Standard library imports style check (#50116)

* put stdlib imports in pandas/tests at top of file

* Update .pre-commit-config.yaml

Removed ^pandas/core/generic\.py from .pre-commit-config.yaml

* requested changes from @MarcoGorelli to fix tests and revert one unrelated docstring change.

* Restore ugly docstring

Co-authored-by: Marco Edward Gorelli <[email protected]>

Author: Thextan

pandas/tests/apply/test_series_apply.py

@@ -2,6 +2,8 @@
     Counter,
     defaultdict,
 )
+from decimal import Decimal
+import math
 
 import numpy as np
 import pytest
@@ -37,8 +39,6 @@ def test_apply(datetime_series):
         tm.assert_series_equal(datetime_series.apply(np.sqrt), np.sqrt(datetime_series))
 
         # element-wise apply
-        import math
-
         tm.assert_series_equal(datetime_series.apply(math.exp), np.exp(datetime_series))
 
     # empty series
@@ -525,8 +525,6 @@ def test_map_type_inference():
 
 
 def test_map_decimal(string_series):
-    from decimal import Decimal
-
     result = string_series.map(lambda x: Decimal(str(x)))
     assert result.dtype == np.object_
     assert isinstance(result[0], Decimal)

pandas/tests/arrays/test_datetimelike.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import array
 import re
 
 import numpy as np
@@ -1346,9 +1347,6 @@ def array_likes(request):
     if name == "memoryview":
         data = memoryview(arr)
     elif name == "array":
-        # stdlib array
-        import array
-
         data = array.array("i", arr)
     elif name == "dask":
         import dask.array

pandas/tests/frame/indexing/test_indexing.py

@@ -3,6 +3,7 @@
     datetime,
     timedelta,
 )
+from decimal import Decimal
 import re
 
 import numpy as np
@@ -467,8 +468,6 @@ def test_setitem_corner2(self):
 
     def test_setitem_ambig(self):
         # Difficulties with mixed-type data
-        from decimal import Decimal
-
         # Created as float type
         dm = DataFrame(index=range(3), columns=range(3))
 

pandas/tests/frame/methods/test_to_records.py

@@ -1,4 +1,6 @@
 from collections import abc
+import email
+from email.parser import Parser
 
 import numpy as np
 import pytest
@@ -58,9 +60,6 @@ def test_to_records_with_multindex(self):
         assert "one" not in r
 
     def test_to_records_with_Mapping_type(self):
-        import email
-        from email.parser import Parser
-
         abc.Mapping.register(email.message.Message)
 
         headers = Parser().parsestr(

pandas/tests/frame/test_constructors.py

@@ -1,13 +1,18 @@
+import array
 from collections import (
     OrderedDict,
     abc,
+    defaultdict,
+    namedtuple,
 )
+from dataclasses import make_dataclass
 from datetime import (
     date,
     datetime,
     timedelta,
 )
 import functools
+import random
 import re
 from typing import Iterator
 import warnings
@@ -466,8 +471,6 @@ def test_constructor_numpy_uints(self, values):
         assert result[0][0] == value
 
     def test_constructor_ordereddict(self):
-        import random
-
         nitems = 100
         nums = list(range(nitems))
         random.shuffle(nums)
@@ -718,8 +721,6 @@ def test_constructor_subclass_dict(self, dict_subclass):
 
     def test_constructor_defaultdict(self, float_frame):
         # try with defaultdict
-        from collections import defaultdict
-
         data = {}
         float_frame.loc[: float_frame.index[10], "B"] = np.nan
 
@@ -1343,8 +1344,6 @@ def __len__(self) -> int:
     def test_constructor_stdlib_array(self):
         # GH 4297
         # support Array
-        import array
-
         result = DataFrame({"A": array.array("i", range(10))})
         expected = DataFrame({"A": list(range(10))})
         tm.assert_frame_equal(result, expected, check_dtype=False)
@@ -1544,8 +1543,6 @@ def test_constructor_list_of_tuples(self):
 
     def test_constructor_list_of_namedtuples(self):
         # GH11181
-        from collections import namedtuple
-
         named_tuple = namedtuple("Pandas", list("ab"))
         tuples = [named_tuple(1, 3), named_tuple(2, 4)]
         expected = DataFrame({"a": [1, 2], "b": [3, 4]})
@@ -1559,8 +1556,6 @@ def test_constructor_list_of_namedtuples(self):
 
