apply

.pre-commit-config.yaml

@@ -21,7 +21,7 @@ repos:
     hooks:
       - id: cython-lint
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: 'v1.10.0'
+    rev: v1.10.0
     hooks:
       - id: mypy
         additional_dependencies: [types-cachetools]
@@ -129,6 +129,7 @@ repos:
     rev: v0.4.8
     hooks:
       - id: ruff
+        args: ["--fix"]
         files: python/.*$
       - id: ruff-format
         files: python/.*$

pyproject.toml

@@ -98,15 +98,16 @@ ignore = [
     "E203",
     # line-too-long (due to Copyright header)
     "E501",
-    # [*] Import block is un-sorted or un-formatted
-    "I001",
 ]
 fixable = ["ALL"]
 exclude = [
     # TODO: Remove this in a follow-up where we fix __all__.
     "__init__.py",
 ]
 
+[tool.ruff.lint.isort]
+known-first-party = ["cudf*", "dask_cudf", "custreamz"]
+
 [tool.ruff.lint.per-file-ignores]
 # Lots of pytest implicitly injected attributes in conftest-patch.py
 "python/cudf/cudf/pandas/scripts/conftest-patch.py" = ["F821"]

python/cudf/cudf/core/_internals/expressions.py

@@ -5,7 +5,6 @@
 import functools
 
 import pyarrow as pa
-
 import pylibcudf as plc
 from pylibcudf.expressions import (
     ASTOperator,

python/cudf/cudf/core/_internals/timezones.py

@@ -3,12 +3,12 @@
 
 import datetime
 import os
-import zoneinfo
 from functools import lru_cache
 from typing import TYPE_CHECKING, Literal
 
 import numpy as np
 import pandas as pd
+import zoneinfo
 
 import cudf
 from cudf._lib.timezone import make_timezone_transition_table

python/cudf/cudf/core/buffer/buffer.py

@@ -9,10 +9,9 @@
 from typing import Any, Literal, Mapping
 
 import numpy
-from typing_extensions import Self
-
 import pylibcudf
 import rmm
+from typing_extensions import Self
 
 import cudf
 from cudf.core.abc import Serializable

python/cudf/cudf/core/buffer/spillable_buffer.py

@@ -11,9 +11,8 @@
 
 import numpy
 import nvtx
-from typing_extensions import Self
-
 import rmm
+from typing_extensions import Self
 
 from cudf.core.buffer.buffer import (
     Buffer,

python/cudf/cudf/core/byte_pair_encoding.py

@@ -5,6 +5,8 @@
 import cudf
 from cudf._lib.nvtext.byte_pair_encode import (
     BPEMergePairs as cpp_merge_pairs,
+)
+from cudf._lib.nvtext.byte_pair_encode import (
     byte_pair_encoding as cpp_byte_pair_encoding,
 )
 

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

@@ -14,12 +14,11 @@
 import pandas as pd
 import pyarrow as pa
 import pyarrow.compute as pc
+import rmm
 from numba import cuda
 from pandas.core.arrays.arrow.extension_types import ArrowIntervalType
 from typing_extensions import Self
 
-import rmm
-
 import cudf
 from cudf import _lib as libcudf
 from cudf._lib.column import Column
@@ -31,10 +30,12 @@
 from cudf._lib.scalar import as_device_scalar
 from cudf._lib.stream_compaction import (
     apply_boolean_mask,
-    distinct_count as cpp_distinct_count,
     drop_duplicates,
     drop_nulls,
 )
+from cudf._lib.stream_compaction import (
+    distinct_count as cpp_distinct_count,
+)
 from cudf._lib.transform import bools_to_mask
 from cudf._lib.types import size_type_dtype
 from cudf.api.types import (

python/cudf/cudf/core/column/numerical.py

@@ -7,9 +7,8 @@
 
 import numpy as np
 import pandas as pd
-from typing_extensions import Self
-
 import pylibcudf
+from typing_extensions import Self
 
 import cudf
 from cudf import _lib as libcudf

python/cudf/cudf/core/column/string.py

@@ -14,7 +14,8 @@
 import cudf
 import cudf.api.types
 from cudf import _lib as libcudf
-from cudf._lib import string_casting as str_cast, strings as libstrings
+from cudf._lib import string_casting as str_cast
+from cudf._lib import strings as libstrings
 from cudf._lib.column import Column
 from cudf._lib.types import size_type_dtype
 from cudf.api.types import is_integer, is_scalar, is_string_dtype

