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 59d147a4f48f [SPARK-46504][PS][TESTS][FOLLOWUP] Break the remaining
part of `IndexesTests` into small test files
59d147a4f48f is described below
commit 59d147a4f48ff6112c682e9797dbd982022bfc10
Author: Ruifeng Zheng <ruife...@apache.org>
AuthorDate: Thu Jan 4 14:33:42 2024 +0800
[SPARK-46504][PS][TESTS][FOLLOWUP] Break the remaining part of
`IndexesTests` into small test files
### What changes were proposed in this pull request?
Break the remaining part of `IndexesTests` into small test files
### Why are the changes needed?
testing parallelism
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
ci
### Was this patch authored or co-authored using generative AI tooling?
no
Closes #44588 from zhengruifeng/ps_test_idx_base_lastlast.
Authored-by: Ruifeng Zheng <ruife...@apache.org>
Signed-off-by: Ruifeng Zheng <ruife...@apache.org>
---
dev/sparktestsupport/modules.py | 8 +-
.../{test_parity_base.py => test_parity_basic.py} | 17 +-
...{test_parity_base.py => test_parity_getattr.py} | 17 +-
.../{test_parity_base.py => test_parity_name.py} | 17 +-
.../tests/indexes/{test_base.py => test_basic.py} | 155 +----------------
.../pyspark/pandas/tests/indexes/test_getattr.py | 79 +++++++++
python/pyspark/pandas/tests/indexes/test_name.py | 183 +++++++++++++++++++++
7 files changed, 296 insertions(+), 180 deletions(-)
diff --git a/dev/sparktestsupport/modules.py b/dev/sparktestsupport/modules.py
index a97e6afdc356..699a9d07452d 100644
--- a/dev/sparktestsupport/modules.py
+++ b/dev/sparktestsupport/modules.py
@@ -795,7 +795,9 @@ pyspark_pandas_slow = Module(
"pyspark.pandas.generic",
"pyspark.pandas.series",
# unittests
- "pyspark.pandas.tests.indexes.test_base",
+ "pyspark.pandas.tests.indexes.test_basic",
+ "pyspark.pandas.tests.indexes.test_getattr",
+ "pyspark.pandas.tests.indexes.test_name",
"pyspark.pandas.tests.indexes.test_conversion",
"pyspark.pandas.tests.indexes.test_drop",
"pyspark.pandas.tests.indexes.test_level",
@@ -1095,7 +1097,9 @@ pyspark_pandas_connect_part0 = Module(
"pyspark.pandas.tests.connect.test_parity_sql",
"pyspark.pandas.tests.connect.test_parity_typedef",
"pyspark.pandas.tests.connect.test_parity_utils",
- "pyspark.pandas.tests.connect.indexes.test_parity_base",
+ "pyspark.pandas.tests.connect.indexes.test_parity_basic",
+ "pyspark.pandas.tests.connect.indexes.test_parity_getattr",
+ "pyspark.pandas.tests.connect.indexes.test_parity_name",
"pyspark.pandas.tests.connect.indexes.test_parity_conversion",
"pyspark.pandas.tests.connect.indexes.test_parity_drop",
"pyspark.pandas.tests.connect.indexes.test_parity_level",
diff --git a/python/pyspark/pandas/tests/connect/indexes/test_parity_base.py
b/python/pyspark/pandas/tests/connect/indexes/test_parity_basic.py
similarity index 72%
copy from python/pyspark/pandas/tests/connect/indexes/test_parity_base.py
copy to python/pyspark/pandas/tests/connect/indexes/test_parity_basic.py
index 83ce92eb34b2..94651552ea8d 100644
--- a/python/pyspark/pandas/tests/connect/indexes/test_parity_base.py
+++ b/python/pyspark/pandas/tests/connect/indexes/test_parity_basic.py
@@ -16,22 +16,21 @@
#
import unittest
-from pyspark import pandas as ps
-from pyspark.pandas.tests.indexes.test_base import IndexesTestsMixin
+from pyspark.pandas.tests.indexes.test_basic import IndexBasicMixin
from pyspark.testing.connectutils import ReusedConnectTestCase
-from pyspark.testing.pandasutils import PandasOnSparkTestUtils, TestUtils
+from pyspark.testing.pandasutils import PandasOnSparkTestUtils
