CI, CLN remove unnecessary noqa statements, add CI check

.pre-commit-config.yaml

@@ -43,3 +43,7 @@ repos:
         entry: python -m scripts.generate_pip_deps_from_conda
         files: ^(environment.yml|requirements-dev.txt)$
         pass_filenames: false
+-   repo: https://github.com/asottile/yesqa
+    rev: v1.2.2
+    hooks:
+    -   id: yesqa

asv_bench/benchmarks/pandas_vb_common.py

@@ -15,7 +15,7 @@
 
 # Compatibility import for the testing module
 try:
-    import pandas._testing as tm  # noqa
+    import pandas._testing as tm
 except ImportError:
     import pandas.util.testing as tm  # noqa
 

asv_bench/benchmarks/tslibs/offsets.py

@@ -9,7 +9,7 @@
 from pandas import offsets
 
 try:
-    import pandas.tseries.holiday  # noqa
+    import pandas.tseries.holiday
 except ImportError:
     pass
 

doc/source/conf.py

@@ -146,7 +146,7 @@
 # built documents.
 #
 # The short X.Y version.
-import pandas  # noqa: E402 isort:skip
+import pandas  # isort:skip
 
 # version = '%s r%s' % (pandas.__version__, svn_version())
 version = str(pandas.__version__)
@@ -441,14 +441,14 @@
 # Add custom Documenter to handle attributes/methods of an AccessorProperty
 # eg pandas.Series.str and pandas.Series.dt (see GH9322)
 
-import sphinx  # noqa: E402 isort:skip
-from sphinx.util import rpartition  # noqa: E402 isort:skip
-from sphinx.ext.autodoc import (  # noqa: E402 isort:skip
+import sphinx  # isort:skip
+from sphinx.util import rpartition  # isort:skip
+from sphinx.ext.autodoc import (  # isort:skip
     AttributeDocumenter,
     Documenter,
     MethodDocumenter,
 )
-from sphinx.ext.autosummary import Autosummary  # noqa: E402 isort:skip
+from sphinx.ext.autosummary import Autosummary  # isort:skip
 
 
 class AccessorDocumenter(MethodDocumenter):

pandas/_typing.py

@@ -27,16 +27,16 @@
 # and use a string literal forward reference to it in subsequent types
 # https://mypy.readthedocs.io/en/latest/common_issues.html#import-cycles
 if TYPE_CHECKING:
-    from pandas._libs import Period, Timedelta, Timestamp  # noqa: F401
+    from pandas._libs import Period, Timedelta, Timestamp
 
-    from pandas.core.dtypes.dtypes import ExtensionDtype  # noqa: F401
+    from pandas.core.dtypes.dtypes import ExtensionDtype
 
-    from pandas import Interval  # noqa: F401
+    from pandas import Interval
     from pandas.core.arrays.base import ExtensionArray  # noqa: F401
-    from pandas.core.frame import DataFrame  # noqa: F401
+    from pandas.core.frame import DataFrame
     from pandas.core.generic import NDFrame  # noqa: F401
-    from pandas.core.indexes.base import Index  # noqa: F401
-    from pandas.core.series import Series  # noqa: F401
+    from pandas.core.indexes.base import Index
+    from pandas.core.series import Series
 
 # array-like
 

pandas/api/types/__init__.py

@@ -4,7 +4,7 @@
 
 from pandas._libs.lib import infer_dtype
 
-from pandas.core.dtypes.api import *  # noqa: F403, F401
+from pandas.core.dtypes.api import *  # noqa: F401, F403
 from pandas.core.dtypes.concat import union_categoricals
 from pandas.core.dtypes.dtypes import (
     CategoricalDtype,

pandas/conftest.py

@@ -1226,7 +1226,7 @@ def ip():
     from IPython.core.interactiveshell import InteractiveShell
 
     # GH#35711 make sure sqlite history file handle is not leaked
-    from traitlets.config import Config  # noqa: F401 isort:skip
+    from traitlets.config import Config  # isort:skip
 
     c = Config()
     c.HistoryManager.hist_file = ":memory:"

pandas/core/arrays/floating.py

@@ -34,7 +34,7 @@
 from .masked import BaseMaskedArray, BaseMaskedDtype
 
 if TYPE_CHECKING:
-    import pyarrow  # noqa: F401
+    import pyarrow
 
 
 class FloatingDtype(BaseMaskedDtype):
@@ -82,7 +82,7 @@ def __from_arrow__(
         """
         Construct FloatingArray from pyarrow Array/ChunkedArray.
         """
-        import pyarrow  # noqa: F811
+        import pyarrow
 
         from pandas.core.arrays._arrow_utils import pyarrow_array_to_numpy_and_mask
 

pandas/io/common.py

@@ -53,7 +53,7 @@
 
 
 if TYPE_CHECKING:
-    from io import IOBase  # noqa: F401
+    from io import IOBase
 
 
 def is_url(url) -> bool:

pandas/io/formats/console.py

@@ -69,7 +69,7 @@ def check_main():
         return not hasattr(main, "__file__") or get_option("mode.sim_interactive")
 
     try:
-        return __IPYTHON__ or check_main()  # noqa
+        return __IPYTHON__ or check_main()
     except NameError:
         return check_main()
 
