CI: fix flake C413, C414, C416 errors (pandas-dev#29646)

Author: simonjayhawkins

.pre-commit-config.yaml

@@ -9,7 +9,7 @@ repos:
     hooks:
     -   id: flake8
         language: python_venv
-        additional_dependencies: [flake8-comprehensions]
+        additional_dependencies: [flake8-comprehensions>=3.1.0]
 -   repo: https://github.com/pre-commit/mirrors-isort
     rev: v4.3.20
     hooks:

asv_bench/benchmarks/categoricals.py

@@ -164,7 +164,7 @@ def setup(self, dtype):
         np.random.seed(1234)
         n = 5 * 10 ** 5
         sample_size = 100
-        arr = [i for i in np.random.randint(0, n // 10, size=n)]
+        arr = list(np.random.randint(0, n // 10, size=n))
         if dtype == "object":
             arr = [f"s{i:04d}" for i in arr]
         self.sample = np.random.choice(arr, sample_size)

asv_bench/benchmarks/frame_ctor.py

@@ -99,7 +99,7 @@ class FromLists:
     def setup(self):
         N = 1000
         M = 100
-        self.data = [[j for j in range(M)] for i in range(N)]
+        self.data = [list(range(M)) for i in range(N)]
 
     def time_frame_from_lists(self):
         self.df = DataFrame(self.data)

doc/source/whatsnew/v0.24.0.rst

@@ -353,7 +353,7 @@ Example:
 
     mi = pd.MultiIndex.from_product([list('AB'), list('CD'), list('EF')],
                                     names=['AB', 'CD', 'EF'])
-    df = pd.DataFrame([i for i in range(len(mi))], index=mi, columns=['N'])
+    df = pd.DataFrame(list(range(len(mi))), index=mi, columns=['N'])
     df
     df.rename_axis(index={'CD': 'New'})
 

environment.yml

@@ -18,7 +18,7 @@ dependencies:
   - black<=19.3b0
   - cpplint
   - flake8
-  - flake8-comprehensions  # used by flake8, linting of unnecessary comprehensions
+  - flake8-comprehensions>=3.1.0  # used by flake8, linting of unnecessary comprehensions
   - flake8-rst>=0.6.0,<=0.7.0  # linting of code blocks in rst files
   - isort  # check that imports are in the right order
   - mypy=0.720

pandas/core/arrays/categorical.py

@@ -1110,7 +1110,7 @@ def remove_categories(self, removals, inplace=False):
         if not is_list_like(removals):
             removals = [removals]
 
-        removal_set = set(list(removals))
+        removal_set = set(removals)
         not_included = removal_set - set(self.dtype.categories)
         new_categories = [c for c in self.dtype.categories if c not in removal_set]
 

pandas/core/arrays/sparse/scipy_sparse.py

@@ -51,7 +51,7 @@ def _get_label_to_i_dict(labels, sort_labels=False):
             """
             labels = Index(map(tuple, labels)).unique().tolist()  # squish
             if sort_labels:
-                labels = sorted(list(labels))
+                labels = sorted(labels)
             d = OrderedDict((k, i) for i, k in enumerate(labels))
             return d
 

pandas/core/frame.py

@@ -4281,7 +4281,7 @@ def set_index(
         arrays = []
         names = []
         if append:
-            names = [x for x in self.index.names]
+            names = list(self.index.names)
             if isinstance(self.index, ABCMultiIndex):
                 for i in range(self.index.nlevels):
                     arrays.append(self.index._get_level_values(i))
@@ -7268,7 +7268,7 @@ def _series_round(s, decimals):
             if isinstance(decimals, Series):
                 if not decimals.index.is_unique:
                     raise ValueError("Index of decimals must be unique")
-            new_cols = [col for col in _dict_round(self, decimals)]
+            new_cols = list(_dict_round(self, decimals))
         elif is_integer(decimals):
             # Dispatch to Series.round
             new_cols = [_series_round(v, decimals) for _, v in self.items()]

pandas/core/indexes/multi.py

@@ -368,7 +368,7 @@ def _verify_integrity(self, codes=None, levels=None):
             if not level.is_unique:
                 raise ValueError(
                     "Level values must be unique: {values} on "
-                    "level {level}".format(values=[value for value in level], level=i)
+                    "level {level}".format(values=list(level), level=i)
                 )
         if self.sortorder is not None:
             if self.sortorder > self._lexsort_depth():
@@ -1992,8 +1992,8 @@ def levshape(self):
     def __reduce__(self):
         """Necessary for making this object picklable"""
         d = dict(
-            levels=[lev for lev in self.levels],
-            codes=[level_codes for level_codes in self.codes],
+            levels=list(self.levels),
+            codes=list(self.codes),
             sortorder=self.sortorder,
             names=list(self.names),
         )

pandas/core/internals/managers.py

@@ -260,7 +260,7 @@ def get_ftypes(self):
     def __getstate__(self):
         block_values = [b.values for b in self.blocks]
         block_items = [self.items[b.mgr_locs.indexer] for b in self.blocks]
-        axes_array = [ax for ax in self.axes]
+        axes_array = list(self.axes)
 
         extra_state = {
             "0.14.1": {

pandas/core/tools/datetimes.py

@@ -857,7 +857,7 @@ def f(value):
 
