upgrade version of 'black'

Author: MarcoGorelli

asv_bench/benchmarks/arithmetic.py

@@ -125,7 +125,7 @@ def setup(self, op):
         arr1 = np.random.randn(n_rows, int(n_cols / 2)).astype("f8")
         arr2 = np.random.randn(n_rows, int(n_cols / 2)).astype("f4")
         df = pd.concat(
-            [pd.DataFrame(arr1), pd.DataFrame(arr2)], axis=1, ignore_index=True,
+            [pd.DataFrame(arr1), pd.DataFrame(arr2)], axis=1, ignore_index=True
         )
         # should already be the case, but just to be sure
         df._consolidate_inplace()

doc/make.py

@@ -286,7 +286,7 @@ def main():
 
     joined = ",".join(cmds)
     argparser = argparse.ArgumentParser(
-        description="pandas documentation builder", epilog=f"Commands: {joined}",
+        description="pandas documentation builder", epilog=f"Commands: {joined}"
     )
 
     joined = ", ".join(cmds)

doc/source/conf.py

@@ -308,7 +308,7 @@
 
     for method in methods:
         # ... and each of its public methods
-        moved_api_pages.append((f"{old}.{method}", f"{new}.{method}",))
+        moved_api_pages.append((f"{old}.{method}", f"{new}.{method}"))
 
 if pattern is None:
     html_additional_pages = {

pandas/_vendored/typing_extensions.py

@@ -2116,8 +2116,7 @@ def __init_subclass__(cls, *args, **kwargs):
             raise TypeError(f"Cannot subclass {cls.__module__}.Annotated")
 
     def _strip_annotations(t):
-        """Strips the annotations from a given type.
-        """
+        """Strips the annotations from a given type."""
         if isinstance(t, _AnnotatedAlias):
             return _strip_annotations(t.__origin__)
         if isinstance(t, typing._GenericAlias):

pandas/core/aggregation.py

@@ -387,7 +387,7 @@ def validate_func_kwargs(
 
 
 def transform(
-    obj: FrameOrSeries, func: AggFuncType, axis: Axis, *args, **kwargs,
+    obj: FrameOrSeries, func: AggFuncType, axis: Axis, *args, **kwargs
 ) -> FrameOrSeries:
     """
     Transform a DataFrame or Series

pandas/core/algorithms.py

@@ -1023,11 +1023,10 @@ def checked_add_with_arr(arr, b, arr_mask=None, b_mask=None):
         to_raise = ((np.iinfo(np.int64).max - b2 < arr) & not_nan).any()
     else:
         to_raise = (
-            ((np.iinfo(np.int64).max - b2[mask1] < arr[mask1]) & not_nan[mask1]).any()
-            or (
-                (np.iinfo(np.int64).min - b2[mask2] > arr[mask2]) & not_nan[mask2]
-            ).any()
-        )
+            (np.iinfo(np.int64).max - b2[mask1] < arr[mask1]) & not_nan[mask1]
+        ).any() or (
+            (np.iinfo(np.int64).min - b2[mask2] > arr[mask2]) & not_nan[mask2]
+        ).any()
 
     if to_raise:
         raise OverflowError("Overflow in int64 addition")

pandas/core/array_algos/replace.py

@@ -17,7 +17,7 @@
 
 
 def compare_or_regex_search(
-    a: ArrayLike, b: Union[Scalar, Pattern], regex: bool, mask: ArrayLike,
+    a: ArrayLike, b: Union[Scalar, Pattern], regex: bool, mask: ArrayLike
 ) -> Union[ArrayLike, bool]:
     """
     Compare two array_like inputs of the same shape or two scalar values

pandas/core/frame.py

@@ -449,9 +449,7 @@ def __init__(
         if isinstance(data, BlockManager):
             if index is None and columns is None and dtype is None and copy is False:
                 # GH#33357 fastpath
-                NDFrame.__init__(
-                    self, data,
-                )
+                NDFrame.__init__(self, data)
                 return
 
             mgr = self._init_mgr(
@@ -5747,7 +5745,7 @@ def nsmallest(self, n, columns, keep="first") -> DataFrame:
                   population    GDP alpha-2
         Tuvalu         11300     38      TV
         Anguilla       11300    311      AI
-        Iceland       337000  17036	     IS
+        Iceland       337000  17036      IS
 
