DEV/STYLE: use ruff for linting (#50160)

* Test ruff for linting

* further updates

* add pre-commit

* fixup

* restore flake (still needed for validate_docstrings)

* hey, all the per-file-ignores can be removed!

* Update pandas/tests/io/test_html.py

Co-authored-by: Joris Van den Bossche <jorisvandenbossche@gmail.com>

* remove outdated per-file-ignores

* update to .216, set target version

* sync version with environment (todo - remove later)

* CI didnt start, empty commit to retry?

* remove ruff from environment.yml

* back to 0.0.215

Co-authored-by: MarcoGorelli <>
Co-authored-by: Marco Edward Gorelli <33491632+MarcoGorelli@users.noreply.github.com>

Author: jorisvandenbossche

.pre-commit-config.yaml

@@ -15,6 +15,10 @@ default_stages: [
 ci:
     autofix_prs: false
 repos:
+-   repo: https://github.com/charliermarsh/ruff-pre-commit
+    rev: v0.0.215
+    hooks:
+    -   id: ruff
 -   repo: https://github.com/MarcoGorelli/absolufy-imports
     rev: v0.3.1
     hooks:
@@ -66,13 +70,6 @@ repos:
             --linelength=88,
             '--filter=-readability/casting,-runtime/int,-build/include_subdir,-readability/fn_size'
         ]
--   repo: https://github.com/PyCQA/flake8
-    rev: 6.0.0
-    hooks:
-    -   id: flake8
-        additional_dependencies: &flake8_dependencies
-        - flake8==6.0.0
-        - flake8-bugbear==22.7.1
 -   repo: https://github.com/pycqa/pylint
     rev: v2.15.9
     hooks:
@@ -117,12 +114,6 @@ repos:
     rev: v0.6.7
     hooks:
     - id: sphinx-lint
--   repo: https://github.com/asottile/yesqa
-    rev: v1.4.0
-    hooks:
-    -   id: yesqa
-        additional_dependencies: *flake8_dependencies
-        stages: [manual]
 -   repo: local
     hooks:
     # NOTE: we make `black` a local hook because if it's installed from
@@ -326,13 +317,6 @@ repos:
         files: ^(environment.yml|requirements-dev.txt)$
         pass_filenames: false
         additional_dependencies: [pyyaml, toml]
-    -   id: sync-flake8-versions
-        name: Check flake8 version is synced across flake8, yesqa, and environment.yml
-        language: python
-        entry: python scripts/sync_flake8_versions.py
-        files: ^(\.pre-commit-config\.yaml|environment\.yml)$
-        pass_filenames: false
-        additional_dependencies: [pyyaml, toml]
     -   id: title-capitalization
         name: Validate correct capitalization among titles in documentation
         entry: python scripts/validate_rst_title_capitalization.py

doc/source/development/contributing_codebase.rst

@@ -43,7 +43,7 @@ Pre-commit
 ----------
 
 Additionally, :ref:`Continuous Integration <contributing.ci>` will run code formatting checks
-like ``black``, ``flake8``,
+like ``black``, ``ruff``,
 ``isort``, and ``cpplint`` and more using `pre-commit hooks <https://pre-commit.com/>`_
 Any warnings from these checks will cause the :ref:`Continuous Integration <contributing.ci>` to fail; therefore,
 it is helpful to run the check yourself before submitting code. This

environment.yml

@@ -78,12 +78,11 @@ dependencies:
   - black=22.10.0
   - cpplint
   - flake8=6.0.0
-  - flake8-bugbear=22.7.1 # used by flake8, find likely bugs
   - isort>=5.2.1  # check that imports are in the right order
   - mypy=0.991
   - pre-commit>=2.15.0
-  - pycodestyle  # used by flake8
   - pyupgrade
+  - ruff=0.0.215
 
