refactor(ruff): switch from select to ignore

.pre-commit-config.yaml

@@ -2,14 +2,6 @@ minimum_pre_commit_version: 2.15.0
 ci:
     autofix_prs: false
 repos:
--   repo: https://github.com/psf/black
-    rev: 25.9.0
-    hooks:
-    -   id: black
--   repo: https://github.com/PyCQA/isort
-    rev: 6.0.1
-    hooks:
-    -   id: isort
 -   repo: https://github.com/astral-sh/ruff-pre-commit
     rev: v0.13.3
     hooks:
@@ -21,3 +13,11 @@ repos:
     - id: codespell
       additional_dependencies: [ tomli ]
       args: [-L, "THIRDPARTY"]
+-   repo: https://github.com/PyCQA/isort
+    rev: 6.0.1
+    hooks:
+    -   id: isort
+-   repo: https://github.com/psf/black
+    rev: 25.9.0
+    hooks:
+    -   id: black

conftest.py

@@ -1,10 +1,11 @@
+from collections.abc import Generator
 import gc
 
 import pytest
 
 
 @pytest.fixture
-def mpl_cleanup():
+def mpl_cleanup() -> Generator[None, None, None]:
     """
     Ensure Matplotlib is cleaned up around a test.
 

pandas-stubs/_libs/tslibs/__init__.pyi

@@ -1,14 +1,14 @@
 __all__ = [
-    "Period",
-    "Timestamp",
-    "Timedelta",
+    "BaseOffset",
     "NaT",
     "NaTType",
+    "OutOfBoundsDatetime",
+    "Period",
+    "Tick",
+    "Timedelta",
+    "Timestamp",
     "iNaT",
     "nat_strings",
-    "BaseOffset",
-    "Tick",
-    "OutOfBoundsDatetime",
 ]
 from pandas._libs.tslibs.nattype import (
     NaT,

pandas-stubs/core/groupby/__init__.pyi

@@ -8,8 +8,8 @@ from pandas.core.groupby.grouper import Grouper as Grouper
 
 __all__ = [
     "DataFrameGroupBy",
-    "NamedAgg",
-    "SeriesGroupBy",
     "GroupBy",
     "Grouper",
+    "NamedAgg",
+    "SeriesGroupBy",
 ]

pandas-stubs/testing.pyi

@@ -8,6 +8,6 @@ from pandas._testing import (
 __all__ = [
     "assert_extension_array_equal",
     "assert_frame_equal",
-    "assert_series_equal",
     "assert_index_equal",
+    "assert_series_equal",
 ]

pyproject.toml

@@ -176,16 +176,48 @@ fix = true
 
 
 [tool.ruff.lint]
-extend-select = ["B007", "B018", "PYI", "UP", "RUF100", "RUF059"]
+extend-select = ["ALL"]
 ignore = [
-  "E501",   # https://docs.astral.sh/ruff/rules/line-too-long/
-  "E731",   # https://docs.astral.sh/ruff/rules/lambda-assignment/
-  "PYI042", # https://docs.astral.sh/ruff/rules/snake-case-type-alias/
+  # The following rules are ignored permanently for good reasons
+  "COM",     # https://docs.astral.sh/ruff/rules/#flake8-commas-com
+  "D",       # https://docs.astral.sh/ruff/rules/#pydocstyle-d
+  "E501",    # handled by black https://docs.astral.sh/ruff/rules/line-too-long/
+  "EM",      # https://docs.astral.sh/ruff/rules/#flake8-errmsg-em
+  "FBT",     # https://docs.astral.sh/ruff/rules/#flake8-boolean-trap-fbt
+  "I",       # handled by isort
 ]
 
