Skip to content
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

Jump to bottom

[SPARK-39881][PYTHON] Fix erroneous check for black and reenable black validation. #37305

Closed
wants to merge 5 commits into from
Closed

[SPARK-39881][PYTHON] Fix erroneous check for black and reenable black validation. #37305

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
d29d43a
fixing linter issues
grundprinzip Jul 26, 2022
a62ac64
fixing GH workflow installation
grundprinzip Jul 26, 2022
a626a13
Revert unnecessary change.
grundprinzip Jul 27, 2022
8691d39
Updating dev depenencies.
grundprinzip Jul 29, 2022
5a89f6d
Simplifying error messages.
grundprinzip Jul 29, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
2 changes: 1 addition & 1 deletion .github/workflows/build_and_test.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -549,7 +549,7 @@ jobs:
# See also https://github.com/sphinx-doc/sphinx/issues/7551.
# Jinja2 3.0.0+ causes error when building with Sphinx.
# See also https://issues.apache.org/jira/browse/SPARK-35375.
python3.9 -m pip install 'flake8==3.9.0' pydata_sphinx_theme 'mypy==0.920' 'pytest-mypy-plugins==1.9.3' numpydoc 'jinja2<3.0.0' 'black==21.12b0'
python3.9 -m pip install 'flake8==3.9.0' pydata_sphinx_theme 'mypy==0.920' 'pytest-mypy-plugins==1.9.3' numpydoc 'jinja2<3.0.0' 'black==22.6.0'
python3.9 -m pip install 'pandas-stubs==1.2.0.53'
- name: Install R linter dependencies and SparkR
run: |
Expand Down
2 changes: 1 addition & 1 deletion dev/lint-python
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -210,7 +210,7 @@ function black_test {
local BLACK_STATUS=

# Skip check if black is not installed.
$BLACK_BUILD 2> /dev/null
$PYTHON_EXECUTABLE -c 'import black' &> /dev/null
if [ $? -ne 0 ]; then
echo "The $BLACK_BUILD command was not found. Skipping black checks for now."
grundprinzip marked this conversation as resolved.
Show resolved Hide resolved
echo
Expand Down
2 changes: 1 addition & 1 deletion dev/pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@ testpaths = [
[tool.black]
# When changing the version, we have to update
# GitHub workflow version and dev/reformat-python
required-version = "21.12b0"
required-version = "22.6.0"
grundprinzip marked this conversation as resolved.
Show resolved Hide resolved
line-length = 100
target-version = ['py37']
include = '\.pyi?$'
Expand Down
7 changes: 4 additions & 3 deletions dev/reformat-python
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,13 +16,14 @@
# limitations under the License.

# The current directory of the script.
PYTHON_EXECUTABLE="${PYTHON_EXECUTABLE:-python3}"
DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
FWDIR="$( cd "$DIR"/.. && pwd )"
cd "$FWDIR"

BLACK_BUILD="python -m black"
BLACK_VERSION="21.12b0"
$BLACK_BUILD 2> /dev/null
BLACK_BUILD="${PYTHON_EXECUTABLE} -m black"
BLACK_VERSION="22.6.0"
$PYTHON_EXECUTABLE -c 'import black' 2> /dev/null
grundprinzip marked this conversation as resolved.
Show resolved Hide resolved
if [ $? -ne 0 ]; then
echo "The '$BLACK_BUILD' command was not found. Please install Black, for example, via 'pip install black==$BLACK_VERSION'."
exit 1
Expand Down
5 changes: 1 addition & 4 deletions python/pyspark/context.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -309,10 +309,7 @@ def _do_init(
if sys.version_info[:2] < (3, 8):
with warnings.catch_warnings():
warnings.simplefilter("once")
warnings.warn(
"Python 3.7 support is deprecated in Spark 3.4.",
FutureWarning
)
warnings.warn("Python 3.7 support is deprecated in Spark 3.4.", FutureWarning)