   # documentation
   - gitpython  # obtain contributors from git for whatsnew

pandas/core/computation/pytables.py

@@ -242,7 +242,7 @@ def stringify(value):
             return TermValue(v, v, kind)
         elif kind == "bool":
             if isinstance(v, str):
-                v = not v.strip().lower() in [
+                v = v.strip().lower() not in [
                     "false",
                     "f",
                     "no",

pandas/core/generic.py

@@ -10811,7 +10811,7 @@ def _accum_func(
 
         if axis == 1:
             return self.T._accum_func(
-                name, func, axis=0, skipna=skipna, *args, **kwargs
+                name, func, axis=0, skipna=skipna, *args, **kwargs  # noqa: B026
             ).T
 
         def block_accum_func(blk_values):

pandas/core/reshape/merge.py

@@ -10,6 +10,7 @@
 from typing import (
     TYPE_CHECKING,
     Hashable,
+    Literal,
     Sequence,
     cast,
 )
@@ -31,7 +32,6 @@
     DtypeObj,
     IndexLabel,
     JoinHow,
-    Literal,
     MergeHow,
     Shape,
     Suffixes,

pandas/io/formats/latex.py

@@ -54,7 +54,7 @@ def _split_into_full_short_caption(
     return full_caption, short_caption
 
 
-class RowStringConverter(ABC):
+class RowStringConverter:
     r"""Converter for dataframe rows into LaTeX strings.
 
     Parameters

pandas/io/formats/style.py

@@ -2253,7 +2253,7 @@ def set_sticky(
                         "props": props + "top:0px; z-index:2;",
                     }
                 ]
-                if not self.index.names[0] is None:
+                if self.index.names[0] is not None:
                     styles[0]["props"] = (
                         props + f"top:0px; z-index:2; height:{pixel_size}px;"
                     )

pandas/io/parsers/python_parser.py

@@ -1017,12 +1017,12 @@ def _rows_to_cols(self, content: list[list[Scalar]]) -> list[np.ndarray]:
             content_len = len(content)
             content = []
 
-            for (i, l) in iter_content:
-                actual_len = len(l)
+            for (i, _content) in iter_content:
+                actual_len = len(_content)
 
                 if actual_len > col_len:
                     if callable(self.on_bad_lines):
-                        new_l = self.on_bad_lines(l)
+                        new_l = self.on_bad_lines(_content)
                         if new_l is not None:
                             content.append(new_l)
                     elif self.on_bad_lines in (
@@ -1035,7 +1035,7 @@ def _rows_to_cols(self, content: list[list[Scalar]]) -> list[np.ndarray]:
                         if self.on_bad_lines == self.BadLineHandleMethod.ERROR:
                             break
                 else:
-                    content.append(l)
+                    content.append(_content)
 
             for row_num, actual_len in bad_lines:
                 msg = (

pandas/plotting/_matplotlib/core.py

@@ -455,6 +455,7 @@ def generate(self) -> None:
             self._post_plot_logic_common(ax, self.data)
             self._post_plot_logic(ax, self.data)
 
+    @abstractmethod
     def _args_adjust(self) -> None:
         pass
 
@@ -664,6 +665,7 @@ def _post_plot_logic_common(self, ax, data):
         else:  # pragma no cover
             raise ValueError
 
+    @abstractmethod
     def _post_plot_logic(self, ax, data) -> None:
         """Post process for each axes. Overridden in child classes"""
 
@@ -1278,6 +1280,9 @@ def _make_plot(self):
             err_kwds["ecolor"] = scatter.get_facecolor()[0]
             ax.errorbar(data[x].values, data[y].values, linestyle="none", **err_kwds)
 
+    def _args_adjust(self) -> None:
+        pass
+
 
 class HexBinPlot(PlanePlot):
     @property
@@ -1310,6 +1315,9 @@ def _make_plot(self) -> None:
     def _make_legend(self) -> None:
         pass
 
+    def _args_adjust(self) -> None:
+        pass
+
 
 class LinePlot(MPLPlot):
     _default_rot = 0
@@ -1469,6 +1477,9 @@ def _update_stacker(cls, ax: Axes, stacking_id, values) -> None:
         elif (values <= 0).all():
             ax._stacker_neg_prior[stacking_id] += values
 
+    def _args_adjust(self) -> None:
+        pass
+
     def _post_plot_logic(self, ax: Axes, data) -> None:
         from matplotlib.ticker import FixedLocator
 
@@ -1573,6 +1584,9 @@ def _plot(  # type: ignore[override]
         res = [rect]
         return res
 
+    def _args_adjust(self) -> None:
+        pass
+
     def _post_plot_logic(self, ax: Axes, data) -> None:
         LinePlot._post_plot_logic(self, ax, data)
 
@@ -1855,5 +1869,8 @@ def blank_labeler(label, value):
 
             # leglabels is used for legend labels
             leglabels = labels if labels is not None else idx
-            for p, l in zip(patches, leglabels):
-                self._append_legend_handles_labels(p, l)
+            for _patch, _leglabel in zip(patches, leglabels):
+                self._append_legend_handles_labels(_patch, _leglabel)
+
+    def _post_plot_logic(self, ax: Axes, data) -> None:
+        pass

pandas/tests/arithmetic/test_datetime64.py

@@ -201,13 +201,13 @@ def test_nat_comparisons(
         expected,
     ):
         box = index_or_series
-        l, r = pair
+        lhs, rhs = pair
         if reverse:
             # add lhs / rhs switched data
-            l, r = r, l
+            lhs, rhs = rhs, lhs
 
-        left = Series(l, dtype=dtype)
-        right = box(r, dtype=dtype)
+        left = Series(lhs, dtype=dtype)
+        right = box(rhs, dtype=dtype)
 
         result = op(left, right)
 

pandas/tests/frame/test_constructors.py

@@ -2469,7 +2469,7 @@ def test_dict_nocopy(
         if (
             using_array_manager
             and not copy
-            and not (any_numpy_dtype in (tm.STRING_DTYPES + tm.BYTES_DTYPES))
+            and any_numpy_dtype not in tm.STRING_DTYPES + tm.BYTES_DTYPES
         ):
             # TODO(ArrayManager) properly honor copy keyword for dict input
             td.mark_array_manager_not_yet_implemented(request)

pandas/tests/indexes/period/test_indexing.py

@@ -778,8 +778,8 @@ def test_contains_freq_mismatch(self):
         rng = period_range("2007-01", freq="M", periods=10)
 
         assert Period("2007-01", freq="M") in rng
-        assert not Period("2007-01", freq="D") in rng
-        assert not Period("2007-01", freq="2M") in rng
+        assert Period("2007-01", freq="D") not in rng
+        assert Period("2007-01", freq="2M") not in rng
 
     def test_contains_nat(self):
         # see gh-13582

pandas/tests/io/formats/test_format.py

@@ -134,7 +134,7 @@ def has_horizontally_truncated_repr(df):
         return False
     # Make sure each row has this ... in the same place
     r = repr(df)
-    for ix, l in enumerate(r.splitlines()):
+    for ix, _ in enumerate(r.splitlines()):
         if not r.split()[cand_col] == "...":
             return False
     return True

pandas/tests/io/test_html.py

@@ -405,10 +405,8 @@ def test_invalid_table_attrs(self, banklist_data):
                 url, match="First Federal Bank of Florida", attrs={"id": "tasdfable"}
             )
 
-    def _bank_data(self, path, *args, **kwargs):
-        return self.read_html(
-            path, match="Metcalf", attrs={"id": "table"}, *args, **kwargs
-        )
+    def _bank_data(self, path, **kwargs):
+        return self.read_html(path, match="Metcalf", attrs={"id": "table"}, **kwargs)
 
