Replace black with ruff-format

.pre-commit-config.yaml

@@ -23,13 +23,6 @@ repos:
         args: ["--config-root=python/", "--resolve-all-configs"]
         files: python/.*
         types_or: [python, cython, pyi]
-  - repo: https://github.com/psf/black
-    rev: 23.12.1
-    hooks:
-      - id: black
-        files: python/.*
-        # Explicitly specify the pyproject.toml at the repo root, not per-project.
-        args: ["--config", "pyproject.toml"]
   - repo: https://github.com/MarcoGorelli/cython-lint
     rev: v0.16.0
     hooks:
@@ -155,6 +148,8 @@ repos:
     hooks:
       - id: ruff
         files: python/.*$
+      - id: ruff-format
+        files: python/.*$
   - repo: https://github.com/rapidsai/pre-commit-hooks
     rev: v0.0.1
     hooks:

pyproject.toml

@@ -1,22 +1,4 @@
-[tool.black]
-line-length = 79
-target-version = ["py39"]
-include = '\.py?$'
-force-exclude = '''
-/(
-    thirdparty |
-    \.eggs |
-    \.git |
-    \.hg |
-    \.mypy_cache |
-    \.tox |
-    \.venv |
-    _build |
-    buck-out |
-    build |
-    dist
-)/
-'''
+# Copyright (c) 2019-2024, NVIDIA CORPORATION.
 
 [tool.pydocstyle]
 # Due to https://github.com/PyCQA/pydocstyle/issues/363, we must exclude rather
@@ -66,7 +48,7 @@ exclude = [
     # TODO: Remove this in a follow-up where we fix __all__.
     "__init__.py",
 ]
-line-length = 88
+line-length = 79
 
 [tool.ruff.per-file-ignores]
 # Lots of pytest implicitly injected attributes in conftest-patch.py

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

@@ -85,8 +85,9 @@ def _read_tzfile_as_frame(tzdir, zone_name):
     if not transition_times_and_offsets:
         # this happens for UTC-like zones
         min_date = np.int64(np.iinfo("int64").min + 1).astype("M8[s]")
-        transition_times_and_offsets = as_column([min_date]), as_column(
-            [np.timedelta64(0, "s")]
+        transition_times_and_offsets = (
+            as_column([min_date]),
+            as_column([np.timedelta64(0, "s")]),
         )
 
     return DataFrame._from_data(

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

@@ -1731,7 +1731,8 @@ def as_column(
         If None (default), treats NaN values in arbitrary as null if there is
         no mask passed along with it. If True, combines the mask and NaNs to
         form a new validity mask. If False, leaves NaN values as is.
-        Only applies when arbitrary is not a cudf object (Index, Series, Column).
+        Only applies when arbitrary is not a cudf object
+        (Index, Series, Column).
     dtype : optional
         Optionally typecast the constructed Column to the given
         dtype.

python/cudf/cudf/core/dataframe.py

@@ -470,9 +470,12 @@ class _DataFrameIlocIndexer(_DataFrameIndexer):
     _frame: DataFrame
 
     def __getitem__(self, arg):
-        row_key, (
-            col_is_scalar,
-            column_names,
+        (
+            row_key,
+            (
+                col_is_scalar,
+                column_names,
+            ),
         ) = indexing_utils.destructure_dataframe_iloc_indexer(arg, self._frame)
         row_spec = indexing_utils.parse_row_iloc_indexer(
             row_key, len(self._frame)
@@ -6901,16 +6904,18 @@ def stack(self, level=-1, dropna=no_default, future_stack=False):
         if future_stack:
             if dropna is not no_default:
                 raise ValueError(
-                    "dropna must be unspecified with future_stack=True as the new "
-                    "implementation does not introduce rows of NA values. This "
-                    "argument will be removed in a future version of cudf."
+                    "dropna must be unspecified with future_stack=True as "
+                    "the new implementation does not introduce rows of NA "
+                    "values. This argument will be removed in a future "
+                    "version of cudf."
                 )
         else:
             if dropna is not no_default or self._data.nlevels > 1:
                 warnings.warn(
-                    "The previous implementation of stack is deprecated and will be "
-                    "removed in a future version of cudf. Specify future_stack=True "
-                    "to adopt the new implementation and silence this warning.",
+                    "The previous implementation of stack is deprecated and "
+                    "will be removed in a future version of cudf. Specify "
+                    "future_stack=True to adopt the new implementation and "
+                    "silence this warning.",
                     FutureWarning,
                 )
             if dropna is no_default:
@@ -7028,9 +7033,13 @@ def unnamed_group_generator():
                             unique_named_levels, axis=0, fill_value=-1
                         ).values
                     else:
-                        yield grpdf.reindex(
-                            unique_named_levels, axis=0, fill_value=-1
-                        ).sort_index().values
+                        yield (
+                            grpdf.reindex(
+                                unique_named_levels, axis=0, fill_value=-1
+                            )
+                            .sort_index()
+                            .values
+                        )
             else:
                 if future_stack:
                     yield column_idx_df.values

python/cudf/cudf/core/groupby/groupby.py

@@ -282,9 +282,12 @@ def __iter__(self):
         if isinstance(group_names, cudf.BaseIndex):
             group_names = group_names.to_pandas()
         for i, name in enumerate(group_names):
-            yield (name,) if isinstance(self._by, list) and len(
-                self._by
-            ) == 1 else name, grouped_values[offsets[i] : offsets[i + 1]]
+            yield (
+                (name,)
+                if isinstance(self._by, list) and len(self._by) == 1
+                else name,
+                grouped_values[offsets[i] : offsets[i + 1]],
+            )
 
     @property
     def dtypes(self):
@@ -2269,8 +2272,8 @@ def fillna(
         """
         warnings.warn(
             "groupby fillna is deprecated and "
-            "will be removed in a future version. Use groupby ffill or groupby bfill "
-            "for forward or backward filling instead.",
+            "will be removed in a future version. Use groupby ffill "
+            "or groupby bfill for forward or backward filling instead.",
             FutureWarning,
         )
         if inplace:

python/cudf/cudf/core/indexed_frame.py

@@ -211,8 +211,8 @@ def _get_label_range_or_mask(index, start, stop, step):
                 return slice(start_loc, stop_loc)
             else:
                 raise KeyError(
-                    "Value based partial slicing on non-monotonic DatetimeIndexes "
-                    "with non-existing keys is not allowed.",
+                    "Value based partial slicing on non-monotonic "
+                    "DatetimeIndexes with non-existing keys is not allowed.",
                 )
         elif start is not None:
             boolean_mask = index >= start
@@ -2449,7 +2449,8 @@ def squeeze(self, axis: Literal["index", "columns", 0, 1, None] = None):
         ----------
         axis : {0 or 'index', 1 or 'columns', None}, default None
             A specific axis to squeeze. By default, all length-1 axes are
-            squeezed. For `Series` this parameter is unused and defaults to `None`.
+            squeezed. For `Series` this parameter is unused and defaults
+            to `None`.
 
         Returns
         -------
@@ -5835,9 +5836,7 @@ def floordiv(self, other, axis, level=None, fill_value=None):  # noqa: D102
             ),
         )
     )
-    def rfloordiv(
-        self, other, axis, level=None, fill_value=None
-    ):  # noqa: D102
+    def rfloordiv(self, other, axis, level=None, fill_value=None):  # noqa: D102
         if level is not None:
             raise NotImplementedError("level parameter is not supported yet.")
 
@@ -5967,9 +5966,7 @@ def rtruediv(self, other, axis, level=None, fill_value=None):  # noqa: D102
             ),
         )
     )
-    def eq(
-        self, other, axis="columns", level=None, fill_value=None
-    ):  # noqa: D102
+    def eq(self, other, axis="columns", level=None, fill_value=None):  # noqa: D102
         return self._binaryop(
             other=other, op="__eq__", fill_value=fill_value, can_reindex=True
         )
@@ -6009,9 +6006,7 @@ def eq(
             ),
         )
     )
-    def ne(
-        self, other, axis="columns", level=None, fill_value=None
-    ):  # noqa: D102
+    def ne(self, other, axis="columns", level=None, fill_value=None):  # noqa: D102
         return self._binaryop(
             other=other, op="__ne__", fill_value=fill_value, can_reindex=True
         )
@@ -6051,9 +6046,7 @@ def ne(
             ),
         )
     )
-    def lt(
-        self, other, axis="columns", level=None, fill_value=None
-    ):  # noqa: D102
+    def lt(self, other, axis="columns", level=None, fill_value=None):  # noqa: D102
         return self._binaryop(
             other=other, op="__lt__", fill_value=fill_value, can_reindex=True
         )
@@ -6093,9 +6086,7 @@ def lt(
             ),
         )
     )
-    def le(
-        self, other, axis="columns", level=None, fill_value=None
-    ):  # noqa: D102
+    def le(self, other, axis="columns", level=None, fill_value=None):  # noqa: D102
         return self._binaryop(
             other=other, op="__le__", fill_value=fill_value, can_reindex=True
         )
@@ -6135,9 +6126,7 @@ def le(
             ),
         )
     )
-    def gt(
-        self, other, axis="columns", level=None, fill_value=None
-    ):  # noqa: D102
+    def gt(self, other, axis="columns", level=None, fill_value=None):  # noqa: D102
         return self._binaryop(
             other=other, op="__gt__", fill_value=fill_value, can_reindex=True
         )
@@ -6177,9 +6166,7 @@ def gt(
             ),
         )
     )
-    def ge(
-        self, other, axis="columns", level=None, fill_value=None
-    ):  # noqa: D102
+    def ge(self, other, axis="columns", level=None, fill_value=None):  # noqa: D102
         return self._binaryop(
             other=other, op="__ge__", fill_value=fill_value, can_reindex=True
         )

python/cudf/cudf/core/resample.py

@@ -1,4 +1,4 @@
-# SPDX-FileCopyrightText: Copyright (c) 2021-2024, NVIDIA CORPORATION & AFFILIATES.
+# SPDX-FileCopyrightText: Copyright (c) 2021-2024, NVIDIA CORPORATION & AFFILIATES.  # noqa: E501
 # All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 #

python/cudf/cudf/core/tools/datetimes.py

@@ -164,9 +164,9 @@ def to_datetime(
 
     if errors == "ignore":
         warnings.warn(
-            "errors='ignore' is deprecated and will raise in a future version. "
-            "Use to_datetime without passing `errors` and catch exceptions "
-            "explicitly instead",
+            "errors='ignore' is deprecated and will raise in a "
+            "future version. Use to_datetime without passing `errors` "
+            "and catch exceptions explicitly instead",
             FutureWarning,
         )
 

python/cudf/cudf/core/tools/numeric.py

@@ -97,9 +97,9 @@ def to_numeric(arg, errors="raise", downcast=None):
         raise ValueError("invalid error value specified")
     elif errors == "ignore":
         warnings.warn(
-            "errors='ignore' is deprecated and will raise in a future version. "
-            "Use to_numeric without passing `errors` and catch exceptions "
-            "explicitly instead",
+            "errors='ignore' is deprecated and will raise in "
+            "a future version. Use to_numeric without passing `errors` "
+            "and catch exceptions explicitly instead",
             FutureWarning,
         )
 

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

@@ -1,4 +1,4 @@
-# Copyright (c) 2022-2023, NVIDIA CORPORATION.
+# Copyright (c) 2022-2024, NVIDIA CORPORATION.
 
 import operator
 from functools import partial
@@ -249,7 +249,7 @@ def replace_impl(context, builder, sig, args):
     replacement_ptr = builder.alloca(args[2].type)
 
     builder.store(args[0], src_ptr)
-    builder.store(args[1], to_replace_ptr),
+    (builder.store(args[1], to_replace_ptr),)
     builder.store(args[2], replacement_ptr)
 
     udf_str_ptr = builder.alloca(default_manager[udf_string].get_value_type())

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

@@ -41,9 +41,7 @@
 from cudf.utils.utils import initfunc
 
 # Maximum size of a string column is 2 GiB
-_STRINGS_UDF_DEFAULT_HEAP_SIZE = os.environ.get(
-    "STRINGS_UDF_HEAP_SIZE", 2**31
-)
+_STRINGS_UDF_DEFAULT_HEAP_SIZE = os.environ.get("STRINGS_UDF_HEAP_SIZE", 2**31)
 _heap_size = 0
 _cudf_str_dtype = dtype(str)
 

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

@@ -1,4 +1,4 @@
-# SPDX-FileCopyrightText: Copyright (c) 2023-2024, NVIDIA CORPORATION & AFFILIATES.
+# SPDX-FileCopyrightText: Copyright (c) 2023-2024, NVIDIA CORPORATION & AFFILIATES.  # noqa: E501
 # All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 import copyreg

python/cudf/cudf/pandas/fast_slow_proxy.py

@@ -1,4 +1,4 @@
-# SPDX-FileCopyrightText: Copyright (c) 2023-2024, NVIDIA CORPORATION & AFFILIATES.
+# SPDX-FileCopyrightText: Copyright (c) 2023-2024, NVIDIA CORPORATION & AFFILIATES.   # noqa: E501
 # All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 
@@ -437,9 +437,7 @@ def __get__(self, obj, owner=None) -> Any:
                 # methods because dir for the method won't be the same as for
                 # the pure unbound function, but the alternative is
                 # materializing the slow object when we don't really want to.
-                result._fsproxy_slow_dir = dir(
-                    slow_result_type
-                )  # type: ignore
+                result._fsproxy_slow_dir = dir(slow_result_type)  # type: ignore
 
         return result
 

python/cudf/cudf/pandas/module_accelerator.py

@@ -1,4 +1,4 @@
-# SPDX-FileCopyrightText: Copyright (c) 2023-2024, NVIDIA CORPORATION & AFFILIATES.
+# SPDX-FileCopyrightText: Copyright (c) 2023-2024, NVIDIA CORPORATION & AFFILIATES.  # noqa: E501
 # All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 

python/cudf/cudf/pandas/profiler.py

@@ -1,4 +1,4 @@
-# SPDX-FileCopyrightText: Copyright (c) 2023 NVIDIA CORPORATION & AFFILIATES.
+# SPDX-FileCopyrightText: Copyright (c) 2023-2024, NVIDIA CORPORATION & AFFILIATES.  # noqa: E501
 # All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 
@@ -124,7 +124,7 @@ def get_namespaced_function_name(
             _MethodProxy,
             type[_FinalProxy],
             type[_IntermediateProxy],
-        ]
+        ],
     ):
         if isinstance(func_obj, _MethodProxy):
             # Extract classname from method object
@@ -177,17 +177,15 @@ def _tracefunc(self, frame, event, arg):
             if self._currkey is not None and arg is not None:
                 if arg[1]:  # fast
                     run_time = time.perf_counter() - self._timer[self._currkey]
-                    self._results[self._currkey][
-                        "gpu_time"
-                    ] = run_time + self._results[self._currkey].get(
-                        "gpu_time", 0
+                    self._results[self._currkey]["gpu_time"] = (
+                        run_time
+                        + self._results[self._currkey].get("gpu_time", 0)
                     )
                 else:
                     run_time = time.perf_counter() - self._timer[self._currkey]
-                    self._results[self._currkey][
-                        "cpu_time"
-                    ] = run_time + self._results[self._currkey].get(
-                        "cpu_time", 0
+                    self._results[self._currkey]["cpu_time"] = (
+                        run_time
+                        + self._results[self._currkey].get("cpu_time", 0)
                     )
 
             frame_locals = inspect.getargvalues(frame).locals

python/cudf/cudf/tests/test_dataframe.py

@@ -2351,7 +2351,7 @@ def test_dataframe_reductions(data, axis, func, skipna):
     for kwargs in all_kwargs:
         if expected_exception is not None:
             with pytest.raises(expected_exception):
-                getattr(gdf, func)(axis=axis, skipna=skipna, **kwargs),
+                (getattr(gdf, func)(axis=axis, skipna=skipna, **kwargs),)
         else:
             expect = getattr(pdf, func)(axis=axis, skipna=skipna, **kwargs)
             with expect_warning_if(