CLN: Update files (as per #36450) to Python 3.7+ syntax

pandas/_config/display.py

@@ -22,7 +22,7 @@ def detect_console_encoding() -> str:
     encoding = None
     try:
         encoding = sys.stdout.encoding or sys.stdin.encoding
-    except (AttributeError, IOError):
+    except (AttributeError, OSError):
         pass
 
     # try again for something better

pandas/_testing.py

@@ -1960,8 +1960,7 @@ def index_subclass_makers_generator():
         makeCategoricalIndex,
         makeMultiIndex,
     ]
-    for make_index_func in make_index_funcs:
-        yield make_index_func
+    yield from make_index_funcs
 
 
 def all_timeseries_index_generator(k=10):

pandas/_vendored/typing_extensions.py

@@ -409,7 +409,7 @@ def __repr__(self):
 
         def __getitem__(self, parameters):
             item = typing._type_check(
-                parameters, "{} accepts only single type".format(self._name)
+                parameters, f"{self._name} accepts only single type"
             )
             return _GenericAlias(self, (item,))
 
@@ -1671,7 +1671,7 @@ def __class_getitem__(cls, params):
                 params = (params,)
             if not params and cls is not Tuple:
                 raise TypeError(
-                    "Parameter list to {}[...] cannot be empty".format(cls.__qualname__)
+                    f"Parameter list to {cls.__qualname__}[...] cannot be empty"
                 )
             msg = "Parameters to generic types must be types."
             params = tuple(_type_check(p, msg) for p in params)
@@ -2113,7 +2113,7 @@ def __class_getitem__(cls, params):
             return _AnnotatedAlias(origin, metadata)
 
         def __init_subclass__(cls, *args, **kwargs):
-            raise TypeError("Cannot subclass {}.Annotated".format(cls.__module__))
+            raise TypeError(f"Cannot subclass {cls.__module__}.Annotated")
 
     def _strip_annotations(t):
         """Strips the annotations from a given type.
@@ -2195,7 +2195,7 @@ def _tree_repr(self, tree):
             else:
                 tp_repr = origin[0]._tree_repr(origin)
             metadata_reprs = ", ".join(repr(arg) for arg in metadata)
-            return "%s[%s, %s]" % (cls, tp_repr, metadata_reprs)
+            return f"{cls}[{tp_repr}, {metadata_reprs}]"
 
         def _subs_tree(self, tvars=None, args=None):  # noqa
             if self is Annotated:
@@ -2382,7 +2382,7 @@ def TypeAlias(self, parameters):
 
         It's invalid when used anywhere except as in the example above.
         """
-        raise TypeError("{} is not subscriptable".format(self))
+        raise TypeError(f"{self} is not subscriptable")
 
 
 elif sys.version_info[:2] >= (3, 7):

pandas/_version.py

@@ -74,7 +74,7 @@ def run_command(commands, args, cwd=None, verbose=False, hide_stderr=False):
                 stderr=(subprocess.PIPE if hide_stderr else None),
             )
             break
-        except EnvironmentError:
+        except OSError:
             e = sys.exc_info()[1]
             if e.errno == errno.ENOENT:
                 continue
@@ -121,7 +121,7 @@ def git_get_keywords(versionfile_abs):
     # _version.py.
     keywords = {}
     try:
-        f = open(versionfile_abs, "r")
+        f = open(versionfile_abs)
         for line in f.readlines():
             if line.strip().startswith("git_refnames ="):
                 mo = re.search(r'=\s*"(.*)"', line)
@@ -132,7 +132,7 @@ def git_get_keywords(versionfile_abs):
                 if mo:
                     keywords["full"] = mo.group(1)
         f.close()
-    except EnvironmentError:
+    except OSError:
         pass
     return keywords
 

pandas/io/clipboard/__init__.py

@@ -274,7 +274,7 @@ def copy_dev_clipboard(text):
             fo.write(text)
 
     def paste_dev_clipboard() -> str:
-        with open("/dev/clipboard", "rt") as fo:
+        with open("/dev/clipboard") as fo:
             content = fo.read()
         return content
 