# Broadcast's __reduce__ method stores Broadcast instances here.
# This allows other code to determine which Broadcast instances have
Expand Down
6 changes: 3 additions & 3 deletions python/pyspark/ml/feature.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -968,7 +968,7 @@ class _CountVectorizerParams(JavaParams, HasInputCol, HasOutputCol):

def __init__(self, *args: Any):
super(_CountVectorizerParams, self).__init__(*args)
self._setDefault(minTF=1.0, minDF=1.0, maxDF=2 ** 63 - 1, vocabSize=1 << 18, binary=False)
self._setDefault(minTF=1.0, minDF=1.0, maxDF=2**63 - 1, vocabSize=1 << 18, binary=False)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

FWIW, I think this is false positive from Black presumably (per https://peps.python.org/pep-0008/#other-recommendations). I believe we use one space around these operators.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Doesn't this fall into this rule?

If operators with different priorities are used, consider adding whitespace around the operators with the lowest priority(ies). Use your own judgment; however, never use more than one space, and always have the same amount of whitespace on both sides of a binary operator:

2**63 - 1

The - has a lower priority compared to the power operator?

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is this style change because we are upgrading black?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Apparently, yes. I just tested. In the old version it would not touch this change, the new version does. Playing with it actually shows that the behaviour is specifc to the power operator. I'll check if I find some more details in the black releases.

Copy link
Member

@ueshin ueshin Jul 27, 2022 •
edited

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Found the doc that mentions about this:

Almost all operators will be surrounded by single spaces, the only exceptions are unary
operators (+, -, and ~), and power operators when both operands are simple. For
powers, an operand is considered simple if it's only a NAME, numeric CONSTANT, or
attribute access (chained attribute access is allowed), with or without a preceding
unary operator.

And the commit.

The style change is from 22.1.0.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@ueshin Please see - psf/black#538

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks like ** is not covered by PEP8, and the main reason of balck change is consider about readable, so I personaly think black choice is right.


@since("1.6.0")
def getMinTF(self) -> float:
Expand Down Expand Up @@ -1077,7 +1077,7 @@ def __init__(
*,
minTF: float = 1.0,
minDF: float = 1.0,
maxDF: float = 2 ** 63 - 1,
maxDF: float = 2**63 - 1,
vocabSize: int = 1 << 18,
binary: bool = False,
inputCol: Optional[str] = None,
Expand All @@ -1099,7 +1099,7 @@ def setParams(
*,
minTF: float = 1.0,
minDF: float = 1.0,
maxDF: float = 2 ** 63 - 1,
maxDF: float = 2**63 - 1,
vocabSize: int = 1 << 18,
binary: bool = False,
inputCol: Optional[str] = None,
Expand Down
6 changes: 3 additions & 3 deletions python/pyspark/pandas/data_type_ops/boolean_ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -153,11 +153,11 @@ def pow(self, left: IndexOpsLike, right: Any) -> SeriesOrIndex:
)
if isinstance(right, numbers.Number):
left = transform_boolean_operand_to_numeric(left, spark_type=as_spark_type(type(right)))
return left ** right
return left**right
else:
assert isinstance(right, IndexOpsMixin)
left = transform_boolean_operand_to_numeric(left, spark_type=right.spark.data_type)
return left ** right
return left**right

def radd(self, left: IndexOpsLike, right: Any) -> SeriesOrIndex:
_sanitize_list_like(right)
Expand Down Expand Up @@ -217,7 +217,7 @@ def rpow(self, left: IndexOpsLike, right: Any) -> SeriesOrIndex:
_sanitize_list_like(right)
if isinstance(right, numbers.Number) and not isinstance(right, bool):
left = transform_boolean_operand_to_numeric(left, spark_type=as_spark_type(type(right)))
return right ** left
return right**left
else:
raise TypeError(
"Exponentiation can not be applied to %s and the given type." % self.pretty_name
Expand Down
4 changes: 2 additions & 2 deletions python/pyspark/pandas/frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -955,14 +955,14 @@ def rmod(self, other: Any) -> "DataFrame":
)

def pow(self, other: Any) -> "DataFrame":
return self ** other
return self**other

