Migrate pylint to ruff (#57182)

tqa236 · mroeschke · web-flow · commit d460abddac3e · 2024-04-08T14:24:19.000-07:00
Configure ruff pylint

Co-authored-by: Matthew Roeschke &lt;10647082+mroeschke@users.noreply.github.com&gt;
diff --git a/.github/workflows/code-checks.yml b/.github/workflows/code-checks.yml
@@ -85,7 +85,7 @@ jobs:
         echo "PYTHONPATH=$PYTHONPATH" >> $GITHUB_ENV
       if: ${{ steps.build.outcome == 'success' && always() }}
 
-    - name: Typing + pylint
+    - name: Typing
       uses: pre-commit/action@v3.0.1
       with:
         extra_args: --verbose --hook-stage manual --all-files
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -16,7 +16,7 @@ ci:
     autofix_prs: false
     autoupdate_schedule: monthly
     # manual stage hooks
-    skip: [pylint, pyright, mypy]
+    skip: [pyright, mypy]
 repos:
 -   repo: https://github.com/astral-sh/ruff-pre-commit
     rev: v0.3.4
@@ -67,25 +67,6 @@ repos:
     -   id: fix-encoding-pragma
         args: [--remove]
     -   id: trailing-whitespace
--   repo: https://github.com/pylint-dev/pylint
-    rev: v3.0.1
-    hooks:
-    -   id: pylint
-        stages: [manual]
-        args: [--load-plugins=pylint.extensions.redefined_loop_name, --fail-on=I0021]
-    -   id: pylint
-        alias: redefined-outer-name
-        name: Redefining name from outer scope
-        files: ^pandas/
-        exclude: |
-            (?x)
-            ^pandas/tests  # keep excluded
-            |/_testing/  # keep excluded
-            |^pandas/util/_test_decorators\.py  # keep excluded
-            |^pandas/_version\.py  # keep excluded
-            |^pandas/conftest\.py  # keep excluded
-        args: [--disable=all, --enable=redefined-outer-name]
-        stages: [manual]
 -   repo: https://github.com/PyCQA/isort
     rev: 5.13.2
     hooks:
diff --git a/pandas/_libs/tslibs/__init__.py b/pandas/_libs/tslibs/__init__.py
@@ -36,7 +36,7 @@
     "is_supported_dtype",
 ]
 
-from pandas._libs.tslibs import dtypes  # pylint: disable=import-self
+from pandas._libs.tslibs import dtypes
 from pandas._libs.tslibs.conversion import localize_pydatetime
 from pandas._libs.tslibs.dtypes import (
     Resolution,
diff --git a/pandas/core/arrays/categorical.py b/pandas/core/arrays/categorical.py
@@ -2482,7 +2482,6 @@ def unique(self) -> Self:
         ['b', 'a']
         Categories (3, object): ['a' < 'b' < 'c']
         """
-        # pylint: disable=useless-parent-delegation
         return super().unique()
 
     def _cast_quantile_result(self, res_values: np.ndarray) -> np.ndarray:
diff --git a/pandas/core/arrays/datetimelike.py b/pandas/core/arrays/datetimelike.py
@@ -506,7 +506,6 @@ def view(self, dtype: Literal["m8[ns]"]) -> TimedeltaArray: ...
     @overload
     def view(self, dtype: Dtype | None = ...) -> ArrayLike: ...
 
-    # pylint: disable-next=useless-parent-delegation
     def view(self, dtype: Dtype | None = None) -> ArrayLike:
         # we need to explicitly call super() method as long as the `@overload`s
         #  are present in this file.
diff --git a/pandas/core/base.py b/pandas/core/base.py
@@ -127,7 +127,7 @@ def __sizeof__(self) -> int:
         """
         memory_usage = getattr(self, "memory_usage", None)
         if memory_usage:
-            mem = memory_usage(deep=True)  # pylint: disable=not-callable
+            mem = memory_usage(deep=True)
             return int(mem if is_scalar(mem) else mem.sum())
 
         # no memory_usage attribute, so fall back to object's 'sizeof'
diff --git a/pandas/core/dtypes/common.py b/pandas/core/dtypes/common.py
@@ -250,7 +250,7 @@ def is_scipy_sparse(arr) -> bool:
     """
     global _is_scipy_sparse
 
