Fix style issues in 2.0 feature branch (rapidsai#14918)

This PR fixes all style issues in pandas-2.0 feature branch

.github/workflows/pr.yaml

@@ -196,4 +196,3 @@ jobs:
   #            repo: context.repo.repo,
   #            body: `${summary_comment}\n\nHere is [a link to the full test summary](${summary_url}).\n`
   #          })
-

python/cudf/cudf/_lib/column.pyx

@@ -12,7 +12,6 @@ import rmm
 import cudf
 import cudf._lib as libcudf
 from cudf._lib import pylibcudf
-from cudf.api.types import _is_categorical_dtype, _is_datetime64tz_dtype
 from cudf.core.buffer import (
     Buffer,
     ExposureTrackedBuffer,

python/cudf/cudf/api/types.py

@@ -12,9 +12,10 @@
 
 import cupy as cp
 import numpy as np
+import pandas as pd
+from pandas.api import types as pd_types
 
 import cudf
-import pandas as pd
 from cudf.core._compat import PANDAS_GE_150
 from cudf.core.dtypes import (  # noqa: F401
     _BaseDtype,
@@ -30,7 +31,6 @@
     is_list_dtype,
     is_struct_dtype,
 )
-from pandas.api import types as pd_types
 
 
 def is_numeric_dtype(obj):

python/cudf/cudf/core/column/datetime.py

@@ -28,7 +28,6 @@
     is_scalar,
     is_timedelta64_dtype,
 )
-
 from cudf.core._compat import PANDAS_GE_200, PANDAS_GE_220
 from cudf.core.buffer import Buffer, cuda_array_interface_wrapper
 from cudf.core.column import ColumnBase, as_column, column, string

python/cudf/cudf/core/column/interval.py

@@ -1,11 +1,10 @@
 # Copyright (c) 2018-2024, NVIDIA CORPORATION.
 from typing import Optional
 
-import pyarrow as pa
 import pandas as pd
+import pyarrow as pa
 
 import cudf
-
 from cudf.api.types import _is_interval_dtype
 from cudf.core.column import StructColumn
 from cudf.core.dtypes import CategoricalDtype, IntervalDtype

python/cudf/cudf/core/column/timedelta.py

@@ -14,12 +14,11 @@
 from cudf import _lib as libcudf
 from cudf._typing import ColumnBinaryOperand, DatetimeLikeScalar, Dtype
 from cudf.api.types import is_scalar, is_timedelta64_dtype
+from cudf.core._compat import PANDAS_GE_200
 from cudf.core.buffer import Buffer, acquire_spill_lock
 from cudf.core.column import ColumnBase, column, string
 from cudf.utils.dtypes import np_to_pa_dtype
 from cudf.utils.utils import _all_bools_with_nulls
-from cudf.core._compat import PANDAS_GE_200
-
 
 _dtype_to_format_conversion = {
     "timedelta64[ns]": "%D days %H:%M:%S",

python/cudf/cudf/core/dataframe.py

@@ -6099,7 +6099,6 @@ def _reduce(
         numeric_only=False,
         **kwargs,
     ):
-
         source = self
 
         if axis is None:

python/cudf/cudf/core/dtypes.py

@@ -9,21 +9,21 @@
 from typing import Any, Callable, Dict, List, Tuple, Type, Union
 
 import numpy as np
+import pandas as pd
 import pyarrow as pa
+from pandas.api import types as pd_types
+from pandas.api.extensions import ExtensionDtype
+from pandas.core.dtypes.dtypes import (
+    CategoricalDtype as pd_CategoricalDtype,
+    CategoricalDtypeType as pd_CategoricalDtypeType,
+)
 
 import cudf
-import pandas as pd
 from cudf._typing import Dtype
 from cudf.core._compat import PANDAS_GE_150
 from cudf.core.abc import Serializable
 from cudf.core.buffer import Buffer
 from cudf.utils.docutils import doc_apply
-from pandas.api import types as pd_types
-from pandas.api.extensions import ExtensionDtype
-from pandas.core.dtypes.dtypes import (
-    CategoricalDtype as pd_CategoricalDtype,
-    CategoricalDtypeType as pd_CategoricalDtypeType,
-)
 
 if PANDAS_GE_150:
     from pandas.core.arrays.arrow.extension_types import ArrowIntervalType

python/cudf/cudf/core/multiindex.py

@@ -34,8 +34,8 @@
 )
 from cudf.core.join._join_helpers import _match_join_keys
 from cudf.utils.dtypes import is_column_like
-from cudf.utils.utils import NotIterable, _external_only_api, _is_same_name
 from cudf.utils.nvtx_annotation import _cudf_nvtx_annotate
+from cudf.utils.utils import NotIterable, _external_only_api, _is_same_name
 
 
 def _maybe_indices_to_slice(indices: cp.ndarray) -> Union[slice, cp.ndarray]:
@@ -726,7 +726,11 @@ def _compute_validity_mask(self, index, row_tuple, max_length):
                 [
                     frame,
                     cudf.DataFrame(
-                        {"idx": cudf.Series(column.as_column(range(len(frame))))}
+                        {
+                            "idx": cudf.Series(
+                                column.as_column(range(len(frame)))
+                            )
+                        }
                     ),
                 ],
                 axis=1,

python/cudf/cudf/testing/testing.py

@@ -4,9 +4,9 @@
 
 import cupy as cp
 import numpy as np
+import pandas as pd
 
 import cudf
-import pandas as pd
 from cudf._lib.unary import is_nan
 from cudf.api.types import (
     _is_categorical_dtype,

python/cudf/cudf/tests/test_api_types.py

@@ -6,9 +6,8 @@
 from pandas.api import types as pd_types
 
 import cudf
-from cudf.core._compat import PANDAS_GE_200, PANDAS_GE_210, PANDAS_GE_214
 from cudf.api import types
-
+from cudf.core._compat import PANDAS_GE_200, PANDAS_GE_210, PANDAS_GE_214
 from cudf.testing._utils import expect_warning_if
 
 

python/cudf/cudf/tests/test_applymap.py

@@ -3,8 +3,8 @@
 import pytest
 
 from cudf import NA, DataFrame
-from cudf.testing import _utils as utils
 from cudf.core._compat import PANDAS_GE_210
+from cudf.testing import _utils as utils
 
 
 @pytest.mark.parametrize(

python/cudf/cudf/tests/test_array_function.py

@@ -1,4 +1,5 @@
-# Copyright (c) 2018-2023, NVIDIA CORPORATION.
+# Copyright (c) 2018-2024, NVIDIA CORPORATION.
+
 import numpy as np
 import pandas as pd
 import pytest

python/cudf/cudf/tests/test_categorical.py

@@ -346,7 +346,6 @@ def test_categorical_set_categories_preserves_order():
 
 
 def test_categorical_as_ordered(pd_str_cat):
-
     pd_sr = pd.Series(pd_str_cat.copy().set_ordered(False))
     cd_sr = cudf.Series(pd_str_cat.copy().set_ordered(False))
 
@@ -362,7 +361,6 @@ def test_categorical_as_ordered(pd_str_cat):
 
 
 def test_categorical_as_unordered(pd_str_cat):
-
     pd_sr = pd.Series(pd_str_cat.copy().set_ordered(True))
     cd_sr = cudf.Series(pd_str_cat.copy().set_ordered(True))
 
@@ -380,7 +378,6 @@ def test_categorical_as_unordered(pd_str_cat):
 @pytest.mark.parametrize("from_ordered", [True, False])
 @pytest.mark.parametrize("to_ordered", [True, False])
 def test_categorical_reorder_categories(pd_str_cat, from_ordered, to_ordered):
-
     pd_sr = pd.Series(pd_str_cat.copy().set_ordered(from_ordered))
     cd_sr = cudf.Series(pd_str_cat.copy().set_ordered(from_ordered))
 
@@ -401,7 +398,6 @@ def test_categorical_reorder_categories(pd_str_cat, from_ordered, to_ordered):
 
 
 def test_categorical_add_categories(pd_str_cat):
-
     pd_sr = pd.Series(pd_str_cat.copy())
     cd_sr = cudf.Series(pd_str_cat.copy())
 
@@ -419,7 +415,6 @@ def test_categorical_add_categories(pd_str_cat):
 
 
 def test_categorical_remove_categories(pd_str_cat):
-
     pd_sr = pd.Series(pd_str_cat.copy())
     cd_sr = cudf.Series(pd_str_cat.copy())
 

python/cudf/cudf/tests/test_column_accessor.py

@@ -5,9 +5,9 @@
 import pytest
 
 import cudf
+from cudf.core._compat import PANDAS_GE_200
 from cudf.core.column_accessor import ColumnAccessor
 from cudf.testing._utils import assert_eq
-from cudf.core._compat import PANDAS_GE_200
 
 simple_test_data = [
     {},

python/cudf/cudf/tests/test_concat.py

@@ -1,17 +1,16 @@
 # Copyright (c) 2018-2024, NVIDIA CORPORATION.
 
+import warnings
+from contextlib import contextmanager
 from decimal import Decimal
 
-import warnings
 import numpy as np
 import pandas as pd
 import pytest
 
-from contextlib import contextmanager
-
 import cudf as gd
 from cudf.api.types import _is_categorical_dtype
-from cudf.core._compat import PANDAS_GE_150, PANDAS_LT_140, PANDAS_GE_200
+from cudf.core._compat import PANDAS_GE_150, PANDAS_GE_200, PANDAS_LT_140
 from cudf.core.dtypes import Decimal32Dtype, Decimal64Dtype, Decimal128Dtype
 from cudf.testing._utils import (
     assert_eq,

python/cudf/cudf/tests/test_csv.py

@@ -17,7 +17,7 @@
 
 import cudf
 from cudf import read_csv
-from cudf.core._compat import PANDAS_LT_140, PANDAS_GE_200
+from cudf.core._compat import PANDAS_GE_200, PANDAS_LT_140
 from cudf.testing._utils import assert_eq, assert_exceptions_equal
 
 

python/cudf/cudf/tests/test_datasets.py

@@ -1,4 +1,4 @@
-# Copyright (c) 2019-2022, NVIDIA CORPORATION.
+# Copyright (c) 2019-2024, NVIDIA CORPORATION.
 
 import numpy as np
 

python/cudf/cudf/tests/test_datetime.py

@@ -2,6 +2,7 @@
 
 import datetime
 import operator
+import warnings
 
 import cupy as cp
 import numpy as np
@@ -10,15 +11,14 @@
 import pytest
 
 import cudf
-import warnings
 import cudf.testing.dataset_generator as dataset_generator
 from cudf import DataFrame, Series
 from cudf.core._compat import (
-    PANDAS_GE_150,
-    PANDAS_LT_140,
     PANDAS_EQ_200,
+    PANDAS_GE_150,
     PANDAS_GE_200,
     PANDAS_GE_210,
+    PANDAS_LT_140,
 )
 from cudf.core.index import DatetimeIndex
 from cudf.testing._utils import (
@@ -623,22 +623,13 @@ def test_datetime_dataframe():
 @pytest.mark.parametrize("dayfirst", [True, False])
 def test_cudf_to_datetime(data, dayfirst):
     pd_data = data
-    is_string_data = False
     if isinstance(pd_data, (pd.Series, pd.DataFrame, pd.Index)):
         gd_data = cudf.from_pandas(pd_data)
-        is_string_data = (
-            gd_data.ndim == 1
-            and not gd_data.empty
-            and gd_data.dtype.kind == "O"
-        )
     else:
         if type(pd_data).__module__ == np.__name__:
             gd_data = cp.array(pd_data)
         else:
             gd_data = pd_data
-            is_string_data = isinstance(gd_data, list) and isinstance(
-                next(iter(gd_data), None), str
-            )
 
     expected = pd.to_datetime(pd_data, dayfirst=dayfirst)
     actual = cudf.to_datetime(gd_data, dayfirst=dayfirst)
@@ -696,7 +687,6 @@ def test_to_datetime_errors(data):
 
 
 def test_to_datetime_not_implemented():
-
     with pytest.raises(NotImplementedError):
         cudf.to_datetime([], exact=False)
 
@@ -817,7 +807,6 @@ def test_to_datetime_different_formats_notimplemented():
 
 
 def test_datetime_can_cast_safely():
-
     sr = cudf.Series(
         ["1679-01-01", "2000-01-31", "2261-01-01"], dtype="datetime64[ms]"
     )
@@ -938,7 +927,6 @@ def test_str_to_datetime_error():
 @pytest.mark.parametrize("data_dtype", DATETIME_TYPES)
 @pytest.mark.parametrize("other_dtype", DATETIME_TYPES)
 def test_datetime_subtract(data, other, data_dtype, other_dtype):
-
     gsr = cudf.Series(data, dtype=data_dtype)
     psr = gsr.to_pandas()
 
@@ -1580,7 +1568,8 @@ def test_date_range_start_end_freq(request, start, end, freq):
     request.applymarker(
         pytest.mark.xfail(
             condition=(
-                not PANDAS_GE_200 and isinstance(freq, dict)
+                not PANDAS_GE_200
+                and isinstance(freq, dict)
                 and freq.get("hours", None) == 10
                 and freq.get("days", None) == 57
                 and freq.get("nanoseconds", None) == 3
@@ -1634,7 +1623,8 @@ def test_date_range_start_freq_periods(request, start, freq, periods):
     request.applymarker(
         pytest.mark.xfail(
             condition=(
-                not PANDAS_GE_200 and isinstance(freq, dict)
+                not PANDAS_GE_200
+                and isinstance(freq, dict)
                 and freq.get("hours", None) == 10
                 and freq.get("days", None) == 57
                 and freq.get("nanoseconds", None) == 3

python/cudf/cudf/tests/test_dropna.py

@@ -21,7 +21,6 @@
 @pytest.mark.parametrize("nulls", ["one", "some", "all", "none"])
 @pytest.mark.parametrize("inplace", [True, False])
 def test_dropna_series(data, nulls, inplace):
-
     psr = pd.Series(data)
 
     if len(data) > 0:

python/cudf/cudf/tests/test_duplicates.py

@@ -9,10 +9,7 @@
 
 import cudf
 from cudf import concat
-from cudf.testing._utils import (
-    assert_eq,
-    assert_exceptions_equal,
-)
+from cudf.testing._utils import assert_eq, assert_exceptions_equal
 
 # TODO: PANDAS 1.0 support
 # Revisit drop_duplicates() tests to update parameters like ignore_index.

python/cudf/cudf/tests/test_groupby.py

@@ -22,9 +22,9 @@
 from cudf.api.extensions import no_default
 from cudf.core._compat import (
     PANDAS_GE_150,
-    PANDAS_LT_140,
     PANDAS_GE_200,
     PANDAS_GE_210,
+    PANDAS_LT_140,
 )
 from cudf.core.udf._ops import arith_ops, comparison_ops, unary_ops
 from cudf.core.udf.groupby_typing import SUPPORTED_GROUPBY_NUMPY_TYPES

python/cudf/cudf/tests/test_monotonic.py

@@ -10,11 +10,7 @@
 
 import cudf
 from cudf import Index, MultiIndex, Series
-from cudf.core.index import (
-    CategoricalIndex,
-    DatetimeIndex,
-    RangeIndex,
-)
+from cudf.core.index import CategoricalIndex, DatetimeIndex, RangeIndex
 from cudf.testing._utils import assert_eq
 
 
@@ -46,7 +42,6 @@ def test_range_index(testrange):
     ],
 )
 def test_generic_index(testlist):
-
     index = Index(testlist)
     index_pd = pd.Index(testlist)