pow.__doc__ = _flex_doc_FRAME.format(
desc="Exponential power of series", op_name="**", equiv="dataframe ** other", reverse="rpow"
)

def rpow(self, other: Any) -> "DataFrame":
return other ** self
return other**self

rpow.__doc__ = _flex_doc_FRAME.format(
desc="Exponential power", op_name="**", equiv="other ** dataframe", reverse="pow"
Expand Down
4 changes: 2 additions & 2 deletions python/pyspark/pandas/series.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -629,7 +629,7 @@ def rmod(self, other: Any) -> "Series":
)

def pow(self, other: Any) -> "Series":
return self ** other
return self**other

pow.__doc__ = _flex_doc_SERIES.format(
desc="Exponential power of series",
Expand All @@ -640,7 +640,7 @@ def pow(self, other: Any) -> "Series":
)

def rpow(self, other: Any) -> "Series":
return other ** self
return other**self

rpow.__doc__ = _flex_doc_SERIES.format(
desc="Reverse Exponential power",
Expand Down
6 changes: 3 additions & 3 deletions python/pyspark/pandas/tests/data_type_ops/test_binary_ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -97,10 +97,10 @@ def test_mod(self):

def test_pow(self):
self.assertRaises(TypeError, lambda: self.psser ** "x")
self.assertRaises(TypeError, lambda: self.psser ** 1)
self.assertRaises(TypeError, lambda: self.psser**1)

for psser in self.pssers:
self.assertRaises(TypeError, lambda: self.psser ** psser)
self.assertRaises(TypeError, lambda: self.psser**psser)

def test_radd(self):
self.assert_eq(b"1" + self.psser, b"1" + self.pser)
Expand Down Expand Up @@ -128,7 +128,7 @@ def test_rmod(self):

def test_rpow(self):
self.assertRaises(TypeError, lambda: "x" ** self.psser)
self.assertRaises(TypeError, lambda: 1 ** self.psser)
self.assertRaises(TypeError, lambda: 1**self.psser)

def test_and(self):
self.assertRaises(TypeError, lambda: self.psser & True)
Expand Down
36 changes: 18 additions & 18 deletions python/pyspark/pandas/tests/data_type_ops/test_boolean_ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -155,11 +155,11 @@ def test_pow(self):

b_pser, b_psser = pdf["bool"], psdf["bool"]
# float is always returned in pandas-on-Spark
self.assert_eq((b_pser ** 1).astype("float"), b_psser ** 1)
self.assert_eq(b_pser ** 0.1, b_psser ** 0.1)
self.assert_eq((b_pser**1).astype("float"), b_psser**1)
self.assert_eq(b_pser**0.1, b_psser**0.1)
self.assert_eq(b_pser ** b_pser.astype(float), b_psser ** b_psser.astype(float))
self.assertRaises(TypeError, lambda: b_psser ** b_psser)
self.assertRaises(TypeError, lambda: b_psser ** True)
self.assertRaises(TypeError, lambda: b_psser**b_psser)
self.assertRaises(TypeError, lambda: b_psser**True)

self.assert_eq(b_pser % pdf["float"], b_psser % psdf["float"])
for col in self.non_numeric_df_cols:
Expand Down Expand Up @@ -226,10 +226,10 @@ def test_rpow(self):

b_pser, b_psser = pdf["bool"], psdf["bool"]
# float is returned always in pandas-on-Spark
self.assert_eq((1 ** b_pser).astype(float), 1 ** b_psser)
self.assert_eq(0.1 ** b_pser, 0.1 ** b_psser)
self.assert_eq((1**b_pser).astype(float), 1**b_psser)
self.assert_eq(0.1**b_pser, 0.1**b_psser)
self.assertRaises(TypeError, lambda: "x" ** b_psser)
self.assertRaises(TypeError, lambda: True ** b_psser)
self.assertRaises(TypeError, lambda: True**b_psser)
self.assertRaises(TypeError, lambda: datetime.date(1994, 1, 1) ** b_psser)
self.assertRaises(TypeError, lambda: datetime.datetime(1994, 1, 1) ** b_psser)
Comment on lines 233 to 234
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'm not sure why Black doesn't reformat this, too...