python/cudf/cudf/core/df_protocol.py

@@ -7,9 +7,8 @@
 
 import cupy as cp
 import numpy as np
-from numba.cuda import as_cuda_array
-
 import rmm
+from numba.cuda import as_cuda_array
 
 import cudf
 from cudf.core.buffer import Buffer, as_buffer

python/cudf/cudf/core/indexed_frame.py

@@ -22,9 +22,8 @@
 import cupy as cp
 import numpy as np
 import pandas as pd
-from typing_extensions import Self
-
 import pylibcudf
+from typing_extensions import Self
 
 import cudf
 import cudf._lib as libcudf

python/cudf/cudf/core/series.py

@@ -39,9 +39,11 @@
 )
 from cudf.core.column.categorical import (
     _DEFAULT_CATEGORICAL_VALUE,
-    CategoricalAccessor as CategoricalAccessor,
     CategoricalColumn,
 )
+from cudf.core.column.categorical import (
+    CategoricalAccessor as CategoricalAccessor,
+)
 from cudf.core.column.column import concat_columns
 from cudf.core.column.lists import ListMethods
 from cudf.core.column.string import StringMethods

python/cudf/cudf/core/subword_tokenizer.py

@@ -8,6 +8,8 @@
 
 from cudf._lib.nvtext.subword_tokenize import (
     Hashed_Vocabulary as cpp_hashed_vocabulary,
+)
+from cudf._lib.nvtext.subword_tokenize import (
     subword_tokenize_inmem_hash as cpp_subword_tokenize,
 )
 

python/cudf/cudf/core/tokenize_vocabulary.py

@@ -5,6 +5,8 @@
 import cudf
 from cudf._lib.nvtext.tokenize import (
     TokenizeVocabulary as cpp_tokenize_vocabulary,
+)
+from cudf._lib.nvtext.tokenize import (
     tokenize_with_vocabulary as cpp_tokenize_with_vocabulary,
 )
 

python/cudf/cudf/core/udf/masked_lowering.py

@@ -1,4 +1,4 @@
-# Copyright (c) 2021-2023, NVIDIA CORPORATION.
+# Copyright (c) 2021-2024, NVIDIA CORPORATION.
 
 import operator
 
@@ -7,6 +7,8 @@
 from numba.core.typing import signature as nb_signature
 from numba.cuda.cudaimpl import (
     lower as cuda_lower,
+)
+from numba.cuda.cudaimpl import (
     registry as cuda_lowering_registry,
 )
 from numba.extending import lower_builtin, types

python/cudf/cudf/core/udf/strings_lowering.py

@@ -9,6 +9,8 @@
 from numba.core.typing import signature as nb_signature
 from numba.cuda.cudaimpl import (
     lower as cuda_lower,
+)
+from numba.cuda.cudaimpl import (
     registry as cuda_lowering_registry,
 )
 

python/cudf/cudf/core/udf/strings_typing.py

@@ -3,14 +3,13 @@
 import operator
 
 import numpy as np
+import rmm
 from numba import types
 from numba.core.extending import models, register_model
 from numba.core.typing import signature as nb_signature
 from numba.core.typing.templates import AbstractTemplate, AttributeTemplate
 from numba.cuda.cudadecl import registry as cuda_decl_registry
 
-import rmm
-
 # libcudf size_type
 size_type = types.int32
 

python/cudf/cudf/core/udf/utils.py

@@ -9,6 +9,7 @@
 import cupy as cp
 import llvmlite.binding as ll
 import numpy as np
+import rmm
 from cuda import cudart
 from numba import cuda, typeof
 from numba.core.datamodel import default_manager, models
@@ -17,8 +18,6 @@
 from numba.np import numpy_support
 from numba.types import CPointer, Poison, Record, Tuple, boolean, int64, void
 
-import rmm
-
 from cudf._lib import strings_udf
 from cudf.api.types import is_scalar
 from cudf.core.column.column import as_column