 
 [tool.ruff.lint.per-file-ignores]
-"_*.pyi" = ["PYI001"]
+"*.pyi" = [
+  # The following rules are ignored permanently for good reasons
+  "A001",    # https://docs.astral.sh/ruff/rules/builtin-variable-shadowing/
+  "A002",    # https://docs.astral.sh/ruff/rules/builtin-argument-shadowing/
+  "A004",    # https://docs.astral.sh/ruff/rules/builtin-import-shadowing/
+  "N",       # https://docs.astral.sh/ruff/rules/#pep8-naming-n
+  "PYI001",  # https://docs.astral.sh/ruff/rules/unprefixed-type-param/
+  "PYI042",  # https://docs.astral.sh/ruff/rules/snake-case-type-alias/
+  "TD002",   # https://docs.astral.sh/ruff/rules/missing-todo-author/
+  # The following rules are ignored temporarily. Either fix them or move to the permanent list above.
+  "ERA", "S", "ANN", "FIX002", "TD003", "TD004", "PLR0402", "PLC0105"
+  ]
+"scripts/*" = [
+  # The following rules are ignored permanently for good reasons
+  "S603",    # https://docs.astral.sh/ruff/rules/subprocess-without-shell-equals-true/
+  # The following rules are ignored temporarily. Either fix them or move to the permanent list above.
+  "TRY", "PT", "BLE"
+]
+"tests/*" = [
+  # The following rules are ignored permanently for good reasons
+  "E731",    # https://docs.astral.sh/ruff/rules/lambda-assignment/
+  "PD",      # Pandas is here
+  "PLC0415", # https://docs.astral.sh/ruff/rules/import-outside-top-level/
+  "S101",    # https://docs.astral.sh/ruff/rules/assert/
+  "S301",    # https://docs.astral.sh/ruff/rules/suspicious-pickle-usage/
+  "SLF001",  # https://docs.astral.sh/ruff/rules/private-member-access/
+  # The following rules are ignored temporarily. Either fix them or move to the permanent list above.
+  "ANN", "ARG", "ERA", "RUF", "SIM", "TRY", "PT", "NPY", "N", "DTZ", "PLR", "TC", "PGH", "PTH", "S311", "C901", "FIX", "TD", "A001", "PYI042", "ANN201"
+]
 
 
 [tool.mypy]

scripts/test/__init__.py

@@ -51,17 +51,17 @@ def stubtest(allowlist: str, check_missing: bool, nightly: bool) -> None:
     steps = _DIST_STEPS[:2]
     if nightly:
         steps.append(_step.nightly)
-    run_job(steps + [stubtest])
+    run_job([*steps, stubtest])
 
 
 def pytest(nightly: bool) -> None:
     setup_steps = []
     pytest_step = _step.pytest
     if nightly:
         setup_steps = [_step.nightly]
-    run_job(setup_steps + [pytest_step])
+    run_job([*setup_steps, pytest_step])
 
 
 def mypy_src(mypy_nightly: bool) -> None:
     steps = [_step.mypy_nightly] if mypy_nightly else []
-    run_job(steps + [_step.mypy_src])
+    run_job([*steps, _step.mypy_src])

tests/__init__.py

@@ -87,8 +87,7 @@ def check(
             and get_origin(shape_type) is tuple
             and (tuple_args := get_args(shape_type))
             and ... not in tuple_args  # fixed-length tuple
-            and (arr_ndim := getattr(actual, "ndim"))
-            != (expected_ndim := len(tuple_args))
+            and (arr_ndim := actual.ndim) != (expected_ndim := len(tuple_args))  # type: ignore[attr-defined]  # pyright: ignore[reportAttributeAccessIssue]
         ):
             raise RuntimeError(
                 f"Array has wrong dimension {arr_ndim}, expected {expected_ndim}"
@@ -100,7 +99,7 @@ def check(
             and (dtype_args := get_args(dtype_type))
             and isinstance((expected_dtype := dtype_args[0]), type)
             and issubclass(expected_dtype, np.generic)
-            and (arr_dtype := getattr(actual, "dtype")) != expected_dtype
+            and (arr_dtype := actual.dtype) != expected_dtype  # type: ignore[attr-defined]  # pyright: ignore[reportAttributeAccessIssue]
         ):
             raise RuntimeError(
                 f"Array has wrong dtype {arr_dtype}, expected {expected_dtype.__name__}"
@@ -208,8 +207,6 @@ def pytest_warns_bounded(
         current = Version(version_str)
     if lb < current < ub:
         return pytest.warns(warning, match=match)
-    else:
-        if upper_exception is None:
-            return nullcontext()
-        else:
-            return suppress(upper_exception)
+    if upper_exception is None:
+        return nullcontext()
+    return suppress(upper_exception)

tests/extension/decimal/array.py

@@ -150,21 +150,18 @@ def __array_ufunc__(self, ufunc: np.ufunc, method: str, *inputs, **kwargs: Any):
         def reconstruct(x):
             if isinstance(x, (decimal.Decimal, numbers.Number)):
                 return x
-            else:
-                return DecimalArray._from_sequence(x)
+            return DecimalArray._from_sequence(x)
 
         if ufunc.nout > 1:
             return tuple(reconstruct(x) for x in result)
-        else:
-            return reconstruct(result)
+        return reconstruct(result)
 