Shouldn't it be reformatted like:

-         self.assertRaises(TypeError, lambda: datetime.date(1994, 1, 1) ** b_psser)
-         self.assertRaises(TypeError, lambda: datetime.datetime(1994, 1, 1) ** b_psser)
+         self.assertRaises(TypeError, lambda: datetime.date(1994, 1, 1)**b_psser)
+         self.assertRaises(TypeError, lambda: datetime.datetime(1994, 1, 1)**b_psser)

???

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'm no black expert, but from the discussion I had with @HyukjinKwon above, it looks like it's a operator precedence behavior thing.

If operators with different priorities are used, consider adding whitespace around the operators with the lowest priority(ies). Use your own judgment; however, never use more than one space, and always have the same amount of whitespace on both sides of a binary operator:

in

self.assertRaises(TypeError, lambda: datetime.date(1994, 1, 1) ** b_psser)

The binary operator ** is not paired with a lower priority other operator.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yeah, I understand about the priority but just wonder why Black did:

-         self.assertRaises(TypeError, lambda: True ** b_psser)
+         self.assertRaises(TypeError, lambda: True**b_psser)

but didn't

-         self.assertRaises(TypeError, lambda: datetime.date(1994, 1, 1) ** b_psser)
-         self.assertRaises(TypeError, lambda: datetime.datetime(1994, 1, 1) ** b_psser)
+         self.assertRaises(TypeError, lambda: datetime.date(1994, 1, 1)**b_psser)
+         self.assertRaises(TypeError, lambda: datetime.datetime(1994, 1, 1)**b_psser)

It seems like just inconsistence behavior from Black, so maybe we can just keep is as is for now.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The reason is explained here #37305 (comment) - in short the operators are not simple ( True vs datetime.datetime(1994, 1, 1))


Expand Down Expand Up @@ -547,19 +547,19 @@ def test_pow(self):
pser, psser = pdf["this"], psdf["this"]
# float is always returned in pandas-on-Spark
if extension_float_dtypes_available:
self.check_extension((pser ** 1).astype("Float64"), psser ** 1)
self.check_extension((pser ** 0.1).astype("Float64"), psser ** 0.1)
self.check_extension((pser**1).astype("Float64"), psser**1)
self.check_extension((pser**0.1).astype("Float64"), psser**0.1)
self.check_extension(
(pser ** pser.astype(float)).astype("Float64"), psser ** psser.astype(float)
)
else:
self.assert_eq((pser ** 1).astype("float"), psser ** 1)
self.assert_eq((pser ** 0.1).astype("float"), psser ** 0.1)
self.assert_eq((pser**1).astype("float"), psser**1)
self.assert_eq((pser**0.1).astype("float"), psser**0.1)
self.assert_eq(
(pser ** pser.astype(float)).astype("float"), psser ** psser.astype(float)
)
self.assertRaises(TypeError, lambda: psser ** psser)
self.assertRaises(TypeError, lambda: psser ** True)
self.assertRaises(TypeError, lambda: psser**psser)
self.assertRaises(TypeError, lambda: psser**True)

self.assert_eq(
pser ** pdf["float"],
Expand Down Expand Up @@ -648,13 +648,13 @@ def test_rfloordiv(self):
def test_rpow(self):
pser, psser = self.boolean_pdf["this"], self.boolean_psdf["this"]
if extension_float_dtypes_available:
self.check_extension(pd.Series([1, 1, 1], dtype="Float64", name=psser.name), 1 ** psser)
self.check_extension((0.1 ** pser).astype("Float64"), 0.1 ** psser)
self.check_extension(pd.Series([1, 1, 1], dtype="Float64", name=psser.name), 1**psser)
self.check_extension((0.1**pser).astype("Float64"), 0.1**psser)
else:
self.assert_eq(pd.Series([1, 1, 1], dtype="float", name=psser.name), 1 ** psser)
self.assert_eq((0.1 ** pser).astype("float"), 0.1 ** psser)
self.assert_eq(pd.Series([1, 1, 1], dtype="float", name=psser.name), 1**psser)
self.assert_eq((0.1**pser).astype("float"), 0.1**psser)
self.assertRaises(TypeError, lambda: "x" ** psser)
self.assertRaises(TypeError, lambda: True ** psser)
self.assertRaises(TypeError, lambda: True**psser)
self.assertRaises(TypeError, lambda: datetime.date(1994, 1, 1) ** psser)
self.assertRaises(TypeError, lambda: datetime.datetime(1994, 1, 1) ** psser)