python/cudf/cudf/pandas/_wrappers/pandas.py

@@ -11,17 +11,41 @@
 import pandas as pd
 from pandas.tseries.holiday import (
     AbstractHolidayCalendar as pd_AbstractHolidayCalendar,
+)
+from pandas.tseries.holiday import (
     EasterMonday as pd_EasterMonday,
+)
+from pandas.tseries.holiday import (
     GoodFriday as pd_GoodFriday,
+)
+from pandas.tseries.holiday import (
     Holiday as pd_Holiday,
+)
+from pandas.tseries.holiday import (
     HolidayCalendarFactory as pd_HolidayCalendarFactory,
+)
+from pandas.tseries.holiday import (
     HolidayCalendarMetaClass as pd_HolidayCalendarMetaClass,
+)
+from pandas.tseries.holiday import (
     USColumbusDay as pd_USColumbusDay,
+)
+from pandas.tseries.holiday import (
     USFederalHolidayCalendar as pd_USFederalHolidayCalendar,
+)
+from pandas.tseries.holiday import (
     USLaborDay as pd_USLaborDay,
+)
+from pandas.tseries.holiday import (
     USMartinLutherKingJr as pd_USMartinLutherKingJr,
+)
+from pandas.tseries.holiday import (
     USMemorialDay as pd_USMemorialDay,
+)
+from pandas.tseries.holiday import (
     USPresidentsDay as pd_USPresidentsDay,
+)
+from pandas.tseries.holiday import (
     USThanksgivingDay as pd_USThanksgivingDay,
 )
 
@@ -36,9 +60,13 @@
     _FastSlowAttribute,
     _FunctionProxy,
     _Unusable,
+    register_proxy_func,
+)
+from ..fast_slow_proxy import (
     make_final_proxy_type as _make_final_proxy_type,
+)
+from ..fast_slow_proxy import (
     make_intermediate_proxy_type as _make_intermediate_proxy_type,
-    register_proxy_func,
 )
 from .common import (
     array_function_method,

python/cudf/cudf/tests/conftest.py

@@ -7,7 +7,6 @@
 import cupy as cp
 import numpy as np
 import pytest
-
 import rmm  # noqa: F401
 
 import cudf

python/cudf/cudf/tests/indexes/datetime/test_indexing.py

@@ -1,7 +1,6 @@
 # Copyright (c) 2023-2024, NVIDIA CORPORATION.
-import zoneinfo
-
 import pandas as pd
+import zoneinfo
 
 import cudf
 from cudf.testing import assert_eq

python/cudf/cudf/tests/indexes/datetime/test_time_specific.py

@@ -1,7 +1,6 @@
 # Copyright (c) 2022-2024, NVIDIA CORPORATION.
-import zoneinfo
-
 import pandas as pd
+import zoneinfo
 
 import cudf
 from cudf.testing import assert_eq

python/cudf/cudf/tests/series/test_datetimelike.py

@@ -2,10 +2,10 @@
 
 import datetime
 import os
-import zoneinfo
 
 import pandas as pd
 import pytest
+import zoneinfo
 
 import cudf
 from cudf import date_range

python/cudf/cudf/tests/test_binops.py

@@ -15,7 +15,8 @@
 from cudf import Index, Series
 from cudf.core._compat import PANDAS_CURRENT_SUPPORTED_VERSION, PANDAS_VERSION
 from cudf.core.buffer.spill_manager import get_global_manager
-from cudf.testing import _utils as utils, assert_eq
+from cudf.testing import _utils as utils
+from cudf.testing import assert_eq
 from cudf.utils.dtypes import (
     BOOL_TYPES,
     DATETIME_TYPES,

python/cudf/cudf/tests/test_dataframe.py

@@ -30,7 +30,8 @@
 from cudf.core.buffer.spill_manager import get_global_manager
 from cudf.core.column import column
 from cudf.errors import MixedTypeError
-from cudf.testing import _utils as utils, assert_eq, assert_neq
+from cudf.testing import _utils as utils
+from cudf.testing import assert_eq, assert_neq
 from cudf.testing._utils import (
     ALL_TYPES,
     DATETIME_TYPES,

python/cudf/cudf/tests/test_groupby.py

@@ -12,11 +12,10 @@
 import numpy as np
 import pandas as pd
 import pytest
+import rmm
 from numba import cuda
 from numpy.testing import assert_array_equal
 
-import rmm
-
 import cudf
 from cudf import DataFrame, Series
 from cudf.api.extensions import no_default

python/cudf/cudf/tests/test_indexing.py

@@ -11,7 +11,8 @@
 
 import cudf
 from cudf.core._compat import PANDAS_CURRENT_SUPPORTED_VERSION, PANDAS_VERSION
-from cudf.testing import _utils as utils, assert_eq
+from cudf.testing import _utils as utils
+from cudf.testing import assert_eq
 from cudf.testing._utils import (
     INTEGER_TYPES,
     assert_exceptions_equal,

python/cudf/cudf/tests/test_parquet.py

@@ -28,7 +28,8 @@
     ParquetWriter,
     merge_parquet_filemetadata,
 )
-from cudf.testing import assert_eq, dataset_generator as dg
+from cudf.testing import assert_eq
+from cudf.testing import dataset_generator as dg
 from cudf.testing._utils import TIMEDELTA_TYPES, set_random_null_mask_inplace