         When using ``keep='last'``, ties are resolved in reverse order:
 
@@ -7142,7 +7140,7 @@ def unstack(self, level=-1, fill_value=None):
 
         return unstack(self, level, fill_value)
 
-    @Appender(_shared_docs["melt"] % dict(caller="df.melt(", other="melt",))
+    @Appender(_shared_docs["melt"] % dict(caller="df.melt(", other="melt"))
     def melt(
         self,
         id_vars=None,
@@ -8624,7 +8622,7 @@ def blk_func(values):
             # After possibly _get_data and transposing, we are now in the
             #  simple case where we can use BlockManager.reduce
             res = df._mgr.reduce(blk_func)
-            out = df._constructor(res,).iloc[0].rename(None)
+            out = df._constructor(res).iloc[0].rename(None)
             if out_dtype is not None:
                 out = out.astype(out_dtype)
             if axis == 0 and is_object_dtype(out.dtype):

pandas/core/series.py

@@ -198,7 +198,7 @@ class Series(base.IndexOpsMixin, generic.NDFrame):
     # Constructors
 
     def __init__(
-        self, data=None, index=None, dtype=None, name=None, copy=False, fastpath=False,
+        self, data=None, index=None, dtype=None, name=None, copy=False, fastpath=False
     ):
 
         if (
@@ -208,9 +208,7 @@ def __init__(
             and copy is False
         ):
             # GH#33357 called with just the SingleBlockManager
-            NDFrame.__init__(
-                self, data,
-            )
+            NDFrame.__init__(self, data)
             self.name = name
             return
 
@@ -330,7 +328,8 @@ def __init__(
                 data = SingleBlockManager.from_array(data, index)
 
         generic.NDFrame.__init__(
-            self, data,
+            self,
+            data,
         )
         self.name = name
         self._set_axis(0, index, fastpath=True)

pandas/core/sorting.py

@@ -72,7 +72,7 @@ def get_indexer_indexer(
         )
     elif isinstance(target, ABCMultiIndex):
         indexer = lexsort_indexer(
-            target._get_codes_for_sorting(), orders=ascending, na_position=na_position,
+            target._get_codes_for_sorting(), orders=ascending, na_position=na_position
         )
     else:
         # Check monotonic-ness before sort an index (GH 11080)

pandas/core/util/numba_.py

@@ -25,7 +25,7 @@ def set_use_numba(enable: bool = False) -> None:
 
 
 def get_jit_arguments(
-    engine_kwargs: Optional[Dict[str, bool]] = None, kwargs: Optional[Dict] = None,
+    engine_kwargs: Optional[Dict[str, bool]] = None, kwargs: Optional[Dict] = None
 ) -> Tuple[bool, bool, bool]:
     """
     Return arguments to pass to numba.JIT, falling back on pandas default JIT settings.

pandas/io/formats/format.py

@@ -1382,10 +1382,6 @@ def _format(x):
 
 
 class FloatArrayFormatter(GenericArrayFormatter):
-    """
-
-    """
-
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
 

pandas/io/formats/info.py

@@ -340,12 +340,29 @@ def _verbose_repr(
             if show_counts:
                 count = counts[i]
 
-            lines.append(
-                line_no
-                + _put_str(col, space)
-                + _put_str(count_temp.format(count=count), space_count)
-                + _put_str(dtype, space_dtype)
-            )
+    def _verbose_repr(
+        self, lines: List[str], ids: "Index", dtypes: "Series", show_counts: bool
+    ) -> None:
+        lines.append(f"Series name: {self.data.name}")
+
+        id_space = 2
+
+        counts = cast("Series", self.data._constructor(self.data.count()))
+        count_configs = _get_count_configs(counts, id_space, show_counts)
+
+        space_dtype, header, len_dtype = _get_header_and_spaces(
+            dtypes, count_configs.space_count, count_configs.count_header
+        )
+
+        lines.append(header)
+        lines.append(
+            _put_str("-" * count_configs.len_count, count_configs.space_count)
+            + _put_str("-" * len_dtype, space_dtype)
+        )
+
+        _display_counts_and_dtypes(
+            lines, ids, dtypes, show_counts, count_configs, space_dtype
+        )
 
     def _non_verbose_repr(self, lines: List[str], ids: "Index") -> None:
         lines.append(ids._summary(name="Columns"))

pandas/io/formats/latex.py

@@ -41,9 +41,9 @@ def __init__(
         self.multirow = multirow
         self.clinebuf: List[List[int]] = []
         self.strcols = self._get_strcols()
-        self.strrows: List[List[str]] = (
-            list(zip(*self.strcols))  # type: ignore[arg-type]
-        )
+        self.strrows: List[List[str]] = list(
+            zip(*self.strcols)
+        )  # type: ignore[arg-type]
 
     def get_strrow(self, row_num: int) -> str:
         """Get string representation of the row."""