Expand Down
6 changes: 3 additions & 3 deletions python/pyspark/pandas/tests/data_type_ops/test_categorical_ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -111,11 +111,11 @@ def test_mod(self):

def test_pow(self):
self.assertRaises(TypeError, lambda: self.psser ** "x")
self.assertRaises(TypeError, lambda: self.psser ** 1)
self.assertRaises(TypeError, lambda: self.psser**1)

with option_context("compute.ops_on_diff_frames", True):
for psser in self.pssers:
self.assertRaises(TypeError, lambda: self.psser ** psser)
self.assertRaises(TypeError, lambda: self.psser**psser)

def test_radd(self):
self.assertRaises(TypeError, lambda: "x" + self.psser)
Expand All @@ -142,7 +142,7 @@ def test_rmod(self):

def test_rpow(self):
self.assertRaises(TypeError, lambda: "x" ** self.psser)
self.assertRaises(TypeError, lambda: 1 ** self.psser)
self.assertRaises(TypeError, lambda: 1**self.psser)

def test_and(self):
self.assertRaises(TypeError, lambda: self.psser & True)
Expand Down
4 changes: 2 additions & 2 deletions python/pyspark/pandas/tests/data_type_ops/test_complex_ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -183,7 +183,7 @@ def test_mod(self):

def test_pow(self):
self.assertRaises(TypeError, lambda: self.psser ** "x")
self.assertRaises(TypeError, lambda: self.psser ** 1)
self.assertRaises(TypeError, lambda: self.psser**1)

psdf = self.array_psdf
for col in self.array_df_cols:
Expand Down Expand Up @@ -215,7 +215,7 @@ def test_rmod(self):

def test_rpow(self):
self.assertRaises(TypeError, lambda: "x" ** self.psser)
self.assertRaises(TypeError, lambda: 1 ** self.psser)
self.assertRaises(TypeError, lambda: 1**self.psser)

def test_and(self):
self.assertRaises(TypeError, lambda: self.psser & True)
Expand Down
10 changes: 5 additions & 5 deletions python/pyspark/pandas/tests/data_type_ops/test_date_ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -111,11 +111,11 @@ def test_mod(self):

def test_pow(self):
self.assertRaises(TypeError, lambda: self.psser ** "x")
self.assertRaises(TypeError, lambda: self.psser ** 1)
self.assertRaises(TypeError, lambda: self.psser ** self.some_date)
self.assertRaises(TypeError, lambda: self.psser**1)
self.assertRaises(TypeError, lambda: self.psser**self.some_date)

for psser in self.pssers:
self.assertRaises(TypeError, lambda: self.psser ** psser)
self.assertRaises(TypeError, lambda: self.psser**psser)

def test_radd(self):
self.assertRaises(TypeError, lambda: "x" + self.psser)
Expand Down Expand Up @@ -151,8 +151,8 @@ def test_rmod(self):

def test_rpow(self):
self.assertRaises(TypeError, lambda: "x" ** self.psser)
self.assertRaises(TypeError, lambda: 1 ** self.psser)
self.assertRaises(TypeError, lambda: self.some_date ** self.psser)
self.assertRaises(TypeError, lambda: 1**self.psser)
self.assertRaises(TypeError, lambda: self.some_date**self.psser)

def test_and(self):
self.assertRaises(TypeError, lambda: self.psser & True)
Expand Down
10 changes: 5 additions & 5 deletions python/pyspark/pandas/tests/data_type_ops/test_datetime_ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -115,11 +115,11 @@ def test_mod(self):