-class IndexesParityTests(
- IndexesTestsMixin, PandasOnSparkTestUtils, TestUtils, ReusedConnectTestCase
+class IndexBasicParityTests(
+ IndexBasicMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
):
- @property
- def psdf(self):
- return ps.from_pandas(self.pdf)
+ pass
if __name__ == "__main__":
- from pyspark.pandas.tests.connect.indexes.test_parity_base import * #
noqa: F401
+ from pyspark.pandas.tests.connect.indexes.test_parity_basic import * #
noqa: F401
try:
import xmlrunner # type: ignore[import]
diff --git a/python/pyspark/pandas/tests/connect/indexes/test_parity_base.py
b/python/pyspark/pandas/tests/connect/indexes/test_parity_getattr.py
similarity index 72%
copy from python/pyspark/pandas/tests/connect/indexes/test_parity_base.py
copy to python/pyspark/pandas/tests/connect/indexes/test_parity_getattr.py
index 83ce92eb34b2..47d893bda3be 100644
--- a/python/pyspark/pandas/tests/connect/indexes/test_parity_base.py
+++ b/python/pyspark/pandas/tests/connect/indexes/test_parity_getattr.py
@@ -16,22 +16,21 @@
#
import unittest
-from pyspark import pandas as ps
-from pyspark.pandas.tests.indexes.test_base import IndexesTestsMixin
+from pyspark.pandas.tests.indexes.test_getattr import IndexGetattrMixin
from pyspark.testing.connectutils import ReusedConnectTestCase
-from pyspark.testing.pandasutils import PandasOnSparkTestUtils, TestUtils
+from pyspark.testing.pandasutils import PandasOnSparkTestUtils
-class IndexesParityTests(
- IndexesTestsMixin, PandasOnSparkTestUtils, TestUtils, ReusedConnectTestCase
+class IndexGetattrParityTests(
+ IndexGetattrMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
):
- @property
- def psdf(self):
- return ps.from_pandas(self.pdf)
+ pass
if __name__ == "__main__":
- from pyspark.pandas.tests.connect.indexes.test_parity_base import * #
noqa: F401
+ from pyspark.pandas.tests.connect.indexes.test_parity_getattr import * #
noqa: F401
try:
import xmlrunner # type: ignore[import]
diff --git a/python/pyspark/pandas/tests/connect/indexes/test_parity_base.py
b/python/pyspark/pandas/tests/connect/indexes/test_parity_name.py
similarity index 73%
rename from python/pyspark/pandas/tests/connect/indexes/test_parity_base.py
rename to python/pyspark/pandas/tests/connect/indexes/test_parity_name.py
index 83ce92eb34b2..c4cbc8cbfbb1 100644
--- a/python/pyspark/pandas/tests/connect/indexes/test_parity_base.py
+++ b/python/pyspark/pandas/tests/connect/indexes/test_parity_name.py
@@ -16,22 +16,21 @@
#
import unittest
-from pyspark import pandas as ps
-from pyspark.pandas.tests.indexes.test_base import IndexesTestsMixin
+from pyspark.pandas.tests.indexes.test_name import IndexNameMixin
from pyspark.testing.connectutils import ReusedConnectTestCase
-from pyspark.testing.pandasutils import PandasOnSparkTestUtils, TestUtils
+from pyspark.testing.pandasutils import PandasOnSparkTestUtils
-class IndexesParityTests(
- IndexesTestsMixin, PandasOnSparkTestUtils, TestUtils, ReusedConnectTestCase
+class IndexNameParityTests(
+ IndexNameMixin,
+ PandasOnSparkTestUtils,
+ ReusedConnectTestCase,
):
- @property
- def psdf(self):
- return ps.from_pandas(self.pdf)
+ pass
if __name__ == "__main__":
- from pyspark.pandas.tests.connect.indexes.test_parity_base import * #
noqa: F401
+ from pyspark.pandas.tests.connect.indexes.test_parity_name import * #
noqa: F401
try:
import xmlrunner # type: ignore[import]
diff --git a/python/pyspark/pandas/tests/indexes/test_base.py
b/python/pyspark/pandas/tests/indexes/test_basic.py
similarity index 56%