@@ -83,7 +83,7 @@ def in_ipython_frontend():
     bool
     """
     try:
-        ip = get_ipython()  # noqa
+        ip = get_ipython()
         return "zmq" in str(type(ip)).lower()
     except NameError:
         pass

pandas/io/formats/info.py

@@ -12,7 +12,7 @@
 from pandas.io.formats.printing import pprint_thing
 
 if TYPE_CHECKING:
-    from pandas.core.series import Series  # noqa: F401
+    from pandas.core.series import Series
 
 
 def _put_str(s: Union[str, Dtype], space: int) -> str:

pandas/io/json/_table_schema.py

@@ -26,7 +26,7 @@
 import pandas.core.common as com
 
 if TYPE_CHECKING:
-    from pandas.core.indexes.multi import MultiIndex  # noqa: F401
+    from pandas.core.indexes.multi import MultiIndex
 
 loads = json.loads
 

pandas/io/pytables.py

@@ -57,7 +57,7 @@
 from pandas.io.formats.printing import adjoin, pprint_thing
 
 if TYPE_CHECKING:
-    from tables import Col, File, Node  # noqa:F401
+    from tables import Col, File, Node
 
 
 # versioning attribute

pandas/io/sas/sasreader.py

@@ -9,7 +9,7 @@
 from pandas.io.common import get_filepath_or_buffer, stringify_path
 
 if TYPE_CHECKING:
-    from pandas import DataFrame  # noqa: F401
+    from pandas import DataFrame
 
 
 # TODO(PY38): replace with Protocol in Python 3.8

pandas/plotting/_matplotlib/__init__.py

@@ -29,7 +29,7 @@
 from pandas.plotting._matplotlib.tools import table
 
 if TYPE_CHECKING:
-    from pandas.plotting._matplotlib.core import MPLPlot  # noqa: F401
+    from pandas.plotting._matplotlib.core import MPLPlot
 
 PLOT_CLASSES: Dict[str, Type["MPLPlot"]] = {
     "line": LinePlot,

pandas/plotting/_matplotlib/timeseries.py

@@ -26,7 +26,7 @@
 if TYPE_CHECKING:
     from matplotlib.axes import Axes
 
-    from pandas import Index, Series  # noqa:F401
+    from pandas import Index, Series
 
 # ---------------------------------------------------------------------
 # Plotting functions and monkey patches

pandas/plotting/_matplotlib/tools.py

@@ -17,7 +17,7 @@
 if TYPE_CHECKING:
     from matplotlib.axes import Axes
     from matplotlib.axis import Axis
-    from matplotlib.lines import Line2D  # noqa:F401
+    from matplotlib.lines import Line2D
     from matplotlib.table import Table
 
 

pandas/tests/arrays/categorical/test_constructors.py

@@ -213,7 +213,7 @@ def test_constructor(self):
         #  - when the first is an integer dtype and the second is not
         #  - when the resulting codes are all -1/NaN
         with tm.assert_produces_warning(None):
-            c_old = Categorical([0, 1, 2, 0, 1, 2], categories=["a", "b", "c"])  # noqa
+            c_old = Categorical([0, 1, 2, 0, 1, 2], categories=["a", "b", "c"])
 
         with tm.assert_produces_warning(None):
             c_old = Categorical([0, 1, 2, 0, 1, 2], categories=[3, 4, 5])  # noqa

pandas/tests/arrays/categorical/test_repr.py

@@ -320,7 +320,7 @@ def test_categorical_repr_timedelta(self):
 
         c = Categorical(idx.append(idx), categories=idx)
         exp = """[1 days, 2 days, 3 days, 4 days, 5 days, 1 days, 2 days, 3 days, 4 days, 5 days]
-Categories (5, timedelta64[ns]): [1 days, 2 days, 3 days, 4 days, 5 days]"""  # noqa
+Categories (5, timedelta64[ns]): [1 days, 2 days, 3 days, 4 days, 5 days]"""
 
