Remove unnecessary **kwargs in function signatures (#14635)

Helps makes function signatures stricter to avoid typo inputs being accepted into signatures

Authors:
  - Matthew Roeschke (https://github.com/mroeschke)

Approvers:
  - Vyas Ramasubramani (https://github.com/vyasr)

URL: #14635

python/cudf/cudf/_lib/groupby.pyx

@@ -1,4 +1,4 @@
-# Copyright (c) 2020-2023, NVIDIA CORPORATION.
+# Copyright (c) 2020-2024, NVIDIA CORPORATION.
 
 from pandas.core.groupby.groupby import DataError
 
@@ -104,7 +104,7 @@ cdef class GroupBy:
     cdef unique_ptr[libcudf_groupby.groupby] c_obj
     cdef dict __dict__
 
-    def __cinit__(self, list keys, bool dropna=True, *args, **kwargs):
+    def __cinit__(self, list keys, bool dropna=True):
         cdef libcudf_types.null_policy c_null_handling
         cdef table_view keys_view
 

python/cudf/cudf/_lib/string_casting.pyx

@@ -1,4 +1,4 @@
-# Copyright (c) 2020-2023, NVIDIA CORPORATION.
+# Copyright (c) 2020-2024, NVIDIA CORPORATION.
 
 from cudf._lib.column cimport Column
 
@@ -95,7 +95,7 @@ def dtos(Column input_col):
     return floating_to_string(input_col)
 
 
-def stod(Column input_col, **kwargs):
+def stod(Column input_col):
     """
     Converting/Casting input column of type string to double
 
@@ -127,7 +127,7 @@ def ftos(Column input_col):
     return floating_to_string(input_col)
 
 
-def stof(Column input_col, **kwargs):
+def stof(Column input_col):
     """
     Converting/Casting input column of type string to float
 
@@ -188,7 +188,7 @@ def i8tos(Column input_col):
     return integer_to_string(input_col)
 
 
-def stoi8(Column input_col, **kwargs):
+def stoi8(Column input_col):
     """
     Converting/Casting input column of type string to int8
 
@@ -284,7 +284,7 @@ def ltos(Column input_col):
     return integer_to_string(input_col)
 
 
-def stol(Column input_col, **kwargs):
+def stol(Column input_col):
     """
     Converting/Casting input column of type string to int64
 
@@ -316,7 +316,7 @@ def ui8tos(Column input_col):
     return integer_to_string(input_col)
 
 
-def stoui8(Column input_col, **kwargs):
+def stoui8(Column input_col):
     """
     Converting/Casting input column of type string to uint8
 
@@ -348,7 +348,7 @@ def ui16tos(Column input_col):
     return integer_to_string(input_col)
 
 
-def stoui16(Column input_col, **kwargs):
+def stoui16(Column input_col):
     """
     Converting/Casting input column of type string to uint16
 
@@ -380,7 +380,7 @@ def uitos(Column input_col):
     return integer_to_string(input_col)
 
 
-def stoui(Column input_col, **kwargs):
+def stoui(Column input_col):
     """
     Converting/Casting input column of type string to uint32
 
@@ -412,7 +412,7 @@ def ultos(Column input_col):
     return integer_to_string(input_col)
 
 
-def stoul(Column input_col, **kwargs):
+def stoul(Column input_col):
     """
     Converting/Casting input column of type string to uint64
 
@@ -456,7 +456,7 @@ def _to_booleans(Column input_col, object string_true="True"):
     return Column.from_unique_ptr(move(c_result))
 
 
-def to_booleans(Column input_col, **kwargs):
+def to_booleans(Column input_col):
 
     return _to_booleans(input_col)
 
@@ -631,9 +631,7 @@ def timedelta2int(Column input_col, dtype, format):
     return Column.from_unique_ptr(move(c_result))
 
 
-def int2timedelta(
-        Column input_col,
-        **kwargs):
+def int2timedelta(Column input_col, str format):
     """
     Converting/Casting input Timedelta column to string
     column with specified format
@@ -649,8 +647,7 @@ def int2timedelta(
     """
 
     cdef column_view input_column_view = input_col.view()
-    cdef string c_duration_format = kwargs.get(
-        'format', "%D days %H:%M:%S").encode('UTF-8')
+    cdef string c_duration_format = format.encode('UTF-8')
     cdef unique_ptr[column] c_result
     with nogil:
         c_result = move(
@@ -661,7 +658,7 @@ def int2timedelta(
     return Column.from_unique_ptr(move(c_result))
 
 
-def int2ip(Column input_col, **kwargs):
+def int2ip(Column input_col):
     """
     Converting/Casting integer column to string column in ipv4 format
 
@@ -684,7 +681,7 @@ def int2ip(Column input_col, **kwargs):
     return Column.from_unique_ptr(move(c_result))
 
 
-def ip2int(Column input_col, **kwargs):
+def ip2int(Column input_col):
     """
     Converting string ipv4 column to integer column
 
@@ -732,7 +729,6 @@ def htoi(Column input_col, **kwargs):
     Parameters
     ----------
     input_col : input column of type string
-    out_type : The type of integer column expected
 
     Returns
     -------
@@ -742,9 +738,7 @@ def htoi(Column input_col, **kwargs):
     cdef column_view input_column_view = input_col.view()
     cdef type_id tid = <type_id> (
         <underlying_type_t_type_id> (
-            SUPPORTED_NUMPY_TO_LIBCUDF_TYPES[
-                kwargs.get('dtype', cudf.dtype("int64"))
-            ]
+            SUPPORTED_NUMPY_TO_LIBCUDF_TYPES[cudf.dtype("int64")]
         )
     )
     cdef data_type c_out_type = data_type(tid)

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

@@ -1310,22 +1310,28 @@ def as_categorical_column(self, dtype: Dtype) -> CategoricalColumn:
             new_categories=dtype.categories, ordered=bool(dtype.ordered)
         )
 
-    def as_numerical_column(self, dtype: Dtype, **kwargs) -> NumericalColumn:
+    def as_numerical_column(self, dtype: Dtype) -> NumericalColumn:
         return self._get_decategorized_column().as_numerical_column(dtype)
 
-    def as_string_column(self, dtype, format=None, **kwargs) -> StringColumn:
+    def as_string_column(
+        self, dtype, format: str | None = None
+    ) -> StringColumn:
         return self._get_decategorized_column().as_string_column(
             dtype, format=format
         )
 
-    def as_datetime_column(self, dtype, **kwargs) -> DatetimeColumn:
+    def as_datetime_column(
+        self, dtype, format: str | None = None
+    ) -> DatetimeColumn:
         return self._get_decategorized_column().as_datetime_column(
-            dtype, **kwargs
+            dtype, format
         )
 
-    def as_timedelta_column(self, dtype, **kwargs) -> TimeDeltaColumn:
+    def as_timedelta_column(
+        self, dtype, format: str | None = None
+    ) -> TimeDeltaColumn:
         return self._get_decategorized_column().as_timedelta_column(
-            dtype, **kwargs
+            dtype, format
         )
 
     def _get_decategorized_column(self) -> ColumnBase:

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

@@ -978,11 +978,17 @@ def distinct_count(self, dropna: bool = True) -> int:
     def can_cast_safely(self, to_dtype: Dtype) -> bool:
         raise NotImplementedError()
 
-    def astype(self, dtype: Dtype, **kwargs) -> ColumnBase:
+    def astype(
+        self, dtype: Dtype, copy: bool = False, format: str | None = None
+    ) -> ColumnBase:
+        if copy:
+            col = self.copy()
+        else:
+            col = self
         if self.dtype == dtype:
-            return self
+            return col
         if is_categorical_dtype(dtype):
-            return self.as_categorical_column(dtype)
+            return col.as_categorical_column(dtype)
 
         if (
             isinstance(dtype, str)
@@ -999,9 +1005,9 @@ def astype(self, dtype: Dtype, **kwargs) -> ColumnBase:
         else:
             dtype = pandas_dtypes_to_np_dtypes.get(dtype, dtype)
         if _is_non_decimal_numeric_dtype(dtype):
-            return self.as_numerical_column(dtype, **kwargs)
+            return col.as_numerical_column(dtype)
         elif is_categorical_dtype(dtype):
-            return self.as_categorical_column(dtype)
+            return col.as_categorical_column(dtype)
         elif cudf.dtype(dtype).type in {
             np.str_,
             np.object_,
@@ -1014,23 +1020,23 @@ def astype(self, dtype: Dtype, **kwargs) -> ColumnBase:
                     f"Casting to {dtype} is not supported, use "
                     "`.astype('str')` instead."
                 )
-            return self.as_string_column(dtype, **kwargs)
+            return col.as_string_column(dtype, format=format)
         elif isinstance(dtype, (ListDtype, StructDtype)):
-            if not self.dtype == dtype:
+            if not col.dtype == dtype:
                 raise NotImplementedError(
                     f"Casting {self.dtype} columns not currently supported"
                 )
-            return self
+            return col
         elif isinstance(dtype, IntervalDtype):
-            return self.as_interval_column(dtype, **kwargs)
+            return col.as_interval_column(dtype)
         elif isinstance(dtype, cudf.core.dtypes.DecimalDtype):
-            return self.as_decimal_column(dtype, **kwargs)
+            return col.as_decimal_column(dtype)
         elif np.issubdtype(cast(Any, dtype), np.datetime64):
-            return self.as_datetime_column(dtype, **kwargs)
+            return col.as_datetime_column(dtype, format=format)
         elif np.issubdtype(cast(Any, dtype), np.timedelta64):
-            return self.as_timedelta_column(dtype, **kwargs)
+            return col.as_timedelta_column(dtype, format=format)
         else:
-            return self.as_numerical_column(dtype, **kwargs)
+            return col.as_numerical_column(dtype)
 
     def as_categorical_column(self, dtype) -> ColumnBase:
         if isinstance(dtype, (cudf.CategoricalDtype, pd.CategoricalDtype)):
@@ -1076,50 +1082,35 @@ def as_categorical_column(self, dtype) -> ColumnBase:
         )
 
     def as_numerical_column(
-        self, dtype: Dtype, **kwargs
+        self, dtype: Dtype
     ) -> "cudf.core.column.NumericalColumn":
         raise NotImplementedError
 
     def as_datetime_column(
-        self, dtype: Dtype, **kwargs
+        self, dtype: Dtype, format: str | None = None
     ) -> "cudf.core.column.DatetimeColumn":
         raise NotImplementedError
 
     def as_interval_column(
-        self, dtype: Dtype, **kwargs
+        self, dtype: Dtype
     ) -> "cudf.core.column.IntervalColumn":
         raise NotImplementedError
 
     def as_timedelta_column(
-        self, dtype: Dtype, **kwargs
+        self, dtype: Dtype, format: str | None = None
     ) -> "cudf.core.column.TimeDeltaColumn":
         raise NotImplementedError
 
     def as_string_column(
-        self, dtype: Dtype, format=None, **kwargs
+        self, dtype: Dtype, format: str | None = None
     ) -> "cudf.core.column.StringColumn":
         raise NotImplementedError
 
     def as_decimal_column(
-        self, dtype: Dtype, **kwargs
+        self, dtype: Dtype
     ) -> Union["cudf.core.column.decimal.DecimalBaseColumn"]:
         raise NotImplementedError
 
-    def as_decimal128_column(
-        self, dtype: Dtype, **kwargs
-    ) -> "cudf.core.column.Decimal128Column":
-        raise NotImplementedError
-
-    def as_decimal64_column(
-        self, dtype: Dtype, **kwargs
-    ) -> "cudf.core.column.Decimal64Column":
-        raise NotImplementedError
-
-    def as_decimal32_column(
-        self, dtype: Dtype, **kwargs
-    ) -> "cudf.core.column.Decimal32Column":
-        raise NotImplementedError
-
     def apply_boolean_mask(self, mask) -> ColumnBase:
         mask = as_column(mask)
         if not is_bool_dtype(mask.dtype):

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

@@ -422,21 +422,23 @@ def __cuda_array_interface__(self) -> Mapping[str, Any]:
             )
         return output
 
-    def as_datetime_column(self, dtype: Dtype, **kwargs) -> DatetimeColumn:
+    def as_datetime_column(
+        self, dtype: Dtype, format: str | None = None
+    ) -> DatetimeColumn:
         dtype = cudf.dtype(dtype)
         if dtype == self.dtype:
             return self
         return libcudf.unary.cast(self, dtype=dtype)
 
     def as_timedelta_column(
-        self, dtype: Dtype, **kwargs
+        self, dtype: Dtype, format: str | None = None
     ) -> "cudf.core.column.TimeDeltaColumn":
         raise TypeError(
             f"cannot astype a datetimelike from {self.dtype} to {dtype}"
         )
 
     def as_numerical_column(
-        self, dtype: Dtype, **kwargs
+        self, dtype: Dtype
     ) -> "cudf.core.column.NumericalColumn":
         col = column.build_column(
             data=self.base_data,
@@ -448,7 +450,7 @@ def as_numerical_column(
         return cast("cudf.core.column.NumericalColumn", col.astype(dtype))
 
     def as_string_column(
-        self, dtype: Dtype, format=None, **kwargs
+        self, dtype: Dtype, format: str | None = None
     ) -> "cudf.core.column.StringColumn":
         if format is None:
             format = _dtype_to_format_conversion.get(
@@ -725,9 +727,9 @@ def _local_time(self):
         return utc_to_local(self, str(self.dtype.tz))
 
     def as_string_column(
-        self, dtype: Dtype, format=None, **kwargs
+        self, dtype: Dtype, format: str | None = None
     ) -> "cudf.core.column.StringColumn":
-        return self._local_time.as_string_column(dtype, format, **kwargs)
+        return self._local_time.as_string_column(dtype, format)
 
     def get_dt_field(self, field: str) -> ColumnBase:
         return libcudf.datetime.extract_datetime_component(