pandas/tests/arrays/sparse/test_array.py

@@ -193,9 +193,7 @@ def test_constructor_inferred_fill_value(self, data, fill_value):
             assert result == fill_value
 
     @pytest.mark.parametrize("format", ["coo", "csc", "csr"])
-    @pytest.mark.parametrize(
-        "size", [0, 10],
-    )
+    @pytest.mark.parametrize("size", [0, 10])
     @td.skip_if_no_scipy
     def test_from_spmatrix(self, size, format):
         import scipy.sparse
@@ -696,14 +694,17 @@ def test_getslice_tuple(self):
         res = sparse[
             4:,
         ]  # noqa: E231
-        exp = SparseArray(dense[4:,])  # noqa: E231
+        exp = SparseArray(np.array([0, 5, np.nan, np.nan, 0]))
         tm.assert_sp_array_equal(res, exp)
 
         sparse = SparseArray(dense, fill_value=0)
         res = sparse[
             4:,
         ]  # noqa: E231
-        exp = SparseArray(dense[4:,], fill_value=0)  # noqa: E231
+        exp = SparseArray(
+            np.array([0, 5, np.nan, np.nan, 0]),
+            fill_value=0,
+        )  # noqa: E231
         tm.assert_sp_array_equal(res, exp)
 
         msg = "too many indices for array"

pandas/tests/frame/test_analytics.py

@@ -1060,14 +1060,14 @@ def test_any_all_bool_only(self):
             (np.any, {"A": pd.Series([0.0, 1.0], dtype="float")}, True),
             (np.all, {"A": pd.Series([0, 1], dtype=int)}, False),
             (np.any, {"A": pd.Series([0, 1], dtype=int)}, True),
-            pytest.param(np.all, {"A": pd.Series([0, 1], dtype="M8[ns]")}, False,),
-            pytest.param(np.any, {"A": pd.Series([0, 1], dtype="M8[ns]")}, True,),
-            pytest.param(np.all, {"A": pd.Series([1, 2], dtype="M8[ns]")}, True,),
-            pytest.param(np.any, {"A": pd.Series([1, 2], dtype="M8[ns]")}, True,),
-            pytest.param(np.all, {"A": pd.Series([0, 1], dtype="m8[ns]")}, False,),
-            pytest.param(np.any, {"A": pd.Series([0, 1], dtype="m8[ns]")}, True,),
-            pytest.param(np.all, {"A": pd.Series([1, 2], dtype="m8[ns]")}, True,),
-            pytest.param(np.any, {"A": pd.Series([1, 2], dtype="m8[ns]")}, True,),
+            pytest.param(np.all, {"A": pd.Series([0, 1], dtype="M8[ns]")}, False),
+            pytest.param(np.any, {"A": pd.Series([0, 1], dtype="M8[ns]")}, True),
+            pytest.param(np.all, {"A": pd.Series([1, 2], dtype="M8[ns]")}, True),
+            pytest.param(np.any, {"A": pd.Series([1, 2], dtype="M8[ns]")}, True),
+            pytest.param(np.all, {"A": pd.Series([0, 1], dtype="m8[ns]")}, False),
+            pytest.param(np.any, {"A": pd.Series([0, 1], dtype="m8[ns]")}, True),
+            pytest.param(np.all, {"A": pd.Series([1, 2], dtype="m8[ns]")}, True),
+            pytest.param(np.any, {"A": pd.Series([1, 2], dtype="m8[ns]")}, True),
             (np.all, {"A": pd.Series([0, 1], dtype="category")}, False),
             (np.any, {"A": pd.Series([0, 1], dtype="category")}, True),
             (np.all, {"A": pd.Series([1, 2], dtype="category")}, True),

pandas/tests/io/formats/test_info.py

@@ -371,6 +371,26 @@ def test_info_memory_usage_qualified():
     df.info(buf=buf)
     assert "+" in buf.getvalue()
 