         assert repr(c) == exp
 
@@ -347,13 +347,13 @@ def test_categorical_repr_timedelta_ordered(self):
         idx = timedelta_range("1 days", periods=5)
         c = Categorical(idx, ordered=True)
         exp = """[1 days, 2 days, 3 days, 4 days, 5 days]
-Categories (5, timedelta64[ns]): [1 days < 2 days < 3 days < 4 days < 5 days]"""  # noqa
+Categories (5, timedelta64[ns]): [1 days < 2 days < 3 days < 4 days < 5 days]"""
 
         assert repr(c) == exp
 
         c = Categorical(idx.append(idx), categories=idx, ordered=True)
         exp = """[1 days, 2 days, 3 days, 4 days, 5 days, 1 days, 2 days, 3 days, 4 days, 5 days]
-Categories (5, timedelta64[ns]): [1 days < 2 days < 3 days < 4 days < 5 days]"""  # noqa
+Categories (5, timedelta64[ns]): [1 days < 2 days < 3 days < 4 days < 5 days]"""
 
         assert repr(c) == exp
 

pandas/tests/arrays/sparse/test_libsparse.py

@@ -452,7 +452,7 @@ def test_check_integrity(self):
 
         # 0-length OK
         # TODO: index variables are not used...is that right?
-        index = BlockIndex(0, locs, lengths)  # noqa
+        index = BlockIndex(0, locs, lengths)
 
         # also OK even though empty
         index = BlockIndex(1, locs, lengths)  # noqa

pandas/tests/computation/test_eval.py

@@ -48,7 +48,7 @@
         )
         for engine in ENGINES
     )
-)  # noqa
+)
 def engine(request):
     return request.param
 
@@ -1885,7 +1885,7 @@ def test_global_scope(self, engine, parser):
         )
 
     def test_no_new_locals(self, engine, parser):
-        x = 1  # noqa
+        x = 1
         lcls = locals().copy()
         pd.eval("x + 1", local_dict=lcls, engine=engine, parser=parser)
         lcls2 = locals().copy()
@@ -1995,8 +1995,8 @@ def test_bool_ops_fails_on_scalars(lhs, cmp, rhs, engine, parser):
     gen = {int: lambda: np.random.randint(10), float: np.random.randn}
 
     mid = gen[lhs]()  # noqa
-    lhs = gen[lhs]()  # noqa
-    rhs = gen[rhs]()  # noqa
+    lhs = gen[lhs]()
+    rhs = gen[rhs]()
 
     ex1 = f"lhs {cmp} mid {cmp} rhs"
     ex2 = f"lhs {cmp} mid and mid {cmp} rhs"

pandas/tests/dtypes/test_inference.py

@@ -1495,7 +1495,7 @@ def test_nan_to_nat_conversions():
 
 @td.skip_if_no_scipy
 @pytest.mark.filterwarnings("ignore::PendingDeprecationWarning")
-def test_is_scipy_sparse(spmatrix):  # noqa: F811
+def test_is_scipy_sparse(spmatrix):
     assert is_scipy_sparse(spmatrix([[0, 1]]))
     assert not is_scipy_sparse(np.array([1]))
 

pandas/tests/frame/indexing/test_indexing.py

@@ -1091,7 +1091,7 @@ def test_getitem_setitem_float_labels(self):
             cp.iloc[1.0:5] = 0
 
         with pytest.raises(TypeError, match=msg):
-            result = cp.iloc[1.0:5] == 0  # noqa
+            result = cp.iloc[1.0:5] == 0
 
         assert result.values.all()
         assert (cp.iloc[0:1] == df.iloc[0:1]).values.all()

pandas/tests/frame/test_block_internals.py

@@ -78,7 +78,7 @@ def test_consolidate_inplace(self, float_frame):
     def test_values_consolidate(self, float_frame):
         float_frame["E"] = 7.0
         assert not float_frame._mgr.is_consolidated()
-        _ = float_frame.values  # noqa
+        _ = float_frame.values
         assert float_frame._mgr.is_consolidated()
 
     def test_modify_values(self, float_frame):

pandas/tests/frame/test_query_eval.py

@@ -633,9 +633,7 @@ def test_chained_cmp_and_in(self):
         res = df.query(
             "a < b < c and a not in b not in c", engine=engine, parser=parser
         )
-        ind = (
-            (df.a < df.b) & (df.b < df.c) & ~df.b.isin(df.a) & ~df.c.isin(df.b)
-        )  # noqa
+        ind = (df.a < df.b) & (df.b < df.c) & ~df.b.isin(df.a) & ~df.c.isin(df.b)
         expec = df[ind]
         tm.assert_frame_equal(res, expec)
 

