Final bits

Author: wence-

python/cudf_polars/cudf_polars/dsl/utils/rolling.py

@@ -76,16 +76,14 @@ def rewrite_rolling(
     if plc.traits.is_integral(index_dtype) and index_dtype.id() != plc.TypeId.INT64:
         index_dtype = plc.DataType(plc.TypeId.INT64)
     index = expr.NamedExpr(index_name, index_col)
-    if len(aggs) == 0:
-        inp = ir.Select(schema, [*keys, index], True, inp)  # noqa: FBT003
-        if options.slice is not None:
-            offset, length = options.slice
-            return ir.Slice(schema, offset, length, inp)
-        return inp
     temp_prefix = "_" * max(map(len, schema))
-    aggs, rolling_schema, apply_post_evaluation = apply_pre_evaluation(
-        schema, keys, aggs, unique_names(temp_prefix), index
-    )
+    if len(aggs) > 0:
+        aggs, rolling_schema, apply_post_evaluation = apply_pre_evaluation(
+            schema, keys, aggs, unique_names(temp_prefix), index
+        )
+    else:
+        rolling_schema = schema
+        apply_post_evaluation = lambda inp: inp  # noqa: E731
     preceding, following = offsets_to_windows(
         index_dtype, options.rolling.offset, options.rolling.period
     )

python/cudf_polars/cudf_polars/dsl/utils/windows.py

@@ -9,6 +9,8 @@
 
 import pyarrow as pa
 
+import polars as pl
+
 import pylibcudf as plc
 
 if TYPE_CHECKING:
@@ -68,6 +70,8 @@ def duration_to_int(
         raise NotImplementedError(
             "Invalid duration for parsed_int"
         )  # pragma: no cover; polars raises first
+    elif not parsed_int and dtype.id() == plc.TypeId.INT64:
+        raise pl.exceptions.InvalidOperationError("Duration must be a parsed integer")
     value = nanoseconds + 24 * 60 * 60 * 10**9 * (days + 7 * weeks)
     return -value if negative else value
 

python/cudf_polars/cudf_polars/testing/plugin.py

@@ -176,6 +176,7 @@ def pytest_configure(config: pytest.Config) -> None:
     "tests/unit/operations/test_group_by.py::test_group_by_binary_agg_with_literal": "Incorrect broadcasting of literals in groupby-agg",
     "tests/unit/operations/test_group_by.py::test_group_by_lit_series": "Incorrect broadcasting of literals in groupby-agg",
     "tests/unit/operations/test_join.py::test_cross_join_slice_pushdown": "Need to implement slice pushdown for cross joins",
+    "tests/unit/operations/test_rolling.py::test_rolling_group_by_empty_groups_by_take_6330": "Ordering difference, might be polars bug",
     "tests/unit/sql/test_cast.py::test_cast_errors[values0-values::uint8-conversion from `f64` to `u64` failed]": "Casting that raises not supported on GPU",
     "tests/unit/sql/test_cast.py::test_cast_errors[values1-values::uint4-conversion from `i64` to `u32` failed]": "Casting that raises not supported on GPU",
     "tests/unit/sql/test_cast.py::test_cast_errors[values2-values::int1-conversion from `i64` to `i8` failed]": "Casting that raises not supported on GPU",

python/cudf_polars/tests/expressions/test_rolling.py

@@ -104,6 +104,12 @@ def test_orderby_nulls_raises_computeerror():
         q.collect(engine=pl.GPUEngine(raise_on_fail=True))
 
 
+def test_invalid_duration_spec_raises_in_translation():
+    df = pl.LazyFrame({"orderby": [1, 2, 4, 5], "values": [1, 2, 3, 4]})
+    q = df.select(pl.col("values").sum().rolling("orderby", period="3d"))
+    assert_ir_translation_raises(q, pl.exceptions.InvalidOperationError)
+
+
 def test_grouped_rolling():
     df = pl.LazyFrame({"a": [1, 2, 3, 4, 5, 6], "b": [1, 2, 1, 3, 1, 2]})