     def __getitem__(self, item):
         if isinstance(item, numbers.Integral):
             return self._data[item]
-        else:
-            # array, slice.
-            item = check_array_indexer(self, item)
-            return type(self)(self._data[item])
+        # array, slice.
+        item = check_array_indexer(self, item)
+        return type(self)(self._data[item])
 
     def take(
         self, indexer: TakeIndexer, *, allow_fill: bool = False, fill_value=None
@@ -208,10 +205,9 @@ def __len__(self) -> int:
     def __contains__(self, item) -> bool | np.bool_:
         if not isinstance(item, decimal.Decimal):
             return False
-        elif item.is_nan():
+        if item.is_nan():
             return self.isna().any()
-        else:
-            return super().__contains__(item)
+        return super().__contains__(item)
 
     @property
     def nbytes(self) -> int:
@@ -270,7 +266,7 @@ def convert_values(param):
 
         # If the operator is not defined for the underlying objects,
         # a TypeError should be raised
-        res = [op(a, b) for (a, b) in zip(lvalues, rvalues)]
+        res = [op(a, b) for (a, b) in zip(lvalues, rvalues, strict=False)]
 
         return np.asarray(res, dtype=bool)
 

tests/indexes/test_indexes.py

@@ -120,7 +120,9 @@ def test_multiindex_constructors() -> None:
         pd.MultiIndex,
     )
     check(
-        assert_type(pd.MultiIndex.from_tuples(zip([1, 2], [3, 4])), pd.MultiIndex),
+        assert_type(
+            pd.MultiIndex.from_tuples(zip([1, 2], [3, 4], strict=False)), pd.MultiIndex
+        ),
         pd.MultiIndex,
     )
     check(
@@ -152,10 +154,10 @@ def test_column_contains() -> None:
     # https://github.com/microsoft/python-type-stubs/issues/199
     df = pd.DataFrame({"A": [1, 2], "B": ["c", "d"], "E": [3, 4]})
 
-    collist = [column for column in df.columns]
+    collist = list(df.columns)
     check(assert_type(collist, list[str]), list, str)
 
-    collist2 = [column for column in df.columns[df.columns.str.contains("A|B")]]
+    collist2 = list(df.columns[df.columns.str.contains("A|B")])
     check(assert_type(collist2, list[str]), list, str)
 
     length = len(df.columns[df.columns.str.contains("A|B")])

tests/series/test_series.py

@@ -1910,7 +1910,7 @@ def test_resample() -> None:
     # GH 181
     N = 10
     index = pd.date_range("1/1/2000", periods=N, freq="min")
-    x = [x for x in range(N)]
+    x = list(range(N))
     s = pd.Series(x, index=index, dtype=float)
     check(assert_type(s.resample("2min").std(), "pd.Series[float]"), pd.Series, float)
     check(assert_type(s.resample("2min").var(), "pd.Series[float]"), pd.Series, float)
@@ -2141,7 +2141,7 @@ def func() -> MySeries[float]:
 def test_change_to_dict_return_type() -> None:
     id = [1, 2, 3]
     value = ["a", "b", "c"]
-    df = pd.DataFrame(zip(id, value), columns=["id", "value"])
+    df = pd.DataFrame(zip(id, value, strict=False), columns=["id", "value"])
     fd = df.set_index("id")["value"].to_dict()
     check(assert_type(fd, dict[Any, Any]), dict)
 
@@ -2976,7 +2976,7 @@ def test_astype_other() -> None:
 
 def test_all_astype_args_tested() -> None:
     """Check that all relevant numpy type aliases are tested."""
-    NUMPY_ALIASES: set[str] = {k for k in np.sctypeDict}
+    NUMPY_ALIASES: set[str] = set(np.sctypeDict)
     EXCLUDED_ALIASES = {
         "datetime64",
         "m",
@@ -3631,7 +3631,7 @@ def test_series_unique_timedelta() -> None:
 def test_slice_timestamp() -> None:
     dti = pd.date_range("1/1/2025", "2/28/2025")
 
-    s = pd.Series([i for i in range(len(dti))], index=dti)
+    s = pd.Series(list(range(len(dti))), index=dti)
 
     # For `s1`, see discussion in GH 397.  Needs mypy fix.
     # s1 = s.loc["2025-01-15":"2025-01-20"]
@@ -3708,7 +3708,7 @@ def test_series_bool_fails() -> None:
         if s == "foo":  # pyright: ignore[reportGeneralTypeIssues]
             # Next line is unreachable.
             _a = s[0]
-            assert False
+            raise AssertionError
     except ValueError:
         pass