pandas/tests/indexes/categorical/test_formats.py

@@ -18,7 +18,7 @@ def test_string_categorical_index_repr(self):
         expected = """CategoricalIndex(['a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a',
                   'bb', 'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a', 'bb',
                   'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc'],
-                 categories=['a', 'bb', 'ccc'], ordered=False, dtype='category')"""  # noqa
+                 categories=['a', 'bb', 'ccc'], ordered=False, dtype='category')"""
 
         assert repr(idx) == expected
 
@@ -49,7 +49,7 @@ def test_string_categorical_index_repr(self):
         expected = """CategoricalIndex(['あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ',
                   'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい',
                   'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう'],
-                 categories=['あ', 'いい', 'ううう'], ordered=False, dtype='category')"""  # noqa
+                 categories=['あ', 'いい', 'ううう'], ordered=False, dtype='category')"""
 
         assert repr(idx) == expected
 
@@ -84,7 +84,7 @@ def test_string_categorical_index_repr(self):
                   'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう',
                   'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい',
                   'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう'],
-                 categories=['あ', 'いい', 'ううう'], ordered=False, dtype='category')"""  # noqa
+                 categories=['あ', 'いい', 'ううう'], ordered=False, dtype='category')"""
 
             assert repr(idx) == expected
 

pandas/tests/indexes/multi/test_formats.py

@@ -206,5 +206,5 @@ def test_tuple_width(self, wide_multi_index):
             ('abc', 10, '2000-01-01 00:33:17', '2000-01-01 00:33:17', ...),
             ('abc', 10, '2000-01-01 00:33:18', '2000-01-01 00:33:18', ...),
             ('abc', 10, '2000-01-01 00:33:19', '2000-01-01 00:33:19', ...)],
-           names=['a', 'b', 'dti_1', 'dti_2', 'dti_3'], length=2000)"""  # noqa
+           names=['a', 'b', 'dti_1', 'dti_2', 'dti_3'], length=2000)"""
         assert result == expected

pandas/tests/indexes/multi/test_sorting.py

@@ -119,7 +119,7 @@ def test_unsortedindex():
 
 
 def test_unsortedindex_doc_examples():
-    # https://pandas.pydata.org/pandas-docs/stable/advanced.html#sorting-a-multiindex  # noqa
+    # https://pandas.pydata.org/pandas-docs/stable/advanced.html#sorting-a-multiindex
     dfm = DataFrame(
         {"jim": [0, 0, 1, 1], "joe": ["x", "x", "z", "y"], "jolie": np.random.rand(4)}
     )

pandas/tests/indexing/test_callable.py

@@ -17,11 +17,11 @@ def test_frame_loc_callable(self):
         res = df.loc[lambda x: x.A > 2]
         tm.assert_frame_equal(res, df.loc[df.A > 2])
 
-        res = df.loc[lambda x: x.A > 2]  # noqa: E231
-        tm.assert_frame_equal(res, df.loc[df.A > 2])  # noqa: E231
+        res = df.loc[lambda x: x.A > 2]
+        tm.assert_frame_equal(res, df.loc[df.A > 2])
 
-        res = df.loc[lambda x: x.A > 2]  # noqa: E231
-        tm.assert_frame_equal(res, df.loc[df.A > 2])  # noqa: E231
+        res = df.loc[lambda x: x.A > 2]
+        tm.assert_frame_equal(res, df.loc[df.A > 2])
 
         res = df.loc[lambda x: x.B == "b", :]
         tm.assert_frame_equal(res, df.loc[df.B == "b", :])
@@ -90,8 +90,8 @@ def test_frame_loc_callable_labels(self):
         res = df.loc[lambda x: ["A", "C"]]
         tm.assert_frame_equal(res, df.loc[["A", "C"]])
 
-        res = df.loc[lambda x: ["A", "C"]]  # noqa: E231
-        tm.assert_frame_equal(res, df.loc[["A", "C"]])  # noqa: E231
+        res = df.loc[lambda x: ["A", "C"]]
+        tm.assert_frame_equal(res, df.loc[["A", "C"]])
 
         res = df.loc[lambda x: ["A", "C"], :]
         tm.assert_frame_equal(res, df.loc[["A", "C"], :])

pandas/tests/io/formats/test_style.py

@@ -12,7 +12,7 @@
 import pandas._testing as tm
 
 jinja2 = pytest.importorskip("jinja2")
-from pandas.io.formats.style import Styler, _get_level_lengths  # noqa  # isort:skip
+from pandas.io.formats.style import Styler, _get_level_lengths  # isort:skip
 
 
 class TestStyler: