Remove cudf._lib.groupby in favor of inlining pylibcudf

python/cudf/cudf/_lib/CMakeLists.txt

@@ -12,7 +12,7 @@
 # the License.
 # =============================================================================
 
-set(cython_sources column.pyx groupby.pyx scalar.pyx strings_udf.pyx types.pyx utils.pyx)
+set(cython_sources column.pyx scalar.pyx strings_udf.pyx types.pyx utils.pyx)
 set(linked_libraries cudf::cudf)
 
 rapids_cython_create_modules(

python/cudf/cudf/_lib/__init__.py

@@ -1,10 +1,7 @@
 # Copyright (c) 2020-2024, NVIDIA CORPORATION.
 import numpy as np
 
-from . import (
-    groupby,
-    strings_udf,
-)
+from . import strings_udf
 
 MAX_COLUMN_SIZE = np.iinfo(np.int32).max
 MAX_COLUMN_SIZE_STR = "INT32_MAX"

python/cudf/cudf/core/_internals/aggregation.py

@@ -29,11 +29,11 @@
 
 class Aggregation:
     def __init__(self, agg: plc.aggregation.Aggregation) -> None:
-        self.c_obj = agg
+        self.plc_obj = agg
 
     @property
     def kind(self) -> str:
-        name = self.c_obj.kind().name
+        name = self.plc_obj.kind().name
         return _agg_name_map.get(name, name)
 
     @classmethod

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

@@ -1605,7 +1605,7 @@ def scan(self, scan_op: str, inclusive: bool, **kwargs) -> Self:
         return type(self).from_pylibcudf(  # type: ignore[return-value]
             plc.reduce.scan(
                 self.to_pylibcudf(mode="read"),
-                aggregation.make_aggregation(scan_op, kwargs).c_obj,
+                aggregation.make_aggregation(scan_op, kwargs).plc_obj,
                 plc.reduce.ScanType.INCLUSIVE
                 if inclusive
                 else plc.reduce.ScanType.EXCLUSIVE,
@@ -1637,7 +1637,7 @@ def reduce(self, reduction_op: str, dtype=None, **kwargs) -> ScalarLike:
         with acquire_spill_lock():
             plc_scalar = plc.reduce.reduce(
                 self.to_pylibcudf(mode="read"),
-                aggregation.make_aggregation(reduction_op, kwargs).c_obj,
+                aggregation.make_aggregation(reduction_op, kwargs).plc_obj,
                 dtype_to_pylibcudf_type(col_dtype),
             )
             result_col = type(self).from_pylibcudf(