rename from python/pyspark/pandas/tests/indexes/test_base.py
rename to python/pyspark/pandas/tests/indexes/test_basic.py
index 6671e3d93f75..a8f2c5b97c42 100644
--- a/python/pyspark/pandas/tests/indexes/test_base.py
+++ b/python/pyspark/pandas/tests/indexes/test_basic.py
@@ -22,12 +22,11 @@ import numpy as np
import pandas as pd
import pyspark.pandas as ps
-from pyspark.loose_version import LooseVersion
from pyspark.pandas.exceptions import PandasNotImplementedError
from pyspark.testing.pandasutils import PandasOnSparkTestCase, TestUtils,
SPARK_CONF_ARROW_ENABLED
-class IndexesTestsMixin:
+class IndexBasicMixin:
@property
def pdf(self):
return pd.DataFrame(
@@ -66,109 +65,6 @@ class IndexesTestsMixin:
with self.assertRaisesRegex(TypeError, "Index.name must be a hashable
type"):
ps.Index([1.0, 2.0, 3.0], name=[(1, 2, 3)])
- def test_index_getattr(self):
- psidx = self.psdf.index
- item = "databricks"
-
- expected_error_message = "'.*Index' object has no attribute
'{}'".format(item)
- with self.assertRaisesRegex(AttributeError, expected_error_message):
- psidx.__getattr__(item)
- with self.assertRaisesRegex(AttributeError, expected_error_message):
- ps.from_pandas(pd.date_range("2011-01-01", freq="D",
periods=10)).__getattr__(item)
-
- def test_multi_index_getattr(self):
- arrays = [[1, 1, 2, 2], ["red", "blue", "red", "blue"]]
- idx = pd.MultiIndex.from_arrays(arrays, names=("number", "color"))
- pdf = pd.DataFrame(np.random.randn(4, 5), idx)
- psdf = ps.from_pandas(pdf)
- psidx = psdf.index
- item = "databricks"
-
- expected_error_message = "'MultiIndex' object has no attribute
'{}'".format(item)
- with self.assertRaisesRegex(AttributeError, expected_error_message):
- psidx.__getattr__(item)
-
- def test_index_names(self):
- psdf = self.psdf
- self.assertIsNone(psdf.index.name)
-
- idx = pd.Index([0, 1, 2, 3, 4, 5, 6, 7, 8, 9], name="x")
- pdf = pd.DataFrame(np.random.randn(10, 5), index=idx,
columns=list("abcde"))
- psdf = ps.from_pandas(pdf)
-
- pser = pdf.a
- psser = psdf.a
-
- self.assertEqual(psdf.index.name, pdf.index.name)
- self.assertEqual(psdf.index.names, pdf.index.names)
-
- pidx = pdf.index
- psidx = psdf.index
- pidx.name = "renamed"
- psidx.name = "renamed"
- self.assertEqual(psidx.name, pidx.name)
- self.assertEqual(psidx.names, pidx.names)
- self.assert_eq(psidx, pidx)
- self.assertEqual(psdf.index.name, pdf.index.name)
- self.assertEqual(psdf.index.names, pdf.index.names)
- self.assertEqual(psser.index.names, pser.index.names)
-
- pidx.name = None
- psidx.name = None
- self.assertEqual(psidx.name, pidx.name)
- self.assertEqual(psidx.names, pidx.names)
- self.assert_eq(psidx, pidx)
- self.assertEqual(psdf.index.name, pdf.index.name)
- self.assertEqual(psdf.index.names, pdf.index.names)
- self.assertEqual(psser.index.names, pser.index.names)
-
- with self.assertRaisesRegex(ValueError, "Names must be a list-like"):
- psidx.names = "hi"
-
- expected_error_message = "Length of new names must be {}, got
{}".format(
- psdf._internal.index_level, len(["0", "1"])
- )
- with self.assertRaisesRegex(ValueError, expected_error_message):
- psidx.names = ["0", "1"]
-
- expected_error_message = "Index.name must be a hashable type"
- with self.assertRaisesRegex(TypeError, expected_error_message):
- ps.Index([1, 2, 3], name=["0", "1"])
- with self.assertRaisesRegex(TypeError, expected_error_message):
- psidx.name = ["renamed"]
- with self.assertRaisesRegex(TypeError, expected_error_message):
- psidx.name = ["0", "1"]
- # Specifying `names` when creating Index is no longer supported from
pandas 2.0.0.