+    buf = StringIO()
+    s = Series(1, index=[1, 2, 3])
+    s.info(buf=buf)
+    assert "+" not in buf.getvalue()
+
+    buf = StringIO()
+    s = Series(1, index=list("ABC"))
+    s.info(buf=buf)
+    assert "+" in buf.getvalue()
+
+    buf = StringIO()
+    s = Series(1, index=MultiIndex.from_product([range(3), range(3)]))
+    s.info(buf=buf)
+    assert "+" not in buf.getvalue()
+
+    buf = StringIO()
+    s = Series(1, index=MultiIndex.from_product([range(3), ["foo", "bar"]]))
+    s.info(buf=buf)
+    assert "+" in buf.getvalue()
+
 
 def test_info_memory_usage_bug_on_multiindex():
     # GH 14308

pandas/tests/io/test_gcs.py

@@ -109,7 +109,9 @@ def test_to_csv_compression_encoding_gcs(gcs_buffer, compression_only, encoding)
     compression["method"] = "infer"
     path_gcs += f".{compression_only}"
     df.to_csv(
-        path_gcs, compression=compression, encoding=encoding,
+        path_gcs,
+        compression=compression,
+        encoding=encoding,
     )
     assert gcs_buffer.getvalue() == buffer.getvalue()
     read_df = read_csv(path_gcs, index_col=0, compression="infer", encoding=encoding)

pandas/tests/io/test_parquet.py

@@ -572,7 +572,9 @@ def test_s3_roundtrip(self, df_compat, s3_resource, pa, s3so):
             pytest.param(
                 ["A"],
                 marks=pytest.mark.xfail(
-                    PY38, reason="Getting back empty DataFrame", raises=AssertionError,
+                    PY38,
+                    reason="Getting back empty DataFrame",
+                    raises=AssertionError,
                 ),
             ),
             [],

pandas/tests/scalar/timestamp/test_constructors.py

@@ -259,17 +259,20 @@ def test_constructor_keyword(self):
             Timestamp("20151112")
         )
 
-        assert repr(
-            Timestamp(
-                year=2015,
-                month=11,
-                day=12,
-                hour=1,
-                minute=2,
-                second=3,
-                microsecond=999999,
+        assert (
+            repr(
+                Timestamp(
+                    year=2015,
+                    month=11,
+                    day=12,
+                    hour=1,
+                    minute=2,
+                    second=3,
+                    microsecond=999999,
+                )
             )
-        ) == repr(Timestamp("2015-11-12 01:02:03.999999"))
+            == repr(Timestamp("2015-11-12 01:02:03.999999"))
+        )
 
     def test_constructor_fromordinal(self):
         base = datetime(2000, 1, 1)

pandas/tests/series/test_operators.py

@@ -555,7 +555,8 @@ def test_unary_minus_nullable_int(
         tm.assert_series_equal(result, expected)
 
     @pytest.mark.parametrize(
-        "source", [[1, 2, 3], [1, 2, None], [-1, 0, 1]],
+        "source",
+        [[1, 2, 3], [1, 2, None], [-1, 0, 1]],
     )
     def test_unary_plus_nullable_int(self, any_signed_nullable_int_dtype, source):
         dtype = any_signed_nullable_int_dtype

scripts/tests/test_validate_docstrings.py

@@ -6,8 +6,7 @@
 
 
 class BadDocstrings:
-    """Everything here has a bad docstring
-    """
+    """Everything here has a bad docstring"""
 
     def private_classes(self):
         """

versioneer.py

@@ -1073,7 +1073,8 @@ def git_pieces_from_vcs(tag_prefix, root, verbose, run_command=run_command):
                 fmt = "tag '%s' doesn't start with prefix '%s'"
                 print(fmt % (full_tag, tag_prefix))
             pieces["error"] = "tag '{}' doesn't start with prefix '{}'".format(
-                full_tag, tag_prefix,
+                full_tag,
+                tag_prefix,
             )
             return pieces
         pieces["closest-tag"] = full_tag[len(tag_prefix) :]