-    if _is_scipy_sparse is None:  # pylint: disable=used-before-assignment
+    if _is_scipy_sparse is None:
         try:
             from scipy.sparse import issparse as _is_scipy_sparse
         except ImportError:
diff --git a/pandas/core/groupby/groupby.py b/pandas/core/groupby/groupby.py
@@ -5014,7 +5014,7 @@ def shift(
             period = cast(int, period)
             if freq is not None:
                 f = lambda x: x.shift(
-                    period,  # pylint: disable=cell-var-from-loop
+                    period,
                     freq,
                     0,  # axis
                     fill_value,
diff --git a/pandas/core/indexes/multi.py b/pandas/core/indexes/multi.py
@@ -2803,7 +2803,6 @@ def get_slice_bound(
             label = (label,)
         return self._partial_tup_index(label, side=side)
 
-    # pylint: disable-next=useless-parent-delegation
     def slice_locs(self, start=None, end=None, step=None) -> tuple[int, int]:
         """
         For an ordered MultiIndex, compute the slice locations for input
diff --git a/pandas/core/internals/__init__.py b/pandas/core/internals/__init__.py
@@ -6,9 +6,9 @@
 )
 
 __all__ = [
-    "Block",  # pylint: disable=undefined-all-variable
-    "DatetimeTZBlock",  # pylint: disable=undefined-all-variable
-    "ExtensionBlock",  # pylint: disable=undefined-all-variable
+    "Block",
+    "DatetimeTZBlock",
+    "ExtensionBlock",
     "make_block",
     "BlockManager",
     "SingleBlockManager",
diff --git a/pandas/core/series.py b/pandas/core/series.py
@@ -1469,7 +1469,6 @@ def __repr__(self) -> str:
         """
         Return a string representation for a particular Series.
         """
-        # pylint: disable=invalid-repr-returned
         repr_params = fmt.get_series_repr_params()
         return self.to_string(**repr_params)
 
@@ -2059,7 +2058,7 @@ def mode(self, dropna: bool = True) -> Series:
             dtype=self.dtype,
         ).__finalize__(self, method="mode")
 
-    def unique(self) -> ArrayLike:  # pylint: disable=useless-parent-delegation
+    def unique(self) -> ArrayLike:
         """
         Return unique values of Series object.
 
diff --git a/pandas/io/formats/style.py b/pandas/io/formats/style.py
@@ -3038,7 +3038,7 @@ def set_properties(self, subset: Subset | None = None, **kwargs) -> Styler:
         return self.map(lambda x: values, subset=subset)
 
     @Substitution(subset=subset_args)
-    def bar(  # pylint: disable=disallowed-name
+    def bar(
         self,
         subset: Subset | None = None,
         axis: Axis | None = 0,
diff --git a/pandas/plotting/_core.py b/pandas/plotting/_core.py
@@ -1187,7 +1187,7 @@ def line(
     )
     @Substitution(kind="bar")
     @Appender(_bar_or_line_doc)
-    def bar(  # pylint: disable=disallowed-name
+    def bar(
         self,
         x: Hashable | None = None,
         y: Hashable | None = None,
diff --git a/pandas/plotting/_matplotlib/boxplot.py b/pandas/plotting/_matplotlib/boxplot.py
@@ -82,7 +82,7 @@ def __init__(self, data, return_type: str = "axes", **kwargs) -> None:
 
         self.return_type = return_type
         # Do not call LinePlot.__init__ which may fill nan
-        MPLPlot.__init__(self, data, **kwargs)  # pylint: disable=non-parent-init-called
+        MPLPlot.__init__(self, data, **kwargs)
 
         if self.subplots:
             # Disable label ax sharing. Otherwise, all subplots shows last
diff --git a/pandas/plotting/_matplotlib/core.py b/pandas/plotting/_matplotlib/core.py
@@ -297,7 +297,7 @@ def __init__(
     def _validate_sharex(sharex: bool | None, ax, by) -> bool:
         if sharex is None:
             # if by is defined, subplots are used and sharex should be False
-            if ax is None and by is None:  # pylint: disable=simplifiable-if-statement
+            if ax is None and by is None:
                 sharex = True
             else:
                 # if we get an axis, the users should do the visibility
diff --git a/pandas/plotting/_matplotlib/hist.py b/pandas/plotting/_matplotlib/hist.py
@@ -78,7 +78,7 @@ def __init__(
         self.xlabel = kwargs.get("xlabel")
         self.ylabel = kwargs.get("ylabel")
         # Do not call LinePlot.__init__ which may fill nan
-        MPLPlot.__init__(self, data, **kwargs)  # pylint: disable=non-parent-init-called
+        MPLPlot.__init__(self, data, **kwargs)
 
         self.bins = self._adjust_bins(bins)
 
@@ -236,7 +236,7 @@ def __init__(
         self, data, bw_method=None, ind=None, *, weights=None, **kwargs
     ) -> None:
         # Do not call LinePlot.__init__ which may fill nan
-        MPLPlot.__init__(self, data, **kwargs)  # pylint: disable=non-parent-init-called
+        MPLPlot.__init__(self, data, **kwargs)
         self.bw_method = bw_method
         self.ind = ind
         self.weights = weights
diff --git a/pandas/tests/config/test_config.py b/pandas/tests/config/test_config.py
@@ -227,7 +227,6 @@ def test_validation(self):
 
         validator = cf.is_one_of_factory([None, cf.is_callable])
         cf.register_option("b", lambda: None, "doc", validator=validator)
-        # pylint: disable-next=consider-using-f-string
         cf.set_option("b", "%.1f".format)  # Formatter is callable
         cf.set_option("b", None)  # Formatter is none (default)
         with pytest.raises(ValueError, match="Value must be a callable"):
diff --git a/pandas/tests/dtypes/test_inference.py b/pandas/tests/dtypes/test_inference.py
@@ -240,8 +240,6 @@ def test_is_list_like_generic():
     # is_list_like was yielding false positives for Generic classes in python 3.11
     T = TypeVar("T")
 
-    # https://github.com/pylint-dev/pylint/issues/9398
-    # pylint: disable=multiple-statements
     class MyDataFrame(DataFrame, Generic[T]): ...
 
     tstc = MyDataFrame[int]
diff --git a/pandas/tests/groupby/test_grouping.py b/pandas/tests/groupby/test_grouping.py
@@ -1044,7 +1044,6 @@ def test_multi_iter_frame(self, three_group):
         grouped = df.groupby(["k1", "k2"])
         # calling `dict` on a DataFrameGroupBy leads to a TypeError,
         # we need to use a dictionary comprehension here
-        # pylint: disable-next=unnecessary-comprehension
         groups = {key: gp for key, gp in grouped}  # noqa: C416
         assert len(groups) == 2
 
diff --git a/pandas/tests/indexes/datetimes/test_iter.py b/pandas/tests/indexes/datetimes/test_iter.py
@@ -20,7 +20,7 @@ def test_iteration_preserves_nanoseconds(self, tz):
             ["2018-02-08 15:00:00.168456358", "2018-02-08 15:00:00.168456359"], tz=tz
         )
         for i, ts in enumerate(index):
-            assert ts == index[i]  # pylint: disable=unnecessary-list-index-lookup
+            assert ts == index[i]
 
     def test_iter_readonly(self):
         # GH#28055 ints_to_pydatetime with readonly array
@@ -35,7 +35,7 @@ def test_iteration_preserves_tz(self):
 
         for i, ts in enumerate(index):
             result = ts
-            expected = index[i]  # pylint: disable=unnecessary-list-index-lookup
+            expected = index[i]
             assert result == expected
 
     def test_iteration_preserves_tz2(self):
@@ -45,7 +45,7 @@ def test_iteration_preserves_tz2(self):
 
         for i, ts in enumerate(index):
             result = ts
-            expected = index[i]  # pylint: disable=unnecessary-list-index-lookup
+            expected = index[i]
             assert result._repr_base == expected._repr_base
             assert result == expected
 