- if LooseVersion(pd.__version__) >= LooseVersion("2.0.0"):
- pass
- else:
- with self.assertRaisesRegex(TypeError, expected_error_message):
- ps.Index([(1, 2), (3, 4)], names=["a", ["b"]])
-
- def test_multi_index_names(self):
- arrays = [[1, 1, 2, 2], ["red", "blue", "red", "blue"]]
- idx = pd.MultiIndex.from_arrays(arrays, names=("number", "color"))
- pdf = pd.DataFrame(np.random.randn(4, 5), idx)
- psdf = ps.from_pandas(pdf)
-
- self.assertEqual(psdf.index.names, pdf.index.names)
-
- pidx = pdf.index
- psidx = psdf.index
- pidx.names = ["renamed_number", "renamed_color"]
- psidx.names = ["renamed_number", "renamed_color"]
- self.assertEqual(psidx.names, pidx.names)
-
- pidx.names = ["renamed_number", None]
- psidx.names = ["renamed_number", None]
- self.assertEqual(psidx.names, pidx.names)
- self.assert_eq(psidx, pidx)
-
- with self.assertRaises(PandasNotImplementedError):
- psidx.name
- with self.assertRaises(PandasNotImplementedError):
- psidx.name = "renamed"
-
def test_multi_index_copy(self):
arrays = [[1, 1, 2, 2], ["red", "blue", "red", "blue"]]
idx = pd.MultiIndex.from_arrays(arrays, names=("number", "color"))
@@ -177,49 +73,6 @@ class IndexesTestsMixin:
self.assert_eq(psdf.index.copy(), pdf.index.copy())
- def test_multiindex_set_names(self):
- pidx = pd.MultiIndex.from_tuples([("a", "x", 1), ("b", "y", 2), ("c",
"z", 3)])
- psidx = ps.from_pandas(pidx)
-
- pidx = pidx.set_names(["set", "new", "names"])
- psidx = psidx.set_names(["set", "new", "names"])
- self.assert_eq(pidx, psidx)
-
- pidx.set_names(["set", "new", "names"], inplace=True)
- psidx.set_names(["set", "new", "names"], inplace=True)
- self.assert_eq(pidx, psidx)
-
- pidx = pidx.set_names("first", level=0)
- psidx = psidx.set_names("first", level=0)
- self.assert_eq(pidx, psidx)
-
- pidx = pidx.set_names("second", level=1)
- psidx = psidx.set_names("second", level=1)
- self.assert_eq(pidx, psidx)
-
- pidx = pidx.set_names("third", level=2)
- psidx = psidx.set_names("third", level=2)
- self.assert_eq(pidx, psidx)
-
- pidx.set_names("first", level=0, inplace=True)
- psidx.set_names("first", level=0, inplace=True)
- self.assert_eq(pidx, psidx)
-
- pidx.set_names("second", level=1, inplace=True)
- psidx.set_names("second", level=1, inplace=True)
- self.assert_eq(pidx, psidx)
-
- pidx.set_names("third", level=2, inplace=True)
- psidx.set_names("third", level=2, inplace=True)
- self.assert_eq(pidx, psidx)
-
- def test_multiindex_tuple_column_name(self):
- column_labels = pd.MultiIndex.from_tuples([("a", "x"), ("a", "y"),
("b", "z")])
- pdf = pd.DataFrame([[1, 2, 3], [4, 5, 6], [7, 8, 9]],
columns=column_labels)
- pdf.set_index(("a", "x"), append=True, inplace=True)
- psdf = ps.from_pandas(pdf)
- self.assert_eq(pdf, psdf)
-
def test_holds_integer(self):
pidx = pd.Index([1, 2, 3, 4])
psidx = ps.from_pandas(pidx)
@@ -347,8 +200,8 @@ class IndexesTestsMixin:
self.assertRaises(PandasNotImplementedError, lambda:
psmidx.factorize())
-class IndexesTests(
- IndexesTestsMixin,
+class IndexBasicTests(
+ IndexBasicMixin,
PandasOnSparkTestCase,
TestUtils,
):
@@ -356,7 +209,7 @@ class IndexesTests(
if __name__ == "__main__":
- from pyspark.pandas.tests.indexes.test_base import * # noqa: F401
+ from pyspark.pandas.tests.indexes.test_basic import * # noqa: F401
try:
import xmlrunner
diff --git a/python/pyspark/pandas/tests/indexes/test_getattr.py
b/python/pyspark/pandas/tests/indexes/test_getattr.py
new file mode 100644
index 000000000000..8632aa5dfeba
--- /dev/null
+++ b/python/pyspark/pandas/tests/indexes/test_getattr.py
@@ -0,0 +1,79 @@
+#
+# 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 PandasOnSparkTestCase
+from pyspark.testing.sqlutils import SQLTestUtils
+
+
+class IndexGetattrMixin:
+ @property
+ def pdf(self):
+ return pd.DataFrame(
+ {"a": [1, 2, 3, 4, 5, 6, 7, 8, 9], "b": [4, 5, 6, 3, 2, 1, 0, 0,