@@ -521,7 +521,7 @@ def determine_clipboard():
         return init_windows_clipboard()
 
     if platform.system() == "Linux":
-        with open("/proc/version", "r") as f:
+        with open("/proc/version") as f:
             if "Microsoft" in f.read():
                 return init_wsl_clipboard()
 

pandas/io/formats/excel.py

@@ -587,8 +587,7 @@ def _format_regular_rows(self):
         else:
             coloffset = 0
 
-        for cell in self._generate_body(coloffset):
-            yield cell
+        yield from self._generate_body(coloffset)
 
     def _format_hierarchical_rows(self):
         has_aliases = isinstance(self.header, (tuple, list, np.ndarray, ABCIndex))
@@ -664,8 +663,7 @@ def _format_hierarchical_rows(self):
                         )
                     gcolidx += 1
 
-        for cell in self._generate_body(gcolidx):
-            yield cell
+        yield from self._generate_body(gcolidx)
 
     def _generate_body(self, coloffset: int):
         if self.styler is None:

pandas/io/html.py

@@ -719,7 +719,7 @@ def _build_doc(self):
                 r = r.getroot()
             except AttributeError:
                 pass
-        except (UnicodeDecodeError, IOError) as e:
+        except (UnicodeDecodeError, OSError) as e:
             # if the input is a blob of html goop
             if not is_url(self.io):
                 r = fromstring(self.io, parser=parser)

pandas/io/json/_json.py

@@ -821,7 +821,7 @@ def close(self):
         if self.should_close:
             try:
                 self.open_stream.close()
-            except (IOError, AttributeError):
+            except (OSError, AttributeError):
                 pass
         for file_handle in self.file_handles:
             file_handle.close()

pandas/io/pytables.py

@@ -364,7 +364,7 @@ def read_hdf(
 
     if isinstance(path_or_buf, HDFStore):
         if not path_or_buf.is_open:
-            raise IOError("The HDFStore must be open for reading.")
+            raise OSError("The HDFStore must be open for reading.")
 
         store = path_or_buf
         auto_close = False
@@ -693,7 +693,7 @@ def open(self, mode: str = "a", **kwargs):
 
         try:
             self._handle = tables.open_file(self._path, self._mode, **kwargs)
-        except IOError as err:  # pragma: no cover
+        except OSError as err:  # pragma: no cover
             if "can not be written" in str(err):
                 print(f"Opening {self._path} in read-only mode")
                 self._handle = tables.open_file(self._path, "r", **kwargs)
@@ -724,7 +724,7 @@ def open(self, mode: str = "a", **kwargs):
             # trying to read from a non-existent file causes an error which
             # is not part of IOError, make it one
             if self._mode == "r" and "Unable to open/create file" in str(err):
-                raise IOError(str(err)) from err
+                raise OSError(str(err)) from err
             raise
 
     def close(self):

pandas/io/stata.py

@@ -1077,7 +1077,7 @@ def close(self) -> None:
         """ close the handle if its open """
         try:
             self.path_or_buf.close()
-        except IOError:
+        except OSError:
             pass
 
     def _set_encoding(self) -> None:

pandas/plotting/_matplotlib/core.py

@@ -342,7 +342,7 @@ def _setup_subplots(self):
         valid_log = {False, True, "sym", None}
         input_log = {self.logx, self.logy, self.loglog}
         if input_log - valid_log:
-            invalid_log = next(iter((input_log - valid_log)))
+            invalid_log = next(iter(input_log - valid_log))
             raise ValueError(
                 f"Boolean, None and 'sym' are valid options, '{invalid_log}' is given."
             )

pandas/tests/arrays/categorical/test_constructors.py

@@ -277,7 +277,7 @@ def test_constructor_with_generator(self):
         # returned a scalar for a generator
 
         exp = Categorical([0, 1, 2])
-        cat = Categorical((x for x in [0, 1, 2]))
+        cat = Categorical(x for x in [0, 1, 2])
         tm.assert_categorical_equal(cat, exp)
         cat = Categorical(range(3))
         tm.assert_categorical_equal(cat, exp)

pandas/tests/arrays/integer/test_construction.py

@@ -29,7 +29,7 @@ def test_from_dtype_from_float(data):
 
