cudf-polars-cu12 25.2.1__py3-none-any.whl → 25.4.0__py3-none-any.whl

cudf_polars/dsl/expressions/selection.py

@@ -1,4 +1,4 @@
-# SPDX-FileCopyrightText: Copyright (c) 2024 NVIDIA CORPORATION & AFFILIATES.
+# SPDX-FileCopyrightText: Copyright (c) 2024-2025, NVIDIA CORPORATION & AFFILIATES.
 # SPDX-License-Identifier: Apache-2.0
 # TODO: remove need for this
 # ruff: noqa: D101
@@ -50,7 +50,7 @@ class Gather(Expr):
         n = df.num_rows
         if hi >= n or lo < -n:
             raise ValueError("gather indices are out of bounds")
-        if indices.obj.null_count():
+        if indices.null_count:
             bounds_policy = plc.copying.OutOfBoundsPolicy.NULLIFY
             obj = plc.replace.replace_nulls(
                 indices.obj,

cudf_polars/dsl/expressions/slicing.py

@@ -0,0 +1,53 @@
+# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES.
+# SPDX-License-Identifier: Apache-2.0
+# TODO: remove need for this
+# ruff: noqa: D101
+"""Slicing DSL nodes."""
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+from cudf_polars.dsl.expressions.base import (
+    ExecutionContext,
+    Expr,
+)
+
+if TYPE_CHECKING:
+    from collections.abc import Mapping
+
+    import pylibcudf as plc
+
+    from cudf_polars.containers import Column, DataFrame
+
+
+__all__ = ["Slice"]
+
+
+class Slice(Expr):
+    __slots__ = ("length", "offset")
+    _non_child = ("dtype", "offset", "length")
+
+    def __init__(
+        self,
+        dtype: plc.DataType,
+        offset: int,
+        length: int,
+        column: Expr,
+    ) -> None:
+        self.dtype = dtype
+        self.offset = offset
+        self.length = length
+        self.children = (column,)
+
+    def do_evaluate(
+        self,
+        df: DataFrame,
+        *,
+        context: ExecutionContext = ExecutionContext.FRAME,
+        mapping: Mapping[Expr, Column] | None = None,
+    ) -> Column:
+        """Evaluate this expression given a dataframe for context."""
+        (child,) = self.children
+        column = child.evaluate(df, context=context, mapping=mapping)
+        return column.slice((self.offset, self.length))

cudf_polars/dsl/expressions/sorting.py

@@ -1,4 +1,4 @@
-# SPDX-FileCopyrightText: Copyright (c) 2024 NVIDIA CORPORATION & AFFILIATES.
+# SPDX-FileCopyrightText: Copyright (c) 2024-2025, NVIDIA CORPORATION & AFFILIATES.
 # SPDX-License-Identifier: Apache-2.0
 # TODO: remove need for this
 # ruff: noqa: D101

cudf_polars/dsl/expressions/string.py

@@ -210,7 +210,7 @@ class StringFunction(Expr):
             (child,) = self.children
             column = child.evaluate(df, context=context, mapping=mapping)
             delimiter, ignore_nulls = self.options
-            if column.obj.null_count() > 0 and not ignore_nulls:
+            if column.null_count > 0 and not ignore_nulls:
                 return Column(plc.Column.all_null_like(column.obj, 1))
             return Column(
                 plc.strings.combine.join_strings(
@@ -228,7 +228,7 @@ class StringFunction(Expr):
                 pat = arg.evaluate(df, context=context, mapping=mapping)
                 pattern = (
                     pat.obj_scalar
-                    if pat.is_scalar and pat.obj.size() != column.obj.size()
+                    if pat.is_scalar and pat.size != column.size
                     else pat.obj
                 )
                 return Column(plc.strings.find.contains(column.obj, pattern))
@@ -298,7 +298,7 @@ class StringFunction(Expr):
                 plc.strings.find.ends_with(
                     column.obj,
                     suffix.obj_scalar
-                    if column.obj.size() != suffix.obj.size() and suffix.is_scalar
+                    if column.size != suffix.size and suffix.is_scalar
                     else suffix.obj,
                 )
             )
@@ -308,7 +308,7 @@ class StringFunction(Expr):
                 plc.strings.find.starts_with(
                     column.obj,
                     prefix.obj_scalar
-                    if column.obj.size() != prefix.obj.size() and prefix.is_scalar
+                    if column.size != prefix.size and prefix.is_scalar
                     else prefix.obj,
                 )
             )

cudf_polars/dsl/expressions/unary.py

@@ -1,4 +1,4 @@
-# SPDX-FileCopyrightText: Copyright (c) 2024 NVIDIA CORPORATION & AFFILIATES.
+# SPDX-FileCopyrightText: Copyright (c) 2024-2025, NVIDIA CORPORATION & AFFILIATES.
 # SPDX-License-Identifier: Apache-2.0
 # TODO: remove need for this
 """DSL nodes for unary operations."""
@@ -119,6 +119,7 @@ class UnaryFunction(Expr):
         "abs": plc.unary.UnaryOperator.ABS,
         "bit_invert": plc.unary.UnaryOperator.BIT_INVERT,
         "not": plc.unary.UnaryOperator.NOT,
+        "negate": plc.unary.UnaryOperator.NEGATE,
     }
     _supported_misc_fns = frozenset(
         {
@@ -235,7 +236,7 @@ class UnaryFunction(Expr):
                 else plc.types.Order.DESCENDING
             )
             null_order = plc.types.NullOrder.BEFORE
-            if column.obj.null_count() > 0 and (n := column.obj.size()) > 1:
+            if column.null_count > 0 and (n := column.size) > 1:
                 # PERF: This invokes four stream synchronisations!
                 has_nulls_first = not plc.copying.get_element(column.obj, 0).is_valid()
                 has_nulls_last = not plc.copying.get_element(