0]},
+ index=[0, 1, 3, 5, 6, 8, 9, 9, 9],
+ )
+
+ @property
+ def psdf(self):
+ return ps.from_pandas(self.pdf)
+
+ def test_index_getattr(self):
+ psidx = self.psdf.index
+ item = "databricks"
+
+ expected_error_message = "'.*Index' object has no attribute
'{}'".format(item)
+ with self.assertRaisesRegex(AttributeError, expected_error_message):
+ psidx.__getattr__(item)
+ with self.assertRaisesRegex(AttributeError, expected_error_message):
+ ps.from_pandas(pd.date_range("2011-01-01", freq="D",
periods=10)).__getattr__(item)
+
+ def test_multi_index_getattr(self):
+ arrays = [[1, 1, 2, 2], ["red", "blue", "red", "blue"]]
+ idx = pd.MultiIndex.from_arrays(arrays, names=("number", "color"))
+ pdf = pd.DataFrame(np.random.randn(4, 5), idx)
+ psdf = ps.from_pandas(pdf)
+ psidx = psdf.index
+ item = "databricks"
+
+ expected_error_message = "'MultiIndex' object has no attribute
'{}'".format(item)
+ with self.assertRaisesRegex(AttributeError, expected_error_message):
+ psidx.__getattr__(item)
+
+
+class IndexGetattrTests(
+ IndexGetattrMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
+ pass
+
+
+if __name__ == "__main__":
+ from pyspark.pandas.tests.indexes.test_getattr 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/indexes/test_name.py
b/python/pyspark/pandas/tests/indexes/test_name.py
new file mode 100644
index 000000000000..cacf3efcb38b
--- /dev/null
+++ b/python/pyspark/pandas/tests/indexes/test_name.py
@@ -0,0 +1,183 @@
+#
+# 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.loose_version import LooseVersion
+from pyspark.pandas.exceptions import PandasNotImplementedError
+from pyspark.testing.pandasutils import PandasOnSparkTestCase
+from pyspark.testing.sqlutils import SQLTestUtils
+
+
+class IndexNameMixin:
+ @property
+ def pdf(self):
+ return pd.DataFrame(
+ {"a": [1, 2, 3, 4, 5, 6, 7, 8, 9], "b": [4, 5, 6, 3, 2, 1, 0, 0,
0]},
+ index=[0, 1, 3, 5, 6, 8, 9, 9, 9],
+ )
+
+ @property
+ def psdf(self):
+ return ps.from_pandas(self.pdf)
+
+ def test_index_names(self):
+ psdf = self.psdf
+ self.assertIsNone(psdf.index.name)
+
+ idx = pd.Index([0, 1, 2, 3, 4, 5, 6, 7, 8, 9], name="x")
+ pdf = pd.DataFrame(np.random.randn(10, 5), index=idx,
columns=list("abcde"))
+ psdf = ps.from_pandas(pdf)
+
+ pser = pdf.a
+ psser = psdf.a
+
+ self.assertEqual(psdf.index.name, pdf.index.name)
+ self.assertEqual(psdf.index.names, pdf.index.names)
+
+ pidx = pdf.index
+ psidx = psdf.index
+ pidx.name = "renamed"
+ psidx.name = "renamed"
+ self.assertEqual(psidx.name, pidx.name)
+ self.assertEqual(psidx.names, pidx.names)
+ self.assert_eq(psidx, pidx)
+ self.assertEqual(psdf.index.name, pdf.index.name)
+ self.assertEqual(psdf.index.names, pdf.index.names)
+ self.assertEqual(psser.index.names, pser.index.names)
+
+ pidx.name = None
+ psidx.name = None
+ self.assertEqual(psidx.name, pidx.name)
+ self.assertEqual(psidx.names, pidx.names)
+ self.assert_eq(psidx, pidx)
+ self.assertEqual(psdf.index.name, pdf.index.name)
+ self.assertEqual(psdf.index.names, pdf.index.names)
+ self.assertEqual(psser.index.names, pser.index.names)
+
+ with self.assertRaisesRegex(ValueError, "Names must be a list-like"):
+ psidx.names = "hi"
+
+ expected_error_message = "Length of new names must be {}, got
{}".format(
+ psdf._internal.index_level, len(["0", "1"])
+ )
+ with self.assertRaisesRegex(ValueError, expected_error_message):
+ psidx.names = ["0", "1"]
+
+ expected_error_message = "Index.name must be a hashable type"
+ with self.assertRaisesRegex(TypeError, expected_error_message):
+ ps.Index([1, 2, 3], name=["0", "1"])
+ with self.assertRaisesRegex(TypeError, expected_error_message):
+ psidx.name = ["renamed"]
+ with self.assertRaisesRegex(TypeError, expected_error_message):
+ psidx.name = ["0", "1"]
+ # Specifying `names` when creating Index is no longer supported from
pandas 2.0.0.
+ if LooseVersion(pd.__version__) >= LooseVersion("2.0.0"):
+ pass
+ else:
+ with self.assertRaisesRegex(TypeError, expected_error_message):
+ ps.Index([(1, 2), (3, 4)], names=["a", ["b"]])
+
+ def test_multi_index_names(self):
+ arrays = [[1, 1, 2, 2], ["red", "blue", "red", "blue"]]
+ idx = pd.MultiIndex.from_arrays(arrays, names=("number", "color"))
+ pdf = pd.DataFrame(np.random.randn(4, 5), idx)
+ psdf = ps.from_pandas(pdf)
+
+ self.assertEqual(psdf.index.names, pdf.index.names)
+
+ pidx = pdf.index
+ psidx = psdf.index
+ pidx.names = ["renamed_number", "renamed_color"]
+ psidx.names = ["renamed_number", "renamed_color"]
+ self.assertEqual(psidx.names, pidx.names)
+
+ pidx.names = ["renamed_number", None]
+ psidx.names = ["renamed_number", None]
+ self.assertEqual(psidx.names, pidx.names)
+ self.assert_eq(psidx, pidx)
+
+ with self.assertRaises(PandasNotImplementedError):
+ psidx.name
+ with self.assertRaises(PandasNotImplementedError):
+ psidx.name = "renamed"
+
+ def test_multiindex_set_names(self):
+ pidx = pd.MultiIndex.from_tuples([("a", "x", 1), ("b", "y", 2), ("c",
"z", 3)])
+ psidx = ps.from_pandas(pidx)
+
+ pidx = pidx.set_names(["set", "new", "names"])
+ psidx = psidx.set_names(["set", "new", "names"])
+ self.assert_eq(pidx, psidx)
+
+ pidx.set_names(["set", "new", "names"], inplace=True)
+ psidx.set_names(["set", "new", "names"], inplace=True)
+ self.assert_eq(pidx, psidx)
+
+ pidx = pidx.set_names("first", level=0)
+ psidx = psidx.set_names("first", level=0)
+ self.assert_eq(pidx, psidx)
+
+ pidx = pidx.set_names("second", level=1)
+ psidx = psidx.set_names("second", level=1)
+ self.assert_eq(pidx, psidx)
+
+ pidx = pidx.set_names("third", level=2)
+ psidx = psidx.set_names("third", level=2)
+ self.assert_eq(pidx, psidx)
+
+ pidx.set_names("first", level=0, inplace=True)
+ psidx.set_names("first", level=0, inplace=True)
+ self.assert_eq(pidx, psidx)
+
+ pidx.set_names("second", level=1, inplace=True)
+ psidx.set_names("second", level=1, inplace=True)
+ self.assert_eq(pidx, psidx)
+
+ pidx.set_names("third", level=2, inplace=True)
+ psidx.set_names("third", level=2, inplace=True)
+ self.assert_eq(pidx, psidx)
+
+ def test_multiindex_tuple_column_name(self):
+ column_labels = pd.MultiIndex.from_tuples([("a", "x"), ("a", "y"),
("b", "z")])
+ pdf = pd.DataFrame([[1, 2, 3], [4, 5, 6], [7, 8, 9]],
columns=column_labels)
+ pdf.set_index(("a", "x"), append=True, inplace=True)
+ psdf = ps.from_pandas(pdf)
+ self.assert_eq(pdf, psdf)
+
+
+class IndexNameTests(
+ IndexNameMixin,
+ PandasOnSparkTestCase,
+ SQLTestUtils,
+):
+ pass
+
+
+if __name__ == "__main__":
+ from pyspark.pandas.tests.indexes.test_name 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)
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org
For additional commands, e-mail: commits-h...@spark.apache.org
