Upgrade pandas pinnings & make style fixes

conda/environments/all_cuda-118_arch-x86_64.yaml

@@ -60,7 +60,7 @@ dependencies:
 - nvcomp==2.6.1
 - nvtx>=0.2.1
 - packaging
-- pandas>=1.3,<1.6.0dev0
+- pandas>=1.3,<2.1.0dev0
 - pandoc
 - pip
 - pre-commit

conda/environments/all_cuda-120_arch-x86_64.yaml

@@ -58,7 +58,7 @@ dependencies:
 - nvcomp==2.6.1
 - nvtx>=0.2.1
 - packaging
-- pandas>=1.3,<1.6.0dev0
+- pandas>=1.3,<2.1.0dev0
 - pandoc
 - pip
 - pre-commit

conda/recipes/cudf/meta.yaml

@@ -76,7 +76,7 @@ requirements:
     - {{ pin_compatible('protobuf', min_pin='x.x', max_pin='x') }}
     - python
     - typing_extensions >=4.0.0
-    - pandas >=1.3,<1.6.0dev0
+    - pandas >=1.3,<2.1.0dev0
     - cupy >=12.0.0
     - numba >=0.57
     - numpy >=1.21

dependencies.yaml

@@ -413,7 +413,7 @@ dependencies:
         packages:
           - fsspec>=0.6.0
           - numpy>=1.21
-          - pandas>=1.3,<1.6.0dev0
+          - pandas>=1.3,<2.1.0dev0
   run_cudf:
     common:
       - output_types: [conda, requirements, pyproject]

python/cudf/cudf/core/_compat.py

@@ -12,3 +12,4 @@
 PANDAS_EQ_200 = PANDAS_VERSION == version.parse("2.0.0")
 PANDAS_GE_200 = PANDAS_VERSION >= version.parse("2.0.0")
 PANDAS_GE_210 = PANDAS_VERSION >= version.parse("2.1.0")
+PANDAS_LT_203 = PANDAS_VERSION < version.parse("2.0.3")

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

@@ -13,11 +13,11 @@
 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 _fillna_natwise
-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

@@ -57,6 +57,7 @@
     is_struct_dtype,
 )
 from cudf.core import column, df_protocol, indexing_utils, reshape
+from cudf.core._compat import PANDAS_GE_200
 from cudf.core.abc import Serializable
 from cudf.core.column import (
     CategoricalColumn,
@@ -99,7 +100,6 @@
     _cudf_nvtx_annotate,
     _external_only_api,
 )
-from cudf.core._compat import PANDAS_GE_200
 
 _cupy_nan_methods_map = {
     "min": "nanmin",

python/cudf/cudf/core/index.py

@@ -7,14 +7,7 @@
 import warnings
 from functools import cache, cached_property
 from numbers import Number
-from typing import (
-    Any,
-    List,
-    MutableMapping,
-    Optional,
-    Tuple,
-    Union,
-)
+from typing import Any, List, MutableMapping, Optional, Tuple, Union
 
 import cupy
 import numpy as np

python/cudf/cudf/tests/test_api_types.py

@@ -6,8 +6,8 @@
 from pandas.api import types as pd_types
 
 import cudf
-from cudf.core._compat import PANDAS_GE_200
 from cudf.api import types
+from cudf.core._compat import PANDAS_GE_200
 
 
 @pytest.mark.parametrize(

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

@@ -8,7 +8,7 @@
 
 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

@@ -16,7 +16,7 @@
 
 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_dataframe.py

@@ -26,6 +26,7 @@
     PANDAS_GE_150,
     PANDAS_GE_200,
     PANDAS_LT_140,
+    PANDAS_LT_203,
 )
 from cudf.core.buffer.spill_manager import get_global_manager
 from cudf.core.column import column
@@ -8406,6 +8407,7 @@ def test_dataframe_mode(request, df, numeric_only, dropna):
     request.applymarker(
         pytest.mark.xfail(
             condition=PANDAS_GE_200
+            and PANDAS_LT_203
             and numeric_only is False
             and "b" in df.columns
             and df["b"].dtype == np.dtype("timedelta64[s]"),

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
@@ -10,10 +11,9 @@
 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
+from cudf.core._compat import PANDAS_EQ_200, PANDAS_GE_150, PANDAS_LT_140
 from cudf.core.index import DatetimeIndex
 from cudf.testing._utils import (
     DATETIME_TYPES,

python/cudf/cudf/tests/test_groupby.py

@@ -21,9 +21,9 @@
 from cudf import DataFrame, Series
 from cudf.core._compat import (
     PANDAS_GE_150,
-    PANDAS_LT_140,
     PANDAS_GE_200,
     PANDAS_GE_210,
+    PANDAS_LT_140,
 )
 from cudf.core.udf.groupby_typing import SUPPORTED_GROUPBY_NUMPY_TYPES
 from cudf.core.udf.utils import precompiled

python/cudf/cudf/tests/test_index.py

@@ -2891,7 +2891,7 @@ def test_rangeindex_join_user_option(default_integer_bitwidth):
     actual = idx1.join(idx2, how="inner", sort=True)
     expected = idx1.to_pandas().join(idx2.to_pandas(), how="inner", sort=True)
     assert actual.dtype == cudf.dtype(f"int{default_integer_bitwidth}")
-    assert_eq(expected, actual)
+    assert_eq(expected, actual, exact=False)
 
 
 def test_rangeindex_where_user_option(default_integer_bitwidth):

python/cudf/cudf/tests/test_joining.py

@@ -7,6 +7,7 @@
 import pytest
 
 import cudf
+from cudf.core._compat import PANDAS_GE_200
 from cudf.core.dtypes import CategoricalDtype, Decimal64Dtype, Decimal128Dtype
 from cudf.testing._utils import (
     INTEGER_TYPES,
@@ -15,7 +16,6 @@
     assert_exceptions_equal,
     expect_warning_if,
 )
-from cudf.core._compat import PANDAS_GE_200
 
 _JOIN_TYPES = ("left", "inner", "outer", "right", "leftanti", "leftsemi")
 
@@ -183,7 +183,9 @@ def test_dataframe_join_suffix():
     assert_eq(expect.index.values, got.index.values)
 
     got_sorted = got.sort_values(by=list(got.columns), axis=0)
+    expect.index.name = None
     expect_sorted = expect.sort_values(by=list(expect.columns), axis=0)
+
     for k in expect_sorted.columns:
         _check_series(expect_sorted[k].fillna(-1), got_sorted[k].fillna(-1))
 

python/cudf/cudf/tests/test_monotonic.py

@@ -9,12 +9,13 @@
 import pytest
 
 import cudf
-from cudf import MultiIndex, Series
-from cudf.core.index import (
+from cudf import (
     CategoricalIndex,
     DatetimeIndex,
     Index,
+    MultiIndex,
     RangeIndex,
+    Series,
 )
 from cudf.testing._utils import assert_eq
 

python/cudf/cudf/tests/test_orc.py

@@ -15,6 +15,7 @@
 import pytest
 
 import cudf
+from cudf.core._compat import PANDAS_GE_200
 from cudf.io.orc import ORCWriter
 from cudf.testing import assert_frame_equal
 from cudf.testing._utils import (
@@ -23,7 +24,6 @@
     gen_rand_series,
     supported_numpy_dtypes,
 )
-from cudf.core._compat import PANDAS_GE_200
 
 # Removal of these deprecated features is no longer imminent. They will not be
 # removed until a suitable alternative has been implemented. As a result, we

python/cudf/cudf/tests/test_parquet.py

@@ -20,7 +20,7 @@
 from pyarrow import fs as pa_fs, parquet as pq
 
 import cudf
-from cudf.core._compat import PANDAS_LT_153, PANDAS_GE_200
+from cudf.core._compat import PANDAS_GE_200, PANDAS_LT_153
 from cudf.io.parquet import (
     ParquetDatasetWriter,
     ParquetWriter,

python/cudf/cudf/tests/test_resampling.py

@@ -5,8 +5,8 @@
 import pytest
 
 import cudf
-from cudf.testing._utils import assert_eq
 from cudf.core._compat import PANDAS_GE_200
+from cudf.testing._utils import assert_eq
 
 
 def assert_resample_results_equal(lhs, rhs, **kwargs):

python/cudf/cudf/tests/test_rolling.py

@@ -8,7 +8,7 @@
 import pytest
 
 import cudf
-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.testing._utils import _create_pandas_series, assert_eq
 from cudf.testing.dataset_generator import rand_dataframe
 

python/cudf/cudf/tests/test_series.py

@@ -13,6 +13,7 @@
 import pytest
 
 import cudf
+from cudf.api.extensions import no_default
 from cudf.core._compat import PANDAS_LT_140
 from cudf.testing._utils import (
     NUMERIC_TYPES,
@@ -23,7 +24,6 @@
     expect_warning_if,
     gen_rand,
 )
-from cudf.api.extensions import no_default
 
 
 def _series_na_data():

python/cudf/cudf/tests/test_timedelta.py

@@ -9,9 +9,9 @@
 import pytest
 
 import cudf
+from cudf.core._compat import PANDAS_GE_200
 from cudf.testing import _utils as utils
 from cudf.testing._utils import assert_eq, assert_exceptions_equal
-from cudf.core._compat import PANDAS_GE_200
 
 _TIMEDELTA_DATA = [
     [1000000, 200000, 3000000],

python/cudf/pyproject.toml

@@ -35,7 +35,7 @@ dependencies = [
     "numpy>=1.21",
     "nvtx>=0.2.1",
     "packaging",
-    "pandas>=1.3,<1.6.0dev0",
+    "pandas>=1.3,<2.1.0dev0",
     "protobuf>=4.21,<5",
     "ptxcompiler",
     "pyarrow==12.*",

python/dask_cudf/pyproject.toml

@@ -24,7 +24,7 @@ dependencies = [
     "distributed>=2023.5.1",
     "fsspec>=0.6.0",
     "numpy>=1.21",
-    "pandas>=1.3,<1.6.0dev0",
+    "pandas>=1.3,<2.1.0dev0",
 ] # This list was generated by `rapids-dependency-file-generator`. To make changes, edit ../../dependencies.yaml and run `rapids-dependency-file-generator`.
 classifiers = [
     "Intended Audience :: Developers",