf.pivot_table(
- index=[("z", "c")], columns=("x", "a"), values=[("x", "b"),
("y", "e")]
- ).sort_index(),
- pdf.pivot_table(
- index=[("z", "c")], columns=[("x", "a")], values=[("x", "b"),
("y", "e")]
- ).sort_index(),
- almost=True,
- )
-
- self.assert_eq(
- psdf.pivot_table(
- index=[("z", "c")], columns=("x", "a"), values=[("x", "b"),
("y", "e"), ("w", "d")]
- ).sort_index(),
- pdf.pivot_table(
- index=[("z", "c")],
- columns=[("x", "a")],
- values=[("x", "b"), ("y", "e"), ("w", "d")],
- ).sort_index(),
- almost=True,
- )
-
- self.assert_eq(
- psdf.pivot_table(
- index=[("z", "c")],
- columns=("x", "a"),
- values=[("x", "b"), ("y", "e")],
- aggfunc={("x", "b"): "mean", ("y", "e"): "sum"},
- ).sort_index(),
- pdf.pivot_table(
- index=[("z", "c")],
- columns=[("x", "a")],
- values=[("x", "b"), ("y", "e")],
- aggfunc={("x", "b"): "mean", ("y", "e"): "sum"},
- ).sort_index(),
- almost=True,
- )
-
def test_pivot_table_and_index(self):
# https://github.com/databricks/koalas/issues/805
pdf = pd.DataFrame(
@@ -332,7 +189,11 @@ class FramePivotMixin:
psdf.pivot_table(index=["C"], columns="A", values="B",
aggfunc={"B": "mean"})
-class FramePivotTests(FramePivotMixin, ComparisonTestBase, SQLTestUtils):
+class FramePivotTests(
+ FramePivotMixin,
+ ComparisonTestBase,
+ SQLTestUtils,
+):
pass
diff --git a/python/pyspark/pandas/tests/computation/test_pivot_table.py
b/python/pyspark/pandas/tests/computation/test_pivot_table.py
new file mode 100644
index 000000000000..5bca2cee55f5
--- /dev/null
+++ b/python/pyspark/pandas/tests/computation/test_pivot_table.py
@@ -0,0 +1,93 @@
+#
+# 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 numpy as np
+import pandas as pd
+
+from pyspark import pandas as ps
+from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.sqlutils import SQLTestUtils
+
+
+class PivotTableMixin:
+ def test_pivot_table(self):
+ pdf = pd.DataFrame(
+ {
+ "a": [4, 2, 3, 4, 8, 6],
+ "b": [1, 2, 2, 4, 2, 4],
+ "e": [10, 20, 20, 40, 20, 40],
+ "c": [1, 2, 9, 4, 7, 4],
+ "d": [-1, -2, -3, -4, -5, -6],
+ },
+ index=np.random.rand(6),
+ )
+ psdf = ps.from_pandas(pdf)
+
+ self.assert_eq(
+ psdf.pivot_table(columns="a", values="b").sort_index(),
+ pdf.pivot_table(columns="a", values="b").sort_index(),
+ almost=True,
+ )
+
+ self.assert_eq(
+ psdf.pivot_table(index=["c"], columns="a",
values="b").sort_index(),
+ pdf.pivot_table(index=["c"], columns="a", values="b").sort_index(),
+ almost=True,
+ )
+
+ self.assert_eq(
+ psdf.pivot_table(index=["c"], columns="a", values="b",
aggfunc="sum").sort_index(),
+ pdf.pivot_table(index=["c"], columns="a", values="b",
aggfunc="sum").sort_index(),
+ almost=True,
+ )
+
+ self.assert_eq(
+ psdf.pivot_table(index=["c"], columns="a", values=["b"],
aggfunc="sum").sort_index(),
+ pdf.pivot_table(index=["c"], columns="a", values=["b"],
aggfunc="sum").sort_index(),
+ almost=True,
+ )
+
+ self.assert_eq(
+ psdf.pivot_table(
+ index=["c"], columns="a", values=["b", "e"], aggfunc="sum"
+ ).sort_index(),
+ pdf.pivot_table(
+ index=["c"], columns="a", values=["b", "e"], aggfunc="sum"
+ ).sort_index(),