     # from int / array
     expected = pd.Series(data).dropna().reset_index(drop=True)
-    dropped = np.array(data.dropna()).astype(np.dtype((dtype.type)))
+    dropped = np.array(data.dropna()).astype(np.dtype(dtype.type))
     result = pd.Series(dropped, dtype=str(dtype))
     tm.assert_series_equal(result, expected)
 

pandas/tests/extension/decimal/array.py

@@ -167,7 +167,7 @@ def _na_value(self):
 
     def _formatter(self, boxed=False):
         if boxed:
-            return "Decimal: {0}".format
+            return "Decimal: {}".format
         return repr
 
     @classmethod

pandas/tests/extension/test_categorical.py

@@ -137,7 +137,7 @@ def test_combine_add(self, data_repeated):
         s2 = pd.Series(orig_data2)
         result = s1.combine(s2, lambda x1, x2: x1 + x2)
         expected = pd.Series(
-            ([a + b for (a, b) in zip(list(orig_data1), list(orig_data2))])
+            [a + b for (a, b) in zip(list(orig_data1), list(orig_data2))]
         )
         self.assert_series_equal(result, expected)
 

pandas/tests/frame/test_constructors.py

@@ -71,7 +71,7 @@ def test_series_with_name_not_matching_column(self):
             lambda: DataFrame({}),
             lambda: DataFrame(()),
             lambda: DataFrame([]),
-            lambda: DataFrame((_ for _ in [])),
+            lambda: DataFrame(_ for _ in []),
             lambda: DataFrame(range(0)),
             lambda: DataFrame(data=None),
             lambda: DataFrame(data={}),

pandas/tests/groupby/test_groupby.py

@@ -249,8 +249,8 @@ def test_len():
 
     # issue 11016
     df = pd.DataFrame(dict(a=[np.nan] * 3, b=[1, 2, 3]))
-    assert len(df.groupby(("a"))) == 0
-    assert len(df.groupby(("b"))) == 3
+    assert len(df.groupby("a")) == 0
+    assert len(df.groupby("b")) == 3
     assert len(df.groupby(["a", "b"])) == 3
 
 

pandas/tests/groupby/test_grouping.py

@@ -739,7 +739,7 @@ def test_get_group(self):
         with pytest.raises(ValueError, match=msg):
             g.get_group("foo")
         with pytest.raises(ValueError, match=msg):
-            g.get_group(("foo"))
+            g.get_group("foo")
         msg = "must supply a same-length tuple to get_group with multiple grouping keys"
         with pytest.raises(ValueError, match=msg):
             g.get_group(("foo", "bar", "baz"))

pandas/tests/indexes/test_base.py

@@ -1360,7 +1360,7 @@ def test_get_indexer_strings_raises(self):
     def test_get_indexer_numeric_index_boolean_target(self, idx_class):
         # GH 16877
 
-        numeric_index = idx_class(RangeIndex((4)))
+        numeric_index = idx_class(RangeIndex(4))
         result = numeric_index.get_indexer([True, False, True])
         expected = np.array([-1, -1, -1], dtype=np.intp)
         tm.assert_numpy_array_equal(result, expected)

pandas/tests/indexing/test_indexing.py

@@ -745,7 +745,7 @@ def run_tests(df, rhs, right):
         # make frames multi-type & re-run tests
         for frame in [df, rhs, right]:
             frame["joe"] = frame["joe"].astype("float64")
-            frame["jolie"] = frame["jolie"].map("@{0}".format)
+            frame["jolie"] = frame["jolie"].map("@{}".format)
 
         run_tests(df, rhs, right)
 

pandas/tests/io/formats/test_format.py

@@ -648,7 +648,7 @@ def test_to_string_unicode_columns(self, float_frame):
         assert isinstance(result, str)
 
     def test_to_string_utf8_columns(self):
-        n = "\u05d0".encode("utf-8")
+        n = "\u05d0".encode()
 
         with option_context("display.max_rows", 1):
             df = DataFrame([1, 2], columns=[n])

pandas/tests/io/formats/test_to_csv.py

@@ -26,7 +26,7 @@ def test_to_csv_with_single_column(self):
 """
         with tm.ensure_clean("test.csv") as path:
             df1.to_csv(path, header=None, index=None)
-            with open(path, "r") as f:
+            with open(path) as f:
                 assert f.read() == expected1
 
