⬆️ UPGRADE: Autoupdate pre-commit config

.pre-commit-config.yaml

@@ -19,14 +19,14 @@ repos:
         types_or: [python, rst, markdown]
         files: ^(pandas|doc)/
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v3.4.0
+    rev: v4.0.1
     hooks:
     -   id: debug-statements
     -   id: end-of-file-fixer
         exclude: \.txt$
     -   id: trailing-whitespace
 -   repo: https://github.com/cpplint/cpplint
-    rev: f7061b1 # the latest tag does not have the hook
+    rev: 1.5.5
     hooks:
     -   id: cpplint
         # We don't lint all C files because we don't want to lint any that are built
@@ -57,7 +57,7 @@ repos:
     hooks:
     -   id: isort
 -   repo: https://github.com/asottile/pyupgrade
-    rev: v2.12.0
+    rev: v2.18.3
     hooks:
     -   id: pyupgrade
         args: [--py37-plus]
@@ -72,7 +72,7 @@ repos:
         types: [text]  # overwrite types: [rst]
         types_or: [python, rst]
 -   repo: https://github.com/asottile/yesqa
-    rev: v1.2.2
+    rev: v1.2.3
     hooks:
     -   id: yesqa
         additional_dependencies:

doc/sphinxext/announce.py

@@ -54,7 +54,7 @@
 
 def get_authors(revision_range):
     pat = "^.*\\t(.*)$"
-    lst_release, cur_release = [r.strip() for r in revision_range.split("..")]
+    lst_release, cur_release = (r.strip() for r in revision_range.split(".."))
 
     if "|" in cur_release:
         # e.g. v1.0.1|HEAD
@@ -119,7 +119,7 @@ def get_pull_requests(repo, revision_range):
 
 
 def build_components(revision_range, heading="Contributors"):
-    lst_release, cur_release = [r.strip() for r in revision_range.split("..")]
+    lst_release, cur_release = (r.strip() for r in revision_range.split(".."))
     authors = get_authors(revision_range)
 
     return {

pandas/_config/config.py

@@ -157,7 +157,7 @@ def _describe_option(pat: str = "", _print_desc: bool = True):
     if len(keys) == 0:
         raise OptionError("No such keys(s)")
 
-    s = "\n".join([_build_option_description(k) for k in keys])
+    s = "\n".join(_build_option_description(k) for k in keys)
 
     if _print_desc:
         print(s)

pandas/core/reshape/merge.py

@@ -1475,7 +1475,7 @@ def get_join_indexers(
         for n in range(len(left_keys))
     )
     zipped = zip(*mapped)
-    llab, rlab, shape = [list(x) for x in zipped]
+    llab, rlab, shape = (list(x) for x in zipped)
 
     # get flat i8 keys from label lists
     lkey, rkey = _get_join_keys(llab, rlab, shape, sort)
@@ -1985,7 +1985,7 @@ def _get_multiindex_indexer(
         for n in range(index.nlevels)
     )
     zipped = zip(*mapped)
-    rcodes, lcodes, shape = [list(x) for x in zipped]
+    rcodes, lcodes, shape = (list(x) for x in zipped)
     if sort:
         rcodes = list(map(np.take, rcodes, index.codes))
     else:

pandas/core/reshape/tile.py

@@ -250,7 +250,7 @@ def cut(
             raise ValueError("Cannot cut empty array")
 
         rng = (nanops.nanmin(x), nanops.nanmax(x))
-        mn, mx = [mi + 0.0 for mi in rng]
+        mn, mx = (mi + 0.0 for mi in rng)
 
         if np.isinf(mn) or np.isinf(mx):
             # GH 24314

pandas/io/formats/excel.py

@@ -773,7 +773,7 @@ def _generate_body(self, coloffset: int) -> Iterable[ExcelCell]:
             series = self.df.iloc[:, colidx]
             for i, val in enumerate(series):
                 if styles is not None:
-                    css = ";".join([a + ":" + str(v) for (a, v) in styles[i, colidx]])
+                    css = ";".join(a + ":" + str(v) for (a, v) in styles[i, colidx])
                     xlstyle = self.style_converter(css)
                 yield ExcelCell(self.rowcounter + i, colidx + coloffset, val, xlstyle)
 

pandas/io/formats/latex.py

@@ -361,7 +361,7 @@ def get_result(self) -> str:
             self.bottom_separator,
             self.env_end,
         ]
-        result = "\n".join([item for item in elements if item])
+        result = "\n".join(item for item in elements if item)
         trailing_newline = "\n"
         result += trailing_newline
         return result
@@ -530,13 +530,13 @@ def env_begin(self) -> str:
             f"\\begin{{longtable}}{self._position_macro}{{{self.column_format}}}"
         )
         elements = [first_row, f"{self._caption_and_label()}"]
-        return "\n".join([item for item in elements if item])
+        return "\n".join(item for item in elements if item)
 
     def _caption_and_label(self) -> str:
         if self.caption or self.label:
             double_backslash = "\\\\"
             elements = [f"{self._caption_macro}", f"{self._label_macro}"]
-            caption_and_label = "\n".join([item for item in elements if item])
+            caption_and_label = "\n".join(item for item in elements if item)
             caption_and_label += double_backslash
             return caption_and_label
         else:
@@ -614,7 +614,7 @@ def env_begin(self) -> str:
             f"{self._label_macro}",
             f"\\begin{{tabular}}{{{self.column_format}}}",
         ]
-        return "\n".join([item for item in elements if item])
+        return "\n".join(item for item in elements if item)
 
     @property
     def bottom_separator(self) -> str:

pandas/io/html.py

@@ -627,7 +627,7 @@ def _build_xpath_expr(attrs) -> str:
     if "class_" in attrs:
         attrs["class"] = attrs.pop("class_")
 
-    s = " and ".join([f"@{k}={repr(v)}" for k, v in attrs.items()])
+    s = " and ".join(f"@{k}={repr(v)}" for k, v in attrs.items())
     return f"[{s}]"
 
 

pandas/io/pytables.py

@@ -3513,7 +3513,7 @@ def validate_version(self, where=None):
         """ are we trying to operate on an old version? """
         if where is not None:
             if self.version[0] <= 0 and self.version[1] <= 10 and self.version[2] < 1:
-                ws = incompatibility_doc % ".".join([str(x) for x in self.version])
+                ws = incompatibility_doc % ".".join(str(x) for x in self.version)
                 warnings.warn(ws, IncompatibilityWarning)
 
     def validate_min_itemsize(self, min_itemsize):

pandas/tests/generic/test_frame.py

@@ -126,7 +126,7 @@ def finalize(self, other, method=None, **kwargs):
             for name in self._metadata:
                 if method == "concat":
                     value = "+".join(
-                        [getattr(o, name) for o in other.objs if getattr(o, name, None)]
+                        getattr(o, name) for o in other.objs if getattr(o, name, None)
                     )
                     object.__setattr__(self, name, value)
                 else:

pandas/tests/generic/test_series.py

@@ -130,7 +130,7 @@ def finalize(self, other, method=None, **kwargs):
             for name in self._metadata:
                 if method == "concat" and name == "filename":
                     value = "+".join(
-                        [getattr(o, name) for o in other.objs if getattr(o, name, None)]
+                        getattr(o, name) for o in other.objs if getattr(o, name, None)
                     )
                     object.__setattr__(self, name, value)
                 else:

pandas/tests/io/parser/test_c_parser_only.py

@@ -434,10 +434,10 @@ def test_internal_null_byte(c_parser_only):
 def test_read_nrows_large(c_parser_only):
     # gh-7626 - Read only nrows of data in for large inputs (>262144b)
     parser = c_parser_only
-    header_narrow = "\t".join(["COL_HEADER_" + str(i) for i in range(10)]) + "\n"
-    data_narrow = "\t".join(["somedatasomedatasomedata1" for _ in range(10)]) + "\n"
-    header_wide = "\t".join(["COL_HEADER_" + str(i) for i in range(15)]) + "\n"
-    data_wide = "\t".join(["somedatasomedatasomedata2" for _ in range(15)]) + "\n"
+    header_narrow = "\t".join("COL_HEADER_" + str(i) for i in range(10)) + "\n"
+    data_narrow = "\t".join("somedatasomedatasomedata1" for _ in range(10)) + "\n"
+    header_wide = "\t".join("COL_HEADER_" + str(i) for i in range(15)) + "\n"
+    data_wide = "\t".join("somedatasomedatasomedata2" for _ in range(15)) + "\n"
     test_input = header_narrow + data_narrow * 1050 + header_wide + data_wide * 2
 
     df = parser.read_csv(StringIO(test_input), sep="\t", nrows=1010)
@@ -565,7 +565,7 @@ def test_bytes_exceed_2gb(c_parser_only):
     if parser.low_memory:
         pytest.skip("not a high_memory test")
 
-    csv = StringIO("strings\n" + "\n".join(["x" * (1 << 20) for _ in range(2100)]))
+    csv = StringIO("strings\n" + "\n".join("x" * (1 << 20) for _ in range(2100)))
     df = parser.read_csv(csv)
     assert not df.empty
 

pandas/tests/io/parser/test_multi_thread.py

@@ -44,7 +44,7 @@ def test_multi_thread_string_io_read_csv(all_parsers):
     num_files = 100
 
     bytes_to_df = [
-        "\n".join([f"{i:d},{i:d},{i:d}" for i in range(max_row_range)]).encode()
+        "\n".join(f"{i:d},{i:d},{i:d}" for i in range(max_row_range)).encode()
         for _ in range(num_files)
     ]
 

pandas/tests/io/parser/test_skiprows.py

@@ -49,10 +49,10 @@ def test_deep_skip_rows(all_parsers):
     # see gh-4382
     parser = all_parsers
     data = "a,b,c\n" + "\n".join(
-        [",".join([str(i), str(i + 1), str(i + 2)]) for i in range(10)]
+        ",".join([str(i), str(i + 1), str(i + 2)]) for i in range(10)
     )
     condensed_data = "a,b,c\n" + "\n".join(
-        [",".join([str(i), str(i + 1), str(i + 2)]) for i in [0, 1, 2, 3, 4, 6, 8, 9]]
+        ",".join([str(i), str(i + 1), str(i + 2)]) for i in [0, 1, 2, 3, 4, 6, 8, 9]
     )
 
     result = parser.read_csv(StringIO(data), skiprows=[6, 8])

pandas/tests/reshape/test_util.py

@@ -22,7 +22,7 @@ def test_datetimeindex(self):
         # regression test for GitHub issue #6439
         # make sure that the ordering on datetimeindex is consistent
         x = date_range("2000-01-01", periods=2)
-        result1, result2 = [Index(y).day for y in cartesian_product([x, x])]
+        result1, result2 = (Index(y).day for y in cartesian_product([x, x]))
         expected1 = Index([1, 1, 2, 2])
         expected2 = Index([1, 2, 1, 2])
         tm.assert_index_equal(result1, expected1)

pandas/util/_decorators.py

@@ -245,7 +245,7 @@ def _format_argument_list(allow_args: list[str]):
         return f" except for the argument '{allow_args[0]}'"
     else:
         last = allow_args[-1]
-        args = ", ".join(["'" + x + "'" for x in allow_args[:-1]])
+        args = ", ".join("'" + x + "'" for x in allow_args[:-1])
         return f" except for the arguments {args} and '{last}'"
 
 
@@ -385,12 +385,10 @@ def decorator(decorated: F) -> F:
 
         # formatting templates and concatenating docstring
         decorated.__doc__ = "".join(
-            [
-                component.format(**params)
-                if isinstance(component, str)
-                else dedent(component.__doc__ or "")
-                for component in docstring_components
-            ]
+            component.format(**params)
+            if isinstance(component, str)
+            else dedent(component.__doc__ or "")
+            for component in docstring_components
         )
 
         # error: "F" has no attribute "_docstring_components"