     @pytest.mark.slow
     def test_multiindex_header(self, banklist_data):

pandas/tests/plotting/test_datetimelike.py

@@ -1021,10 +1021,10 @@ def test_time(self):
         # verify tick labels
         ticks = ax.get_xticks()
         labels = ax.get_xticklabels()
-        for t, l in zip(ticks, labels):
-            m, s = divmod(int(t), 60)
+        for _tick, _label in zip(ticks, labels):
+            m, s = divmod(int(_tick), 60)
             h, m = divmod(m, 60)
-            rs = l.get_text()
+            rs = _label.get_text()
             if len(rs) > 0:
                 if s != 0:
                     xp = time(h, m, s).strftime("%H:%M:%S")
@@ -1045,10 +1045,10 @@ def test_time_change_xlim(self):
         # verify tick labels
         ticks = ax.get_xticks()
         labels = ax.get_xticklabels()
-        for t, l in zip(ticks, labels):
-            m, s = divmod(int(t), 60)
+        for _tick, _label in zip(ticks, labels):
+            m, s = divmod(int(_tick), 60)
             h, m = divmod(m, 60)
-            rs = l.get_text()
+            rs = _label.get_text()
             if len(rs) > 0:
                 if s != 0:
                     xp = time(h, m, s).strftime("%H:%M:%S")
@@ -1062,10 +1062,10 @@ def test_time_change_xlim(self):
         # check tick labels again
         ticks = ax.get_xticks()
         labels = ax.get_xticklabels()
-        for t, l in zip(ticks, labels):
-            m, s = divmod(int(t), 60)
+        for _tick, _label in zip(ticks, labels):
+            m, s = divmod(int(_tick), 60)
             h, m = divmod(m, 60)
-            rs = l.get_text()
+            rs = _label.get_text()
             if len(rs) > 0:
                 if s != 0:
                     xp = time(h, m, s).strftime("%H:%M:%S")
@@ -1086,13 +1086,13 @@ def test_time_musec(self):
         # verify tick labels
         ticks = ax.get_xticks()
         labels = ax.get_xticklabels()
-        for t, l in zip(ticks, labels):
-            m, s = divmod(int(t), 60)
+        for _tick, _label in zip(ticks, labels):
+            m, s = divmod(int(_tick), 60)
 
-            us = round((t - int(t)) * 1e6)
+            us = round((_tick - int(_tick)) * 1e6)
 
             h, m = divmod(m, 60)
-            rs = l.get_text()
+            rs = _label.get_text()
             if len(rs) > 0:
                 if (us % 1000) != 0:
                     xp = time(h, m, s, us).strftime("%H:%M:%S.%f")

pandas/util/_doctools.py

@@ -77,9 +77,9 @@ def plot(self, left, right, labels: Iterable[str] = (), vertical: bool = True):
             # left
             max_left_cols = max(self._shape(df)[1] for df in left)
             max_left_rows = max(self._shape(df)[0] for df in left)
-            for i, (l, label) in enumerate(zip(left, labels)):
+            for i, (_left, _label) in enumerate(zip(left, labels)):
                 ax = fig.add_subplot(gs[i, 0:max_left_cols])
-                self._make_table(ax, l, title=label, height=1.0 / max_left_rows)
+                self._make_table(ax, _left, title=_label, height=1.0 / max_left_rows)
             # right
             ax = plt.subplot(gs[:, max_left_cols:])
             self._make_table(ax, right, title="Result", height=1.05 / vcells)
@@ -90,10 +90,10 @@ def plot(self, left, right, labels: Iterable[str] = (), vertical: bool = True):
             gs = gridspec.GridSpec(1, hcells)
             # left
             i = 0
-            for df, label in zip(left, labels):
+            for df, _label in zip(left, labels):
                 sp = self._shape(df)
                 ax = fig.add_subplot(gs[0, i : i + sp[1]])
-                self._make_table(ax, df, title=label, height=height)
+                self._make_table(ax, df, title=_label, height=height)
                 i += sp[1]
             # right
             ax = plt.subplot(gs[0, i:])