         df2 = DataFrame([1, None])
@@ -36,7 +36,7 @@ def test_to_csv_with_single_column(self):
 """
         with tm.ensure_clean("test.csv") as path:
             df2.to_csv(path, header=None, index=None)
-            with open(path, "r") as f:
+            with open(path) as f:
                 assert f.read() == expected2
 
     def test_to_csv_defualt_encoding(self):
@@ -58,7 +58,7 @@ def test_to_csv_quotechar(self):
 
         with tm.ensure_clean("test.csv") as path:
             df.to_csv(path, quoting=1)  # 1=QUOTE_ALL
-            with open(path, "r") as f:
+            with open(path) as f:
                 assert f.read() == expected
 
         expected = """\
@@ -69,7 +69,7 @@ def test_to_csv_quotechar(self):
 
         with tm.ensure_clean("test.csv") as path:
             df.to_csv(path, quoting=1, quotechar="$")
-            with open(path, "r") as f:
+            with open(path) as f:
                 assert f.read() == expected
 
         with tm.ensure_clean("test.csv") as path:
@@ -86,7 +86,7 @@ def test_to_csv_doublequote(self):
 
         with tm.ensure_clean("test.csv") as path:
             df.to_csv(path, quoting=1, doublequote=True)  # QUOTE_ALL
-            with open(path, "r") as f:
+            with open(path) as f:
                 assert f.read() == expected
 
         from _csv import Error
@@ -105,7 +105,7 @@ def test_to_csv_escapechar(self):
 
         with tm.ensure_clean("test.csv") as path:  # QUOTE_ALL
             df.to_csv(path, quoting=1, doublequote=False, escapechar="\\")
-            with open(path, "r") as f:
+            with open(path) as f:
                 assert f.read() == expected
 
         df = DataFrame({"col": ["a,a", ",bb,"]})
@@ -117,7 +117,7 @@ def test_to_csv_escapechar(self):
 
         with tm.ensure_clean("test.csv") as path:
             df.to_csv(path, quoting=3, escapechar="\\")  # QUOTE_NONE
-            with open(path, "r") as f:
+            with open(path) as f:
                 assert f.read() == expected
 
     def test_csv_to_string(self):
@@ -342,7 +342,7 @@ def test_to_csv_string_array_ascii(self):
 """
         with tm.ensure_clean("str_test.csv") as path:
             df.to_csv(path, encoding="ascii")
-            with open(path, "r") as f:
+            with open(path) as f:
                 assert f.read() == expected_ascii
 
     def test_to_csv_string_array_utf8(self):
@@ -356,7 +356,7 @@ def test_to_csv_string_array_utf8(self):
 """
         with tm.ensure_clean("unicode_test.csv") as path:
             df.to_csv(path, encoding="utf-8")
-            with open(path, "r") as f:
+            with open(path) as f:
                 assert f.read() == expected_utf8
 
     def test_to_csv_string_with_lf(self):
@@ -467,7 +467,7 @@ def test_to_csv_write_to_open_file(self):
             with open(path, "w") as f:
                 f.write("manual header\n")
                 df.to_csv(f, header=None, index=None)
-            with open(path, "r") as f:
+            with open(path) as f:
                 assert f.read() == expected
 
     def test_to_csv_write_to_open_file_with_newline_py3(self):

pandas/tests/io/formats/test_to_html.py

@@ -137,7 +137,7 @@ def test_to_html_encoding(float_frame, tmp_path):
     # GH 28663
     path = tmp_path / "test.html"
     float_frame.to_html(path, encoding="gbk")
-    with open(str(path), "r", encoding="gbk") as f:
+    with open(str(path), encoding="gbk") as f:
         assert float_frame.to_html() == f.read()
 
 

pandas/tests/io/formats/test_to_latex.py

@@ -21,7 +21,7 @@ def test_to_latex_filename(self, float_frame):
         with tm.ensure_clean("test.tex") as path:
             float_frame.to_latex(path)
 
-            with open(path, "r") as f:
+            with open(path) as f:
                 assert float_frame.to_latex() == f.read()
 
         # test with utf-8 and encoding option (GH 7061)