     # we require at least Ymd
     required = ["year", "month", "day"]
-    req = sorted(list(set(required) - set(unit_rev.keys())))
+    req = sorted(set(required) - set(unit_rev.keys()))
     if len(req):
         raise ValueError(
             "to assemble mappings requires at least that "
@@ -866,7 +866,7 @@ def f(value):
         )
 
     # keys we don't recognize
-    excess = sorted(list(set(unit_rev.keys()) - set(_unit_map.values())))
+    excess = sorted(set(unit_rev.keys()) - set(_unit_map.values()))
     if len(excess):
         raise ValueError(
             "extra keys have been passed "

pandas/io/parsers.py

@@ -1605,7 +1605,7 @@ def ix(col):
 
         # remove index items from content and columns, don't pop in
         # loop
-        for i in reversed(sorted(to_remove)):
+        for i in sorted(to_remove, reverse=True):
             data.pop(i)
             if not self._implicit_index:
                 columns.pop(i)
@@ -1637,7 +1637,7 @@ def _get_name(icol):
 
         # remove index items from content and columns, don't pop in
         # loop
-        for c in reversed(sorted(to_remove)):
+        for c in sorted(to_remove, reverse=True):
             data.pop(c)
             col_names.remove(c)
 

pandas/io/pytables.py

@@ -1341,7 +1341,7 @@ def info(self) -> str:
             type=type(self), path=pprint_thing(self._path)
         )
         if self.is_open:
-            lkeys = sorted(list(self.keys()))
+            lkeys = sorted(self.keys())
             if len(lkeys):
                 keys = []
                 values = []

pandas/tests/api/test_api.py

@@ -13,7 +13,7 @@ def check(self, namespace, expected, ignored=None):
 
         result = sorted(f for f in dir(namespace) if not f.startswith("__"))
         if ignored is not None:
-            result = sorted(list(set(result) - set(ignored)))
+            result = sorted(set(result) - set(ignored))
 
         expected = sorted(expected)
         tm.assert_almost_equal(result, expected)

pandas/tests/frame/test_alter_axes.py

@@ -381,7 +381,7 @@ def test_set_index_custom_label_hashable_iterable(self):
         class Thing(frozenset):
             # need to stabilize repr for KeyError (due to random order in sets)
             def __repr__(self) -> str:
-                tmp = sorted(list(self))
+                tmp = sorted(self)
                 # double curly brace prints one brace in format string
                 return "frozenset({{{}}})".format(", ".join(map(repr, tmp)))
 
@@ -745,8 +745,7 @@ def test_rename_axis_mapper(self):
         # GH 19978
         mi = MultiIndex.from_product([["a", "b", "c"], [1, 2]], names=["ll", "nn"])
         df = DataFrame(
-            {"x": [i for i in range(len(mi))], "y": [i * 10 for i in range(len(mi))]},
-            index=mi,
+            {"x": list(range(len(mi))), "y": [i * 10 for i in range(len(mi))]}, index=mi
         )
 
         # Test for rename of the Index object of columns

pandas/tests/frame/test_analytics.py

@@ -1244,7 +1244,7 @@ def test_mode_dropna(self, dropna, expected):
             }
         )
 
-        result = df[sorted(list(expected.keys()))].mode(dropna=dropna)
+        result = df[sorted(expected.keys())].mode(dropna=dropna)
         expected = DataFrame(expected)
         tm.assert_frame_equal(result, expected)
 

pandas/tests/frame/test_reshape.py

@@ -699,7 +699,7 @@ def verify(df):
             for i, j in zip(rows, cols):
                 left = sorted(df.iloc[i, j].split("."))
                 right = mk_list(df.index[i]) + mk_list(df.columns[j])
-                right = sorted(list(map(cast, right)))
+                right = sorted(map(cast, right))
                 assert left == right
 