def test_pow(self):
self.assertRaises(TypeError, lambda: self.psser ** "x")
self.assertRaises(TypeError, lambda: self.psser ** 1)
self.assertRaises(TypeError, lambda: self.psser ** self.some_datetime)
self.assertRaises(TypeError, lambda: self.psser**1)
self.assertRaises(TypeError, lambda: self.psser**self.some_datetime)

for psser in self.pssers:
self.assertRaises(TypeError, lambda: self.psser ** psser)
self.assertRaises(TypeError, lambda: self.psser**psser)

def test_radd(self):
self.assertRaises(TypeError, lambda: "x" + self.psser)
Expand Down Expand Up @@ -155,8 +155,8 @@ def test_rmod(self):

def test_rpow(self):
self.assertRaises(TypeError, lambda: "x" ** self.psser)
self.assertRaises(TypeError, lambda: 1 ** self.psser)
self.assertRaises(TypeError, lambda: self.some_datetime ** self.psser)
self.assertRaises(TypeError, lambda: 1**self.psser)
self.assertRaises(TypeError, lambda: self.some_datetime**self.psser)

def test_and(self):
self.assertRaises(TypeError, lambda: self.psser & True)
Expand Down
6 changes: 3 additions & 3 deletions python/pyspark/pandas/tests/data_type_ops/test_null_ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,10 +75,10 @@ def test_mod(self):

def test_pow(self):
self.assertRaises(TypeError, lambda: self.psser ** "x")
self.assertRaises(TypeError, lambda: self.psser ** 1)
self.assertRaises(TypeError, lambda: self.psser**1)

for psser in self.pssers:
self.assertRaises(TypeError, lambda: self.psser ** psser)
self.assertRaises(TypeError, lambda: self.psser**psser)

def test_radd(self):
self.assertRaises(TypeError, lambda: "x" + self.psser)
Expand All @@ -105,7 +105,7 @@ def test_rmod(self):

def test_rpow(self):
self.assertRaises(TypeError, lambda: "x" ** self.psser)
self.assertRaises(TypeError, lambda: 1 ** self.psser)
self.assertRaises(TypeError, lambda: 1**self.psser)

def test_from_to_pandas(self):
data = [None, None, None]
Expand Down
14 changes: 7 additions & 7 deletions python/pyspark/pandas/tests/data_type_ops/test_num_ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -163,12 +163,12 @@ def test_pow(self):
for col in self.numeric_df_cols:
pser, psser = pdf[col], psdf[col]
if col in ["float", "float_w_nan"]:
self.assert_eq(pser ** pser, psser ** psser)
self.assert_eq(pser**pser, psser**psser)
self.assert_eq(pser ** pser.astype(bool), psser ** psser.astype(bool))
self.assert_eq(pser ** True, psser ** True)
self.assert_eq(pser ** False, psser ** False)
self.assert_eq(pser ** 1, psser ** 1)
self.assert_eq(pser ** 0, psser ** 0)
self.assert_eq(pser**True, psser**True)
self.assert_eq(pser**False, psser**False)
self.assert_eq(pser**1, psser**1)
self.assert_eq(pser**0, psser**0)

for n_col in self.non_numeric_df_cols:
if n_col == "bool":
Expand Down Expand Up @@ -243,8 +243,8 @@ def test_rpow(self):
# self.assert_eq(1 ** pser, 1 ** psser)
# self.assert_eq(0.1 ** pser, 0.1 ** psser)
self.assertRaises(TypeError, lambda: "x" ** psser)
self.assert_eq((True ** pser).astype(float), True ** psser)
self.assert_eq((False ** pser).astype(float), False ** psser)
self.assert_eq((True**pser).astype(float), True**psser)
self.assert_eq((False**pser).astype(float), False**psser)
self.assertRaises(TypeError, lambda: datetime.date(1994, 1, 1) ** psser)
self.assertRaises(TypeError, lambda: datetime.datetime(1994, 1, 1) ** psser)

Expand Down