     def test_constructor_list_of_dataclasses(self):
         # GH21910
-        from dataclasses import make_dataclass
-
         Point = make_dataclass("Point", [("x", int), ("y", int)])
 
         data = [Point(0, 3), Point(1, 3)]
@@ -1570,8 +1565,6 @@ def test_constructor_list_of_dataclasses(self):
 
     def test_constructor_list_of_dataclasses_with_varying_types(self):
         # GH21910
-        from dataclasses import make_dataclass
-
         # varying types
         Point = make_dataclass("Point", [("x", int), ("y", int)])
         HLine = make_dataclass("HLine", [("x0", int), ("x1", int), ("y", int)])
@@ -1586,8 +1579,6 @@ def test_constructor_list_of_dataclasses_with_varying_types(self):
 
     def test_constructor_list_of_dataclasses_error_thrown(self):
         # GH21910
-        from dataclasses import make_dataclass
-
         Point = make_dataclass("Point", [("x", int), ("y", int)])
 
         # expect TypeError

pandas/tests/groupby/test_filters.py

@@ -1,3 +1,5 @@
+from string import ascii_lowercase
+
 import numpy as np
 import pytest
 
@@ -192,8 +194,6 @@ def test_filter_against_workaround():
     tm.assert_series_equal(new_way.sort_values(), old_way.sort_values())
 
     # Set up DataFrame of ints, floats, strings.
-    from string import ascii_lowercase
-
     letters = np.array(list(ascii_lowercase))
     N = 1000
     random_letters = letters.take(np.random.randint(0, 26, N))

pandas/tests/groupby/test_grouping.py

@@ -1,4 +1,10 @@
-""" test where we are determining what we are grouping, or getting groups """
+"""
+test where we are determining what we are grouping, or getting groups
+"""
+from datetime import (
+    date,
+    timedelta,
+)
 
 import numpy as np
 import pytest
@@ -167,14 +173,8 @@ def test_grouper_index_types(self, index):
         df.groupby(list("abcde"), group_keys=False).apply(lambda x: x)
 
     def test_grouper_multilevel_freq(self):
-
         # GH 7885
         # with level and freq specified in a Grouper
-        from datetime import (
-            date,
-            timedelta,
-        )
-
         d0 = date.today() - timedelta(days=14)
         dates = date_range(d0, date.today())
         date_index = MultiIndex.from_product([dates, dates], names=["foo", "bar"])

pandas/tests/groupby/test_timegrouper.py

@@ -1,6 +1,10 @@
-""" test with the TimeGrouper / grouping with datetimes """
-
-from datetime import datetime
+"""
+test with the TimeGrouper / grouping with datetimes
+"""
+from datetime import (
+    datetime,
+    timedelta,
+)
 from io import StringIO
 
 import numpy as np
@@ -763,8 +767,6 @@ def test_first_last_max_min_on_time_data(self):
         # GH 10295
         # Verify that NaT is not in the result of max, min, first and last on
         # Dataframe with datetime or timedelta values.
-        from datetime import timedelta as td
-
         df_test = DataFrame(
             {
                 "dt": [
@@ -774,7 +776,13 @@ def test_first_last_max_min_on_time_data(self):
                     "2015-07-23 12:12",
                     np.nan,
                 ],
-                "td": [np.nan, td(days=1), td(days=2), td(days=3), np.nan],
+                "td": [
+                    np.nan,
+                    timedelta(days=1),
+                    timedelta(days=2),
+                    timedelta(days=3),
+                    np.nan,
+                ],
             }
         )
         df_test.dt = pd.to_datetime(df_test.dt)

pandas/tests/indexes/test_common.py

@@ -3,6 +3,10 @@
 any index subclass except for MultiIndex. Makes use of the `index_flat`
 fixture defined in pandas/conftest.py.
 """
+from copy import (
+    copy,
+    deepcopy,
+)
 import re
 
 import numpy as np
@@ -132,11 +136,6 @@ def test_set_name_methods(self, index_flat):
         assert index.names == [name]
 
     def test_copy_and_deepcopy(self, index_flat):
-        from copy import (
-            copy,
-            deepcopy,
-        )
-
         index = index_flat
 
         for func in (copy, deepcopy):

pandas/tests/indexing/multiindex/test_slice.py

@@ -1,3 +1,8 @@
+from datetime import (
+    datetime,
+    timedelta,
+)
+
 import numpy as np
 import pytest
 
