lint: replace isort with Ruff's rule I

.github/workflows/pr.yaml

@@ -44,7 +44,8 @@ jobs:
       needs: ${{ toJSON(needs) }}
   changed-files:
     secrets: inherit
-    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+    # TODO: Change back to @branch-24.12 before merging
+    uses: rapidsai/shared-workflows/.github/workflows/changed-files.yaml@fix-changed-files-too-long
     with:
       files_yaml: |
         test_cpp:

.pre-commit-config.yaml

@@ -16,17 +16,6 @@ repos:
             ^cpp/cmake/thirdparty/patches/.*|
             ^python/cudf/cudf/tests/data/subword_tokenizer_data/.*
           )
-  - repo: https://github.com/PyCQA/isort
-    rev: 5.13.2
-    hooks:
-      - id: isort
-        # Use the config file specific to each subproject so that each
-        # project can specify its own first/third-party packages.
-        args: ["--config-root=python/", "--resolve-all-configs"]
-        files: python/.*
-        exclude: |
-          (?x)^(^python/cudf_polars/.*)
-        types_or: [python, cython, pyi]
   - repo: https://github.com/MarcoGorelli/cython-lint
     rev: v0.16.2
     hooks:
@@ -150,6 +139,7 @@ repos:
     rev: v0.4.8
     hooks:
       - id: ruff
+        args: ["--fix"]
         files: python/.*$
       - id: ruff-format
         files: python/.*$

CONTRIBUTING.md

@@ -293,8 +293,8 @@ In order to run doxygen as a linter on C++/CUDA code, run
 ./ci/checks/doxygen.sh
 ```
 
-Python code runs several linters including [Black](https://black.readthedocs.io/en/stable/),
-[isort](https://pycqa.github.io/isort/), and [flake8](https://flake8.pycqa.org/en/latest/).
+Python code runs several linters including [Ruff](https://docs.astral.sh/ruff/)
+with its various rules  for Black-like formatting or Isort.
 
 cuDF also uses [codespell](https://github.com/codespell-project/codespell) to find spelling
 mistakes, and this check is run as a pre-commit hook. To apply the suggested spelling fixes,

docs/cudf/source/developer_guide/contributing_guide.md

@@ -16,7 +16,6 @@ The `.pre-commit-config.yaml` file at the root of the repo is the primary source
 Specifically, cuDF uses the following tools:
 
 - [`ruff`](https://beta.ruff.rs/) checks for general code formatting compliance.
-- [`isort`](https://pycqa.github.io/isort/) ensures imports are sorted consistently.
 - [`mypy`](http://mypy-lang.org/) performs static type checking.
   In conjunction with [type hints](https://docs.python.org/3/library/typing.html),
   `mypy` can help catch various bugs that are otherwise difficult to find.

docs/cudf/source/user_guide/10min.ipynb

@@ -38,10 +38,10 @@
     "import os\n",
     "\n",
     "import cupy as cp\n",
+    "import dask_cudf\n",
     "import pandas as pd\n",
     "\n",
     "import cudf\n",
-    "import dask_cudf\n",
     "\n",
     "cp.random.seed(12)\n",
     "\n",

docs/cudf/source/user_guide/guide-to-udfs.ipynb

@@ -101,6 +101,8 @@
    "outputs": [],
    "source": [
     "# define a scalar function\n",
+    "\n",
+    "\n",
     "def f(x):\n",
     "    return x + 1"
    ]
@@ -247,6 +249,8 @@
    "outputs": [],
    "source": [
     "# redefine the same function from above\n",
+    "\n",
+    "\n",
     "def f(x):\n",
     "    return x + 1"
    ]
@@ -1622,6 +1626,8 @@
    "outputs": [],
    "source": [
     "# a user defined aggregation function.\n",
+    "\n",
+    "\n",
     "def udaf(df):\n",
     "    return df[\"b\"].max() - df[\"b\"].min() / 2"
    ]

pyproject.toml

@@ -34,6 +34,8 @@ select = [
     "F",
     # pycodestyle Warning
     "W",
+    # isort
+    "I",
     # no-blank-line-before-function
     "D201",
     # one-blank-line-after-class

python/cudf/benchmarks/API/bench_dataframe.py

@@ -4,11 +4,11 @@
 
 import string
 
+from config import cudf, cupy
 import numba.cuda
 import numpy
 import pytest
 import pytest_cases
-from config import cudf, cupy
 from utils import benchmark_with_object
 
 

python/cudf/benchmarks/API/bench_functions.py

@@ -2,10 +2,10 @@
 
 """Benchmarks of free functions that accept cudf objects."""
 
+from config import NUM_ROWS, cudf, cupy
 import numpy as np
 import pytest
 import pytest_cases
-from config import NUM_ROWS, cudf, cupy
 from utils import benchmark_with_object
 
 

python/cudf/benchmarks/API/bench_index.py

@@ -1,9 +1,9 @@
-# Copyright (c) 2022, NVIDIA CORPORATION.
+# Copyright (c) 2022-2024, NVIDIA CORPORATION.
 
 """Benchmarks of Index methods."""
 
-import pytest
 from config import cudf, cupy
+import pytest
 from utils import benchmark_with_object
 
 

python/cudf/benchmarks/API/bench_multiindex.py

@@ -2,10 +2,10 @@
 
 """Benchmarks of MultiIndex methods."""
 
+from config import cudf
 import numpy as np
 import pandas as pd
 import pytest
-from config import cudf
 
 
 @pytest.fixture

python/cudf/benchmarks/API/bench_series.py

@@ -1,9 +1,9 @@
-# Copyright (c) 2022, NVIDIA CORPORATION.
+# Copyright (c) 2022-2024, NVIDIA CORPORATION.
 
 """Benchmarks of Series methods."""
 
-import pytest
 from config import cudf, cupy
+import pytest
 from utils import benchmark_with_object
 
 

python/cudf/benchmarks/API/cases_functions.py

@@ -2,8 +2,8 @@
 
 """Test cases for benchmarks in bench_functions.py."""
 
-import pytest_cases
 from config import NUM_ROWS, cudf, cupy
+import pytest_cases
 
 
 @pytest_cases.parametrize("nr", NUM_ROWS)

python/cudf/benchmarks/common/utils.py

@@ -1,16 +1,16 @@
-# Copyright (c) 2022, NVIDIA CORPORATION.
+# Copyright (c) 2022-2024, NVIDIA CORPORATION.
 
 """Common utilities for fixture creation and benchmarking."""
 
-import inspect
-import re
-import textwrap
 from collections.abc import MutableSet
+import inspect
 from itertools import groupby
 from numbers import Real
+import re
+import textwrap
 
-import pytest_cases
 from config import NUM_COLS, NUM_ROWS, cudf, cupy
+import pytest_cases
 
 
 def make_gather_map(len_gather_map: Real, len_column: Real, how: str):

python/cudf/benchmarks/conftest.py

@@ -56,27 +56,23 @@
 # into the main repo.
 sys.path.insert(0, os.path.join(os.path.dirname(__file__), "common"))
 
-from config import cudf  # noqa: W0611, E402, F401
-from utils import (  # noqa: E402
-    OrderedSet,
-    collapse_fixtures,
-    column_generators,
-    make_fixture,
-)
-
 # Turn off isort until we upgrade to 5.8.0
 # https://github.com/pycqa/isort/issues/1594
-# isort: off
 from config import (  # noqa: W0611, E402, F401
     NUM_COLS,
     NUM_ROWS,
     collect_ignore,
+    cudf,  # noqa: W0611, E402, F401
     pytest_collection_modifyitems,
     pytest_sessionfinish,
     pytest_sessionstart,
 )
-
-# isort: on
+from utils import (  # noqa: E402
+    OrderedSet,
+    collapse_fixtures,
+    column_generators,
+    make_fixture,
+)
 
 
 @pytest_cases.fixture(params=[0, 1], ids=["AxisIndex", "AxisColumn"])

python/cudf/cudf/_fuzz_testing/json.py

@@ -1,8 +1,8 @@
 # Copyright (c) 2020-2024, NVIDIA CORPORATION.
 
+from collections import abc
 import logging
 import random
-from collections import abc
 
 import numpy as np
 

python/cudf/cudf/_fuzz_testing/tests/fuzz_test_csv.py

@@ -1,7 +1,7 @@
 # Copyright (c) 2020-2024, NVIDIA CORPORATION.
 
-import sys
 from io import StringIO
+import sys
 
 import pandas as pd
 

python/cudf/cudf/_typing.py

@@ -1,8 +1,8 @@
 # Copyright (c) 2021-2024, NVIDIA CORPORATION.
 
+from collections.abc import Callable, Iterable
 import sys
-from collections.abc import Callable
-from typing import TYPE_CHECKING, Any, Dict, Iterable, TypeVar, Union
+from typing import TYPE_CHECKING, Any, TypeVar, Union
 
 import numpy as np
 from pandas import Period, Timedelta, Timestamp
@@ -42,7 +42,7 @@
 SeriesOrSingleColumnIndex = Union["cudf.Series", "cudf.core.index.Index"]
 
 # Groupby aggregation
-AggType = Union[str, Callable]
-MultiColumnAggType = Union[
-    AggType, Iterable[AggType], Dict[Any, Iterable[AggType]]
+AggType = Union[str, Callable]  # noqa: UP007
+MultiColumnAggType = Union[  # noqa: UP007
+    AggType, Iterable[AggType], dict[Any, Iterable[AggType]]
 ]

python/cudf/cudf/api/types.py

@@ -4,11 +4,11 @@
 
 from __future__ import annotations
 
-import warnings
 from collections import abc
 from functools import wraps
 from inspect import isclass
 from typing import cast
+import warnings
 
 import cupy as cp
 import numpy as np

python/cudf/cudf/core/_base_index.py

@@ -2,10 +2,10 @@
 
 from __future__ import annotations
 
-import pickle
-import warnings
 from functools import cached_property
+import pickle
 from typing import TYPE_CHECKING, Any, Literal
+import warnings
 
 import pandas as pd
 from typing_extensions import Self

python/cudf/cudf/core/_compat.py

@@ -1,7 +1,7 @@
 # Copyright (c) 2020-2024, NVIDIA CORPORATION.
 
-import pandas as pd
 from packaging import version
+import pandas as pd
 
 PANDAS_CURRENT_SUPPORTED_VERSION = version.parse("2.2.3")
 PANDAS_VERSION = version.parse(pd.__version__)

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

@@ -2,10 +2,10 @@
 from __future__ import annotations
 
 import datetime
-import os
-import zoneinfo
 from functools import lru_cache
+import os
 from typing import TYPE_CHECKING, Literal
+import zoneinfo
 
 import numpy as np
 import pandas as pd

python/cudf/cudf/core/_internals/where.py

@@ -1,8 +1,8 @@
 # Copyright (c) 2021-2024, NVIDIA CORPORATION.
 from __future__ import annotations
 
-import warnings
 from typing import TYPE_CHECKING
+import warnings
 
 import numpy as np
 

python/cudf/cudf/core/algorithms.py

@@ -1,8 +1,8 @@
 # Copyright (c) 2020-2024, NVIDIA CORPORATION.
 from __future__ import annotations
 
-import warnings
 from typing import TYPE_CHECKING
+import warnings
 
 import cupy as cp
 import numpy as np

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

@@ -4,9 +4,9 @@
 
 import math
 import pickle
-import weakref
 from types import SimpleNamespace
-from typing import Any, Literal, Mapping
+from typing import TYPE_CHECKING, Any, Literal
+import weakref
 
 import numpy
 from typing_extensions import Self
@@ -18,6 +18,9 @@
 from cudf.core.abc import Serializable
 from cudf.utils.string import format_bytes
 
+if TYPE_CHECKING:
+    from collections.abc import Mapping
+
 
 def host_memory_allocation(nbytes: int) -> memoryview:
     """Allocate host memory using NumPy

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

@@ -2,13 +2,16 @@
 
 from __future__ import annotations
 
-from typing import Literal, Mapping
+from typing import TYPE_CHECKING, Literal
 
 from typing_extensions import Self
 
 import cudf
 from cudf.core.buffer.buffer import Buffer, BufferOwner
 
+if TYPE_CHECKING:
+    from collections.abc import Mapping
+
 
 class ExposureTrackedBuffer(Buffer):
     """An exposure tracked buffer.