+ almost=True,
+ )
+
+
+class PivotTableTests(
+ PivotTableMixin,
+ ComparisonTestBase,
+ SQLTestUtils,
+):
+ pass
+
+
+if __name__ == "__main__":
+ from pyspark.pandas.tests.computation.test_pivot_table 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)
diff --git a/python/pyspark/pandas/tests/computation/test_pivot_table_adv.py
b/python/pyspark/pandas/tests/computation/test_pivot_table_adv.py
new file mode 100644
index 000000000000..d4aa75607529
--- /dev/null
+++ b/python/pyspark/pandas/tests/computation/test_pivot_table_adv.py
@@ -0,0 +1,93 @@
+#
+# 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 numpy as np
+import pandas as pd
+
+from pyspark import pandas as ps
+from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.sqlutils import SQLTestUtils
+
+
+class PivotTableAdvMixin:
+ def test_pivot_table(self):
+ pdf = pd.DataFrame(
+ {
+ "a": [4, 2, 3, 4, 8, 6],
+ "b": [1, 2, 2, 4, 2, 4],
+ "e": [10, 20, 20, 40, 20, 40],
+ "c": [1, 2, 9, 4, 7, 4],
+ "d": [-1, -2, -3, -4, -5, -6],
+ },
+ index=np.random.rand(6),
+ )
+ psdf = ps.from_pandas(pdf)
+
+ self.assert_eq(
+ psdf.pivot_table(
+ index=["c"], columns="a", values=["b", "e", "d"], aggfunc="sum"
+ ).sort_index(),
+ pdf.pivot_table(
+ index=["c"], columns="a", values=["b", "e", "d"], aggfunc="sum"
+ ).sort_index(),
+ almost=True,
+ )
+
+ self.assert_eq(
+ psdf.pivot_table(
+ index=["c"], columns="a", values=["b", "e"], aggfunc={"b":
"mean", "e": "sum"}
+ ).sort_index(),
+ pdf.pivot_table(
+ index=["c"], columns="a", values=["b", "e"], aggfunc={"b":
"mean", "e": "sum"}
+ ).sort_index(),
+ almost=True,
+ )
+
+ self.assert_eq(
+ psdf.pivot_table(index=["e", "c"], columns="a",
values="b").sort_index(),
+ pdf.pivot_table(index=["e", "c"], columns="a",
values="b").sort_index(),
+ almost=True,
+ )
+
+ self.assert_eq(
+ psdf.pivot_table(
+ index=["e", "c"], columns="a", values="b", fill_value=999
+ ).sort_index(),
+ pdf.pivot_table(index=["e", "c"], columns="a", values="b",
fill_value=999).sort_index(),
+ almost=True,
+ )
+
+
+class PivotTableAdvTests(
+ PivotTableAdvMixin,
+ ComparisonTestBase,
+ SQLTestUtils,
+):
+ pass
+
+
+if __name__ == "__main__":
+ from pyspark.pandas.tests.computation.test_pivot_table_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)
diff --git
a/python/pyspark/pandas/tests/computation/test_pivot_table_multi_idx.py
b/python/pyspark/pandas/tests/computation/test_pivot_table_multi_idx.py
new file mode 100644
index 000000000000..fbf7cd480114
--- /dev/null
+++ b/python/pyspark/pandas/tests/computation/test_pivot_table_multi_idx.py
@@ -0,0 +1,91 @@
+#
+# 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 numpy as np
+import pandas as pd
+
+from pyspark import pandas as ps
+from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.sqlutils import SQLTestUtils
+
+
+class PivotTableMultiIdxMixin:
+ def test_pivot_table(self):
+ pdf = pd.DataFrame(
+ {
+ "a": [4, 2, 3, 4, 8, 6],
+ "b": [1, 2, 2, 4, 2, 4],
+ "e": [10, 20, 20, 40, 20, 40],
+ "c": [1, 2, 9, 4, 7, 4],
+ "d": [-1, -2, -3, -4, -5, -6],
+ },
+ index=np.random.rand(6),
+ )
+ psdf = ps.from_pandas(pdf)
+
+ columns = pd.MultiIndex.from_tuples(
+ [("x", "a"), ("x", "b"), ("y", "e"), ("z", "c"), ("w", "d")]
+ )
+ pdf.columns = columns
+ psdf.columns = columns
+
+ self.assert_eq(
+ psdf.pivot_table(columns=("x", "a"), values=("x",
"b")).sort_index(),
+ pdf.pivot_table(columns=[("x", "a")], values=[("x",
"b")]).sort_index(),
+ almost=True,
+ )
+
+ self.assert_eq(
+ psdf.pivot_table(
+ index=[("z", "c")], columns=("x", "a"), values=[("x", "b")]
+ ).sort_index(),
+ pdf.pivot_table(
+ index=[("z", "c")], columns=[("x", "a")], values=[("x", "b")]
+ ).sort_index(),
+ almost=True,
+ )
+
+ self.assert_eq(
+ psdf.pivot_table(
+ index=[("z", "c")], columns=("x", "a"), values=[("x", "b"),
("y", "e")]
+ ).sort_index(),
+ pdf.pivot_table(
+ index=[("z", "c")], columns=[("x", "a")], values=[("x", "b"),
("y", "e")]
+ ).sort_index(),
+ almost=True,
+ )
+
+
+class PivotTableMultiIdxTests(
+ PivotTableMultiIdxMixin,
+ ComparisonTestBase,
+ SQLTestUtils,
+):
+ pass
+
+
+if __name__ == "__main__":
+ from pyspark.pandas.tests.computation.test_pivot_table_multi_idx 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)
diff --git
a/python/pyspark/pandas/tests/computation/test_pivot_table_multi_idx_adv.py
b/python/pyspark/pandas/tests/computation/test_pivot_table_multi_idx_adv.py
new file mode 100644
index 000000000000..16a8ca2c0869
--- /dev/null
+++ b/python/pyspark/pandas/tests/computation/test_pivot_table_multi_idx_adv.py
@@ -0,0 +1,93 @@
+#
+# 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 numpy as np
+import pandas as pd
+
+from pyspark import pandas as ps
+from pyspark.testing.pandasutils import ComparisonTestBase
+from pyspark.testing.sqlutils import SQLTestUtils
+
+
+class PivotTableMultiIdxAdvMixin:
+ def test_pivot_table(self):
+ pdf = pd.DataFrame(
+ {
+ "a": [4, 2, 3, 4, 8, 6],
+ "b": [1, 2, 2, 4, 2, 4],
+ "e": [10, 20, 20, 40, 20, 40],
+ "c": [1, 2, 9, 4, 7, 4],
+ "d": [-1, -2, -3, -4, -5, -6],
+ },
+ index=np.random.rand(6),
+ )
+ psdf = ps.from_pandas(pdf)
+
+ columns = pd.MultiIndex.from_tuples(
+ [("x", "a"), ("x", "b"), ("y", "e"), ("z", "c"), ("w", "d")]
+ )
+ pdf.columns = columns
+ psdf.columns = columns
+
+ self.assert_eq(
+ psdf.pivot_table(
+ index=[("z", "c")], columns=("x", "a"), values=[("x", "b"),
("y", "e"), ("w", "d")]
+ ).sort_index(),
+ pdf.pivot_table(
+ index=[("z", "c")],
+ columns=[("x", "a")],
+ values=[("x", "b"), ("y", "e"), ("w", "d")],
+ ).sort_index(),
+ almost=True,
+ )
+
+ self.assert_eq(
+ psdf.pivot_table(
+ index=[("z", "c")],
+ columns=("x", "a"),
+ values=[("x", "b"), ("y", "e")],
+ aggfunc={("x", "b"): "mean", ("y", "e"): "sum"},
+ ).sort_index(),
+ pdf.pivot_table(
+ index=[("z", "c")],
+ columns=[("x", "a")],
+ values=[("x", "b"), ("y", "e")],
+ aggfunc={("x", "b"): "mean", ("y", "e"): "sum"},
+ ).sort_index(),
+ almost=True,
+ )
+
+
+class PivotTableMultiIdxAdvTests(
+ PivotTableMultiIdxAdvMixin,
+ ComparisonTestBase,
+ SQLTestUtils,
+):
+ pass
+
+
+if __name__ == "__main__":
+ from pyspark.pandas.tests.computation.test_pivot_table_multi_idx_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)
diff --git
a/python/pyspark/pandas/tests/connect/computation/test_parity_pivot.py
b/python/pyspark/pandas/tests/connect/computation/test_parity_pivot.py
index c8ec48eb06aa..fabdba7c7018 100644
--- a/python/pyspark/pandas/tests/connect/computation/test_parity_pivot.py
+++ b/python/pyspark/pandas/tests/connect/computation/test_parity_pivot.py
@@ -21,7 +21,11 @@ from pyspark.testing.connectutils import
ReusedConnectTestCase
from pyspark.testing.pandasutils import PandasOnSparkTestUtils
-class FrameParityPivotTests(FramePivotMixin, PandasOnSparkTestUtils,
ReusedConnectTestCase):
+class FrameParityPivotTests(
+ FramePivotMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
+):
pass
diff --git
a/python/pyspark/pandas/tests/connect/computation/test_parity_pivot.py
b/python/pyspark/pandas/tests/connect/computation/test_parity_pivot_table.py
similarity index 85%
copy from python/pyspark/pandas/tests/connect/computation/test_parity_pivot.py
copy to
python/pyspark/pandas/tests/connect/computation/test_parity_pivot_table.py
index c8ec48eb06aa..3afdd875f177 100644
--- a/python/pyspark/pandas/tests/connect/computation/test_parity_pivot.py
+++ b/python/pyspark/pandas/tests/connect/computation/test_parity_pivot_table.py
@@ -16,17 +16,21 @@
#
import unittest
-from pyspark.pandas.tests.computation.test_pivot import FramePivotMixin
+from pyspark.pandas.tests.computation.test_pivot_table import PivotTableMixin
from pyspark.testing.connectutils import ReusedConnectTestCase
from pyspark.testing.pandasutils import PandasOnSparkTestUtils
-class FrameParityPivotTests(FramePivotMixin, PandasOnSparkTestUtils,
ReusedConnectTestCase):
+class PivotTableParityTests(
+ PivotTableMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
+):
pass
if __name__ == "__main__":
- from pyspark.pandas.tests.connect.computation.test_parity_pivot import *
# noqa: F401
+ from pyspark.pandas.tests.connect.computation.test_parity_pivot_table
import * # noqa
try:
import xmlrunner # type: ignore[import]
diff --git
a/python/pyspark/pandas/tests/connect/computation/test_parity_pivot.py
b/python/pyspark/pandas/tests/connect/computation/test_parity_pivot_table_adv.py
similarity index 84%
copy from python/pyspark/pandas/tests/connect/computation/test_parity_pivot.py
copy to
python/pyspark/pandas/tests/connect/computation/test_parity_pivot_table_adv.py
index c8ec48eb06aa..2d6b7e697574 100644
--- a/python/pyspark/pandas/tests/connect/computation/test_parity_pivot.py
+++
b/python/pyspark/pandas/tests/connect/computation/test_parity_pivot_table_adv.py
@@ -16,17 +16,21 @@
#
import unittest
-from pyspark.pandas.tests.computation.test_pivot import FramePivotMixin
+from pyspark.pandas.tests.computation.test_pivot_table_adv import
PivotTableAdvMixin
from pyspark.testing.connectutils import ReusedConnectTestCase
from pyspark.testing.pandasutils import PandasOnSparkTestUtils
-class FrameParityPivotTests(FramePivotMixin, PandasOnSparkTestUtils,
ReusedConnectTestCase):
+class PivotTableAdvParityTests(
+ PivotTableAdvMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
+):
pass
if __name__ == "__main__":
- from pyspark.pandas.tests.connect.computation.test_parity_pivot import *
# noqa: F401
+ from pyspark.pandas.tests.connect.computation.test_parity_pivot_table_adv
import * # noqa
try:
import xmlrunner # type: ignore[import]
diff --git
a/python/pyspark/pandas/tests/connect/computation/test_parity_pivot.py
b/python/pyspark/pandas/tests/connect/computation/test_parity_pivot_table_multi_idx.py
similarity index 83%
copy from python/pyspark/pandas/tests/connect/computation/test_parity_pivot.py
copy to
python/pyspark/pandas/tests/connect/computation/test_parity_pivot_table_multi_idx.py
index c8ec48eb06aa..eb0f676f8bce 100644
--- a/python/pyspark/pandas/tests/connect/computation/test_parity_pivot.py
+++
b/python/pyspark/pandas/tests/connect/computation/test_parity_pivot_table_multi_idx.py
@@ -16,17 +16,21 @@
#
import unittest
-from pyspark.pandas.tests.computation.test_pivot import FramePivotMixin
+from pyspark.pandas.tests.computation.test_pivot_table_multi_idx import
PivotTableMultiIdxMixin
from pyspark.testing.connectutils import ReusedConnectTestCase
from pyspark.testing.pandasutils import PandasOnSparkTestUtils
-class FrameParityPivotTests(FramePivotMixin, PandasOnSparkTestUtils,
ReusedConnectTestCase):
+class PivotTableMultiIdxParityTests(
+ PivotTableMultiIdxMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
+):
pass
if __name__ == "__main__":
- from pyspark.pandas.tests.connect.computation.test_parity_pivot import *
# noqa: F401
+ from
pyspark.pandas.tests.connect.computation.test_parity_pivot_table_multi_idx
import * # noqa
try:
import xmlrunner # type: ignore[import]
diff --git
a/python/pyspark/pandas/tests/connect/computation/test_parity_pivot.py
b/python/pyspark/pandas/tests/connect/computation/test_parity_pivot_table_multi_idx_adv.py
similarity index 81%
copy from python/pyspark/pandas/tests/connect/computation/test_parity_pivot.py
copy to
python/pyspark/pandas/tests/connect/computation/test_parity_pivot_table_multi_idx_adv.py
index c8ec48eb06aa..361b5e8d9c27 100644
--- a/python/pyspark/pandas/tests/connect/computation/test_parity_pivot.py
+++
b/python/pyspark/pandas/tests/connect/computation/test_parity_pivot_table_multi_idx_adv.py
@@ -16,17 +16,23 @@
#
import unittest
-from pyspark.pandas.tests.computation.test_pivot import FramePivotMixin
+from pyspark.pandas.tests.computation.test_pivot_table_multi_idx_adv import (
+ PivotTableMultiIdxAdvMixin,
+)
from pyspark.testing.connectutils import ReusedConnectTestCase
from pyspark.testing.pandasutils import PandasOnSparkTestUtils
-class FrameParityPivotTests(FramePivotMixin, PandasOnSparkTestUtils,
ReusedConnectTestCase):
+class PivotTableMultiIdxAdvParityTests(
+ PivotTableMultiIdxAdvMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
+):
pass
if __name__ == "__main__":
- from pyspark.pandas.tests.connect.computation.test_parity_pivot import *
# noqa: F401
+ from
pyspark.pandas.tests.connect.computation.test_parity_pivot_table_multi_idx_adv
import * # noqa
try:
import xmlrunner # type: ignore[import]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