@@ -56,7 +56,7 @@ def test_iteration_preserves_tz3(self):
         )
         for i, ts in enumerate(index):
             result = ts
-            expected = index[i]  # pylint: disable=unnecessary-list-index-lookup
+            expected = index[i]
             assert result._repr_base == expected._repr_base
             assert result == expected
 
diff --git a/pandas/tests/io/formats/style/test_html.py b/pandas/tests/io/formats/style/test_html.py
@@ -821,7 +821,6 @@ def test_rendered_links(type, text, exp, found):
 
 def test_multiple_rendered_links():
     links = ("www.a.b", "http://a.c", "https://a.d", "ftp://a.e")
-    # pylint: disable-next=consider-using-f-string
     df = DataFrame(["text {} {} text {} {}".format(*links)])
     result = df.style.format(hyperlinks="html").to_html()
     href = '<a href="{0}" target="_blank">{0}</a>'
diff --git a/pandas/tests/io/test_html.py b/pandas/tests/io/test_html.py
@@ -152,7 +152,6 @@ def test_to_html_compat(self, flavor_read_html):
                 np.random.default_rng(2).random((4, 3)),
                 columns=pd.Index(list("abc"), dtype=object),
             )
-            # pylint: disable-next=consider-using-f-string
             .map("{:.3f}".format)
             .astype(float)
         )
@@ -1460,7 +1459,6 @@ def seek(self, offset):
             def seekable(self):
                 return True
 
-            # GH 49036 pylint checks for presence of __next__ for iterators
             def __next__(self): ...
 
             def __iter__(self) -> Iterator:
diff --git a/pandas/tests/reshape/test_pivot.py b/pandas/tests/reshape/test_pivot.py
@@ -819,7 +819,7 @@ def test_pivot_columns_none_raise_error(self):
         df = DataFrame({"col1": ["a", "b", "c"], "col2": [1, 2, 3], "col3": [1, 2, 3]})
         msg = r"pivot\(\) missing 1 required keyword-only argument: 'columns'"
         with pytest.raises(TypeError, match=msg):
-            df.pivot(index="col1", values="col3")  # pylint: disable=missing-kwoa
+            df.pivot(index="col1", values="col3")
 
     @pytest.mark.xfail(
         reason="MultiIndexed unstack with tuple names fails with KeyError GH#19966"
@@ -2600,7 +2600,7 @@ def test_pivot_columns_not_given(self):
         # GH#48293
         df = DataFrame({"a": [1], "b": 1})
         with pytest.raises(TypeError, match="missing 1 required keyword-only argument"):
-            df.pivot()  # pylint: disable=missing-kwoa
+            df.pivot()
 
     @pytest.mark.xfail(using_pyarrow_string_dtype(), reason="None is cast to NaN")
     def test_pivot_columns_is_none(self):
diff --git a/pandas/tests/scalar/timedelta/test_arithmetic.py b/pandas/tests/scalar/timedelta/test_arithmetic.py
@@ -1180,5 +1180,5 @@ def test_ops_error_str():
         with pytest.raises(TypeError, match=msg):
             left > right
 
-        assert not left == right  # pylint: disable=unneeded-not
+        assert not left == right
         assert left != right
diff --git a/pandas/tests/scalar/timestamp/test_comparisons.py b/pandas/tests/scalar/timestamp/test_comparisons.py
@@ -309,5 +309,5 @@ def __eq__(self, other) -> bool:
     for left, right in [(inf, timestamp), (timestamp, inf)]:
         assert left > right or left < right
         assert left >= right or left <= right
-        assert not left == right  # pylint: disable=unneeded-not
+        assert not left == right
         assert left != right
diff --git a/pandas/tests/util/test_deprecate_nonkeyword_arguments.py b/pandas/tests/util/test_deprecate_nonkeyword_arguments.py
@@ -124,8 +124,7 @@ def test_i_signature():
 
 class Foo:
     @deprecate_nonkeyword_arguments(version=None, allowed_args=["self", "bar"])
-    def baz(self, bar=None, foobar=None):  # pylint: disable=disallowed-name
-        ...
+    def baz(self, bar=None, foobar=None): ...
 
 
 def test_foo_signature():
diff --git a/pyproject.toml b/pyproject.toml
diff --git a/scripts/tests/data/deps_minimum.toml b/scripts/tests/data/deps_minimum.toml

Original file line number	Diff line number	Diff line change
`@@ -36,7 +36,7 @@`
`36`	`36`	`"is_supported_dtype",`
`37`	`37`	`]`
`38`	`38`
`39`		`-from pandas._libs.tslibs import dtypes # pylint: disable=import-self`
	`39`	`+from pandas._libs.tslibs import dtypes`
`40`	`40`	`from pandas._libs.tslibs.conversion import localize_pydatetime`
`41`	`41`	`from pandas._libs.tslibs.dtypes import (`
`42`	`42`	`Resolution,`