@@ -248,12 +253,7 @@ def test_multiindex_slicers_datetimelike(self):
 
         # GH 7429
         # buggy/inconsistent behavior when slicing with datetime-like
-        import datetime
-
-        dates = [
-            datetime.datetime(2012, 1, 1, 12, 12, 12) + datetime.timedelta(days=i)
-            for i in range(6)
-        ]
+        dates = [datetime(2012, 1, 1, 12, 12, 12) + timedelta(days=i) for i in range(6)]
         freq = [1, 2]
         index = MultiIndex.from_product([dates, freq], names=["date", "frequency"])
 

pandas/tests/io/excel/test_readers.py

@@ -5,6 +5,7 @@
 from functools import partial
 import os
 from pathlib import Path
+import platform
 from urllib.error import URLError
 from zipfile import BadZipFile
 
@@ -897,8 +898,6 @@ def test_read_from_file_url(self, read_ext, datapath):
             url_table = pd.read_excel("file://localhost/" + localtable)
         except URLError:
             # fails on some systems
-            import platform
-
             platform_info = " ".join(platform.uname()).strip()
             pytest.skip(f"failing on {platform_info}")
 

pandas/tests/io/formats/test_printing.py

@@ -1,3 +1,5 @@
+import string
+
 import numpy as np
 import pytest
 
@@ -19,8 +21,6 @@ def test_adjoin():
 
 
 def test_repr_binary_type():
-    import string
-
     letters = string.ascii_letters
     try:
         raw = bytes(letters, encoding=cf.get_option("display.encoding"))

pandas/tests/io/formats/test_to_csv.py

@@ -3,6 +3,7 @@
 import sys
 from zipfile import ZipFile
 
+from _csv import Error
 import numpy as np
 import pytest
 
@@ -94,8 +95,6 @@ def test_to_csv_doublequote(self):
             with open(path) as f:
                 assert f.read() == expected
 
-        from _csv import Error
-
         with tm.ensure_clean("test.csv") as path:
             with pytest.raises(Error, match="escapechar"):
                 df.to_csv(path, doublequote=False)  # no escapechar set

pandas/tests/io/json/test_pandas.py

@@ -5,6 +5,7 @@
 import json
 import os
 import sys
+import time
 
 import numpy as np
 import pytest
@@ -1730,8 +1731,6 @@ def test_json_multiindex(self, dataframe, expected):
 
     @pytest.mark.single_cpu
     def test_to_s3(self, s3_resource, s3so):
-        import time
-
         # GH 28375
         mock_bucket_name, target_file = "pandas-test", "test.json"
         df = DataFrame({"x": [1, 2, 3], "y": [2, 4, 6]})

pandas/tests/io/parser/test_c_parser_only.py

@@ -4,7 +4,7 @@
 these tests out of this module as soon as the Python parser can accept
 further arguments when parsing.
 """
-
+from decimal import Decimal
 from io import (
     BytesIO,
     StringIO,
@@ -169,8 +169,6 @@ def test_unsupported_dtype(c_parser_only, match, kwargs):
 @td.skip_if_32bit
 @pytest.mark.slow
 def test_precise_conversion(c_parser_only):
-    from decimal import Decimal
-
     parser = c_parser_only
 
     normal_errors = []

pandas/tests/io/parser/test_encoding.py

@@ -2,7 +2,10 @@
 Tests encoding functionality during parsing
 for all of the parsers defined in parsers.py
 """
-from io import BytesIO
+from io import (
+    BytesIO,
+    TextIOWrapper,
+)
 import os
 import tempfile
 import uuid
@@ -59,8 +62,6 @@ def test_utf16_bom_skiprows(all_parsers, sep, encoding):
     utf8 = "utf-8"
 
     with tm.ensure_clean(path) as path:
-        from io import TextIOWrapper
-
         bytes_data = data.encode(encoding)
 
         with open(path, "wb") as f: