Implement a mixin for reductions

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

@@ -69,6 +69,7 @@
     ListDtype,
     StructDtype,
 )
+from cudf.core.mixins import Reducible
 from cudf.utils import utils
 from cudf.utils.dtypes import (
     cudf_dtype_from_pa_type,
@@ -86,7 +87,14 @@
 Slice = TypeVar("Slice", bound=slice)
 
 
-class ColumnBase(Column, Serializable, NotIterable):
+class ColumnBase(Column, Serializable, Reducible, NotIterable):
+    _VALID_REDUCTIONS = {
+        "any",
+        "all",
+        "max",
+        "min",
+    }
+
     def as_frame(self) -> "cudf.core.frame.Frame":
         """
         Converts a Column to Frame
@@ -674,16 +682,10 @@ def append(self, other: ColumnBase) -> ColumnBase:
         return concat_columns([self, as_column(other)])
 
     def quantile(
-        self,
-        q: Union[float, Sequence[float]],
-        interpolation: builtins.str,
-        exact: bool,
+        self, q: Union[float, Sequence[float]], interpolation: str, exact: bool
     ) -> ColumnBase:
         raise TypeError(f"cannot perform quantile with type {self.dtype}")
 
-    def median(self, skipna: bool = None) -> ScalarLike:
-        raise TypeError(f"cannot perform median with type {self.dtype}")
-
     def take(
         self: T, indices: ColumnBase, nullify: bool = False, check_bounds=True
     ) -> T:
@@ -1162,53 +1164,23 @@ def _minmax(self, skipna: bool = None):
             return libcudf.reduce.minmax(result_col)
         return result_col
 
-    def min(self, skipna: bool = None, dtype: Dtype = None):
-        result_col = self._process_for_reduction(skipna=skipna)
-        if isinstance(result_col, ColumnBase):
-            return libcudf.reduce.reduce("min", result_col, dtype=dtype)
-        return result_col
-
-    def max(self, skipna: bool = None, dtype: Dtype = None):
-        result_col = self._process_for_reduction(skipna=skipna)
-        if isinstance(result_col, ColumnBase):
-            return libcudf.reduce.reduce("max", result_col, dtype=dtype)
-        return result_col
-
-    def sum(
-        self, skipna: bool = None, dtype: Dtype = None, min_count: int = 0
-    ):
-        raise TypeError(f"cannot perform sum with type {self.dtype}")
-
-    def product(
-        self, skipna: bool = None, dtype: Dtype = None, min_count: int = 0
-    ):
-        raise TypeError(f"cannot perform product with type {self.dtype}")
-
-    def mean(self, skipna: bool = None, dtype: Dtype = None):
-        raise TypeError(f"cannot perform mean with type {self.dtype}")
-
-    def std(self, skipna: bool = None, ddof=1, dtype: Dtype = np.float64):
-        raise TypeError(f"cannot perform std with type {self.dtype}")
-
-    def var(self, skipna: bool = None, ddof=1, dtype: Dtype = np.float64):
-        raise TypeError(f"cannot perform var with type {self.dtype}")
-
-    def kurtosis(self, skipna: bool = None):
-        raise TypeError(f"cannot perform kurtosis with type {self.dtype}")
+    def _reduce(
+        self, op: str, skipna: bool = None, min_count: int = 0, *args, **kwargs
+    ) -> ScalarLike:
+        """Compute {op} of column values.
 
-    def skew(self, skipna: bool = None):
-        raise TypeError(f"cannot perform skew with type {self.dtype}")
-
-    def cov(self, other: ColumnBase):
-        raise TypeError(
-            f"cannot perform covarience with types {self.dtype}, "
-            f"{other.dtype}"
-        )
-
-    def corr(self, other: ColumnBase):
-        raise TypeError(
-            f"cannot perform corr with types {self.dtype}, {other.dtype}"
+        skipna : bool
+            Whether or not na values must be skipped.
+        min_count : int, default 0
+            The minimum number of entries for the reduction, otherwise the
+            reduction returns NaN.
+        """
+        preprocessed = self._process_for_reduction(
+            skipna=skipna, min_count=min_count
         )
+        if isinstance(preprocessed, ColumnBase):
+            return libcudf.reduce.reduce(op, preprocessed, **kwargs)
+        return preprocessed
 
     @property
     def contains_na_entries(self) -> bool:

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

@@ -1,4 +1,4 @@
-# Copyright (c) 2019-2021, NVIDIA CORPORATION.
+# Copyright (c) 2019-2022, NVIDIA CORPORATION.
 
 from __future__ import annotations
 
@@ -346,17 +346,27 @@ def as_string_column(
                 column.column_empty(0, dtype="object", masked=False),
             )
 
-    def mean(self, skipna=None, dtype=np.float64) -> ScalarLike:
+    def mean(
+        self, skipna=None, min_count: int = 0, dtype=np.float64
+    ) -> ScalarLike:
         return pd.Timestamp(
-            self.as_numerical.mean(skipna=skipna, dtype=dtype),
+            self.as_numerical.mean(
+                skipna=skipna, min_count=min_count, dtype=dtype
+            ),
             unit=self.time_unit,
         )
 
     def std(
-        self, skipna: bool = None, ddof: int = 1, dtype: Dtype = np.float64
+        self,
+        skipna: bool = None,
+        min_count: int = 0,
+        dtype: Dtype = np.float64,
+        ddof: int = 1,
     ) -> pd.Timedelta:
         return pd.Timedelta(
-            self.as_numerical.std(skipna=skipna, ddof=ddof, dtype=dtype)
+            self.as_numerical.std(
+                skipna=skipna, min_count=min_count, dtype=dtype, ddof=ddof
+            )
             * _numpy_to_pandas_conversion[self.time_unit],
         )
 

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

@@ -1,4 +1,4 @@
-# Copyright (c) 2018-2021, NVIDIA CORPORATION.
+# Copyright (c) 2018-2022, NVIDIA CORPORATION.
 """Define an interface for columns that can perform numerical operations."""
 
 from __future__ import annotations
@@ -10,7 +10,7 @@
 
 import cudf
 from cudf import _lib as libcudf
-from cudf._typing import Dtype, ScalarLike
+from cudf._typing import ScalarLike
 from cudf.core.column import ColumnBase
 
 
@@ -23,59 +23,14 @@ class NumericalBaseColumn(ColumnBase):
     point, should be encoded here.
     """
 
-    def reduce(
-        self, op: str, skipna: bool = None, min_count: int = 0, **kwargs
-    ) -> ScalarLike:
-        """Perform a reduction operation.
-
-        op : str
-            The operation to perform.
-        skipna : bool
-            Whether or not na values must be
-        """
-        preprocessed = self._process_for_reduction(
-            skipna=skipna, min_count=min_count
-        )
-        if isinstance(preprocessed, ColumnBase):
-            return libcudf.reduce.reduce(op, preprocessed, **kwargs)
-        else:
-            return preprocessed
-
-    def sum(
-        self, skipna: bool = None, dtype: Dtype = None, min_count: int = 0
-    ) -> ScalarLike:
-        return self.reduce(
-            "sum", skipna=skipna, dtype=dtype, min_count=min_count
-        )
-
-    def product(
-        self, skipna: bool = None, dtype: Dtype = None, min_count: int = 0
-    ) -> ScalarLike:
-        return self.reduce(
-            "product", skipna=skipna, dtype=dtype, min_count=min_count
-        )
-
-    def mean(
-        self, skipna: bool = None, dtype: Dtype = np.float64
-    ) -> ScalarLike:
-        return self.reduce("mean", skipna=skipna, dtype=dtype)
-
-    def var(
-        self, skipna: bool = None, ddof: int = 1, dtype: Dtype = np.float64
-    ) -> ScalarLike:
-        return self.reduce("var", skipna=skipna, dtype=dtype, ddof=ddof)
-
-    def std(
-        self, skipna: bool = None, ddof: int = 1, dtype: Dtype = np.float64
-    ) -> ScalarLike:
-        return self.reduce("std", skipna=skipna, dtype=dtype, ddof=ddof)
-
-    def sum_of_squares(
-        self, skipna: bool = None, dtype: Dtype = None, min_count: int = 0
-    ) -> ScalarLike:
-        return self.reduce(
-            "sum_of_squares", skipna=skipna, dtype=dtype, min_count=min_count
-        )
+    _VALID_REDUCTIONS = {
+        "sum",
+        "product",
+        "sum_of_squares",
+        "mean",
+        "var",
+        "std",
+    }
 
     def _can_return_nan(self, skipna: bool = None) -> bool:
         return not skipna and self.has_nulls()
@@ -148,6 +103,25 @@ def quantile(
             )
         return result
 
+    def mean(self, skipna: bool = None, min_count: int = 0, dtype=np.float64):
+        return self._reduce(
+            "mean", skipna=skipna, min_count=min_count, dtype=dtype
+        )
+
+    def var(
+        self, skipna: bool = None, min_count: int = 0, dtype=np.float64, ddof=1
+    ):
+        return self._reduce(
+            "var", skipna=skipna, min_count=min_count, dtype=dtype, ddof=ddof
+        )
+
+    def std(
+        self, skipna: bool = None, min_count: int = 0, dtype=np.float64, ddof=1
+    ):
+        return self._reduce(
+            "std", skipna=skipna, min_count=min_count, dtype=dtype, ddof=ddof
+        )
+
     def median(self, skipna: bool = None) -> NumericalBaseColumn:
         skipna = True if skipna is None else skipna
 
@@ -171,7 +145,7 @@ def _numeric_quantile(
             self, quant, interpolation, sorted_indices, exact
         )
 
-    def cov(self, other: ColumnBase) -> float:
+    def cov(self, other: NumericalBaseColumn) -> float:
         if (
             len(self) == 0
             or len(other) == 0
@@ -183,7 +157,7 @@ def cov(self, other: ColumnBase) -> float:
         cov_sample = result.sum() / (len(self) - 1)
         return cov_sample
 
-    def corr(self, other: ColumnBase) -> float:
+    def corr(self, other: NumericalBaseColumn) -> float:
         if len(self) == 0 or len(other) == 0:
             return cudf.utils.dtypes._get_nan_for_dtype(self.dtype)
 

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

@@ -5154,7 +5154,7 @@ def to_arrow(self) -> pa.Array:
             return super().to_arrow()
 
     def sum(
-        self, skipna: bool = None, dtype: Dtype = None, min_count: int = 0
+        self, skipna: bool = None, dtype: Dtype = None, min_count: int = 0,
     ):
         result_col = self._process_for_reduction(
             skipna=skipna, min_count=min_count

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

@@ -1,4 +1,4 @@
-# Copyright (c) 2020-2021, NVIDIA CORPORATION.
+# Copyright (c) 2020-2022, NVIDIA CORPORATION.
 
 from __future__ import annotations
 
@@ -385,20 +385,29 @@ def quantile(
         return result.astype(self.dtype)
 
     def sum(
-        self, skipna: bool = None, dtype: Dtype = None, min_count=0
+        self, skipna: bool = None, min_count: int = 0, dtype: Dtype = None,
     ) -> pd.Timedelta:
         return pd.Timedelta(
-            self.as_numerical.sum(
-                skipna=skipna, dtype=dtype, min_count=min_count
+            # Since sum isn't overriden in Numerical[Base]Column, mypy only
+            # sees the signature from Reducible (which doesn't have the extra
+            # parameters from ColumnBase._reduce) so we have to ignore this.
+            self.as_numerical.sum(  # type: ignore
+                skipna=skipna, min_count=min_count, dtype=dtype
             ),
             unit=self.time_unit,
         )
 
     def std(
-        self, skipna: bool = None, ddof: int = 1, dtype: Dtype = np.float64
+        self,
+        skipna: bool = None,
+        min_count: int = 0,
+        dtype: Dtype = np.float64,
+        ddof: int = 1,
     ) -> pd.Timedelta:
         return pd.Timedelta(
-            self.as_numerical.std(skipna=skipna, ddof=ddof, dtype=dtype),
+            self.as_numerical.std(
+                skipna=skipna, min_count=min_count, ddof=ddof, dtype=dtype
+            ),
             unit=self.time_unit,
         )
 

python/cudf/cudf/core/dataframe.py

@@ -5417,10 +5417,13 @@ def _reduce(
         axis = self._get_axis_from_axis_arg(axis)
 
         if axis == 0:
-            result = [
-                getattr(self._data[col], op)(**kwargs)
-                for col in self._data.names
-            ]
+            try:
+                result = [
+                    getattr(self._data[col], op)(**kwargs)
+                    for col in self._data.names
+                ]
+            except AttributeError:
+                raise TypeError(f"cannot perform {op} with type {self.dtype}")
 
             return Series._from_data(
                 {None: result}, as_index(self._data.names)