         df = DataFrame(

pandas/tests/groupby/test_function.py

@@ -1300,8 +1300,8 @@ def test_size_groupby_all_null():
         ([np.nan, 4.0, np.nan, 2.0, np.nan], [np.nan, 4.0, np.nan, 2.0, np.nan]),
         # Timestamps
         (
-            [x for x in pd.date_range("1/1/18", freq="D", periods=5)],
-            [x for x in pd.date_range("1/1/18", freq="D", periods=5)][::-1],
+            list(pd.date_range("1/1/18", freq="D", periods=5)),
+            list(pd.date_range("1/1/18", freq="D", periods=5))[::-1],
         ),
         # All NA
         ([np.nan] * 5, [np.nan] * 5),

pandas/tests/indexes/timedeltas/test_setops.py

@@ -39,7 +39,7 @@ def test_union_bug_1730(self):
         rng_b = timedelta_range("1 day", periods=4, freq="4H")
 
         result = rng_a.union(rng_b)
-        exp = TimedeltaIndex(sorted(set(list(rng_a)) | set(list(rng_b))))
+        exp = TimedeltaIndex(sorted(set(rng_a) | set(rng_b)))
         tm.assert_index_equal(result, exp)
 
     def test_union_bug_1745(self):
@@ -50,7 +50,7 @@ def test_union_bug_1745(self):
         )
 
         result = left.union(right)
-        exp = TimedeltaIndex(sorted(set(list(left)) | set(list(right))))
+        exp = TimedeltaIndex(sorted(set(left) | set(right)))
         tm.assert_index_equal(result, exp)
 
     def test_union_bug_4564(self):
@@ -59,7 +59,7 @@ def test_union_bug_4564(self):
         right = left + pd.offsets.Minute(15)
 
         result = left.union(right)
-        exp = TimedeltaIndex(sorted(set(list(left)) | set(list(right))))
+        exp = TimedeltaIndex(sorted(set(left) | set(right)))
         tm.assert_index_equal(result, exp)
 
     def test_intersection_bug_1708(self):

pandas/tests/indexing/multiindex/test_loc.py

@@ -1,5 +1,3 @@
-import itertools
-
 import numpy as np
 import pytest
 
@@ -223,17 +221,13 @@ def test_loc_getitem_int_slice(self):
         # GH 3053
         # loc should treat integer slices like label slices
 
-        index = MultiIndex.from_tuples(
-            [t for t in itertools.product([6, 7, 8], ["a", "b"])]
-        )
+        index = MultiIndex.from_product([[6, 7, 8], ["a", "b"]])
         df = DataFrame(np.random.randn(6, 6), index, index)
         result = df.loc[6:8, :]
         expected = df
         tm.assert_frame_equal(result, expected)
 
-        index = MultiIndex.from_tuples(
-            [t for t in itertools.product([10, 20, 30], ["a", "b"])]
-        )
+        index = MultiIndex.from_product([[10, 20, 30], ["a", "b"]])
         df = DataFrame(np.random.randn(6, 6), index, index)
         result = df.loc[20:30, :]
         expected = df.iloc[2:]

pandas/tests/indexing/multiindex/test_xs.py

@@ -1,5 +1,3 @@
-from itertools import product
-
 import numpy as np
 import pytest
 
@@ -159,10 +157,8 @@ def test_xs_setting_with_copy_error_multiple(four_level_index_dataframe):
 def test_xs_integer_key():
     # see gh-2107
     dates = range(20111201, 20111205)
-    ids = "abcde"
-    index = MultiIndex.from_tuples(
-        [x for x in product(dates, ids)], names=["date", "secid"]
-    )
+    ids = list("abcde")
+    index = MultiIndex.from_product([dates, ids], names=["date", "secid"])
     df = DataFrame(np.random.randn(len(index), 3), index, ["X", "Y", "Z"])
 
     result = df.xs(20111201, level="date")

pandas/tests/indexing/test_categorical.py

@@ -472,7 +472,7 @@ def test_getitem_with_listlike(self):
             [[1, 0], [0, 1]], dtype="uint8", index=[0, 1], columns=cats
         )
         dummies = pd.get_dummies(cats)
-        result = dummies[[c for c in dummies.columns]]
+        result = dummies[list(dummies.columns)]
         tm.assert_frame_equal(result, expected)
 
     def test_setitem_listlike(self):

pandas/tests/io/formats/test_to_excel.py

@@ -262,7 +262,7 @@ def test_css_to_excel_inherited(css, inherited, expected):
 @pytest.mark.parametrize(
     "input_color,output_color",
     (
-        [(name, rgb) for name, rgb in CSSToExcelConverter.NAMED_COLORS.items()]
+        list(CSSToExcelConverter.NAMED_COLORS.items())
         + [("#" + rgb, rgb) for rgb in CSSToExcelConverter.NAMED_COLORS.values()]
         + [("#F0F", "FF00FF"), ("#ABC", "AABBCC")]
     ),