⬆️ UPGRADE: Autoupdate pre-commit config (#42151)

* ⬆️ UPGRADE: Autoupdate pre-commit config

* fixup new codespell error

Co-authored-by: jreback <[email protected]>
Co-authored-by: MarcoGorelli <[email protected]>

Author: 3 people

.pre-commit-config.yaml

@@ -9,11 +9,11 @@ repos:
     -   id: absolufy-imports
         files: ^pandas/
 -   repo: https://github.com/python/black
-    rev: 21.5b2
+    rev: 21.6b0
     hooks:
     -   id: black
 -   repo: https://github.com/codespell-project/codespell
-    rev: v2.0.0
+    rev: v2.1.0
     hooks:
     -   id: codespell
         types_or: [python, rst, markdown]
@@ -53,16 +53,16 @@ repos:
         types: [text]
         args: [--append-config=flake8/cython-template.cfg]
 -   repo: https://github.com/PyCQA/isort
-    rev: 5.8.0
+    rev: 5.9.0
     hooks:
     -   id: isort
 -   repo: https://github.com/asottile/pyupgrade
-    rev: v2.18.3
+    rev: v2.19.4
     hooks:
     -   id: pyupgrade
         args: [--py37-plus]
 -   repo: https://github.com/pre-commit/pygrep-hooks
-    rev: v1.8.0
+    rev: v1.9.0
     hooks:
       - id: rst-backticks
       - id: rst-directive-colons

pandas/core/arrays/sparse/array.py

@@ -1448,7 +1448,7 @@ def __array_ufunc__(self, ufunc: np.ufunc, method: str, *inputs, **kwargs):
                 sp_values, self.sp_index, SparseDtype(sp_values.dtype, fill_value)
             )
 
-        result = getattr(ufunc, method)(*[np.asarray(x) for x in inputs], **kwargs)
+        result = getattr(ufunc, method)(*(np.asarray(x) for x in inputs), **kwargs)
         if out:
             if len(out) == 1:
                 out = out[0]

pandas/core/arrays/sparse/scipy_sparse.py

@@ -58,7 +58,7 @@ def _get_label_to_i_dict(labels, sort_labels=False):
             return {k: i for i, k in enumerate(labels)}
 
         def _get_index_subset_to_coord_dict(index, subset, sort_labels=False):
-            ilabels = list(zip(*[index._get_level_values(i) for i in subset]))
+            ilabels = list(zip(*(index._get_level_values(i) for i in subset)))
             labels_to_i = _get_label_to_i_dict(ilabels, sort_labels=sort_labels)
             labels_to_i = Series(labels_to_i)
             if len(subset) > 1:

pandas/core/missing.py

@@ -398,7 +398,7 @@ def interpolate_1d(
         # preserve NaNs on the inside
         preserve_nans |= mid_nans
 
-    # sort preserve_nans and covert to list
+    # sort preserve_nans and convert to list
     preserve_nans = sorted(preserve_nans)
 
     result = yvalues.copy()

pandas/core/reshape/melt.py

@@ -227,7 +227,7 @@ def lreshape(data: DataFrame, groups, dropna: bool = True, label=None) -> DataFr
     else:
         keys, values = zip(*groups)
 
-    all_cols = list(set.union(*[set(x) for x in values]))
+    all_cols = list(set.union(*(set(x) for x in values)))
     id_cols = list(data.columns.difference(all_cols))
 
     K = len(values[0])

pandas/io/formats/format.py

@@ -861,7 +861,7 @@ def space_format(x, y):
                 return y
 
             str_columns = list(
-                zip(*[[space_format(x, y) for y in x] for x in fmt_columns])
+                zip(*([space_format(x, y) for y in x] for x in fmt_columns))
             )
             if self.sparsify and len(str_columns):
                 str_columns = sparsify_labels(str_columns)

pandas/io/sql.py

@@ -963,7 +963,7 @@ def insert(self, chunksize: int | None = None, method: str | None = None):
                 if start_i >= end_i:
                     break
 
-                chunk_iter = zip(*[arr[start_i:end_i] for arr in data_list])
+                chunk_iter = zip(*(arr[start_i:end_i] for arr in data_list))
                 exec_insert(conn, keys, chunk_iter)
 
     def _query_iterator(

pandas/tests/frame/methods/test_describe.py

@@ -346,7 +346,7 @@ def test_describe_percentiles_integer_idx(self):
         result = df.describe(percentiles=pct)
 
         expected = DataFrame(
-            {"x": [1.0, 1.0, np.NaN, 1.0, *[1.0 for _ in pct], 1.0]},
+            {"x": [1.0, 1.0, np.NaN, 1.0, *(1.0 for _ in pct), 1.0]},
             index=[
                 "count",
                 "mean",

pandas/tests/frame/test_arithmetic.py

@@ -763,7 +763,7 @@ def test_df_arith_2d_array_collike_broadcasts(self, all_arithmetic_operators):
         if opname in ["__rmod__", "__rfloordiv__"]:
             # Series ops may return mixed int/float dtypes in cases where
             #   DataFrame op will return all-float.  So we upcast `expected`
-            dtype = np.common_type(*[x.values for x in exvals.values()])
+            dtype = np.common_type(*(x.values for x in exvals.values()))
 
         expected = DataFrame(exvals, columns=df.columns, index=df.index, dtype=dtype)
 

pandas/tests/indexing/test_categorical.py

@@ -485,17 +485,17 @@ def test_loc_and_at_with_categorical_index(self):
             [1.5, 2.5, 3.5],
             [-1.5, -2.5, -3.5],
             # numpy int/uint
-            *[np.array([1, 2, 3], dtype=dtype) for dtype in tm.ALL_INT_DTYPES],
+            *(np.array([1, 2, 3], dtype=dtype) for dtype in tm.ALL_INT_DTYPES),
             # numpy floats
-            *[np.array([1.5, 2.5, 3.5], dtype=dtyp) for dtyp in tm.FLOAT_DTYPES],
+            *(np.array([1.5, 2.5, 3.5], dtype=dtyp) for dtyp in tm.FLOAT_DTYPES),
             # numpy object
             np.array([1, "b", 3.5], dtype=object),
             # pandas scalars
             [Interval(1, 4), Interval(4, 6), Interval(6, 9)],
             [Timestamp(2019, 1, 1), Timestamp(2019, 2, 1), Timestamp(2019, 3, 1)],
             [Timedelta(1, "d"), Timedelta(2, "d"), Timedelta(3, "D")],
             # pandas Integer arrays
-            *[pd.array([1, 2, 3], dtype=dtype) for dtype in tm.ALL_EA_INT_DTYPES],
+            *(pd.array([1, 2, 3], dtype=dtype) for dtype in tm.ALL_EA_INT_DTYPES),
             # other pandas arrays
             pd.IntervalIndex.from_breaks([1, 4, 6, 9]).array,
             pd.date_range("2019-01-01", periods=3).array,