feat: Add cum max and cum_min for DuckDB (#2278)

Author: raisadz

narwhals/_duckdb/expr.py

@@ -79,6 +79,22 @@ def __narwhals_namespace__(self) -> DuckDBNamespace:  # pragma: no cover
             backend_version=self._backend_version, version=self._version
         )
 
+    def _cum_window_func(
+        self, *, reverse: bool, func_name: Literal["sum", "max", "min"]
+    ) -> WindowFunction:
+        def func(window_inputs: WindowInputs) -> duckdb.Expression:
+            order_by_sql = generate_order_by_sql(
+                *window_inputs.order_by, ascending=not reverse
+            )
+            partition_by_sql = generate_partition_by_sql(*window_inputs.partition_by)
+            sql = (
+                f"{func_name} ({window_inputs.expr}) over ({partition_by_sql} {order_by_sql} "
+                "rows between unbounded preceding and current row)"
+            )
+            return SQLExpression(sql)  # type: ignore[no-any-return, unused-ignore]
+
+        return func
+
     def broadcast(self, kind: Literal[ExprKind.AGGREGATION, ExprKind.LITERAL]) -> Self:
         if kind is ExprKind.LITERAL:
             return self
@@ -486,18 +502,19 @@ def func(window_inputs: WindowInputs) -> duckdb.Expression:
         return self._with_window_function(func)
 
     def cum_sum(self, *, reverse: bool) -> Self:
-        def func(window_inputs: WindowInputs) -> duckdb.Expression:
-            order_by_sql = generate_order_by_sql(
-                *window_inputs.order_by, ascending=not reverse
-            )
-            partition_by_sql = generate_partition_by_sql(*window_inputs.partition_by)
-            sql = (
-                f"sum ({window_inputs.expr}) over ({partition_by_sql} {order_by_sql} "
-                "rows between unbounded preceding and current row)"
-            )
-            return SQLExpression(sql)  # type: ignore[no-any-return, unused-ignore]
+        return self._with_window_function(
+            self._cum_window_func(reverse=reverse, func_name="sum")
+        )
 
-        return self._with_window_function(func)
+    def cum_max(self, *, reverse: bool) -> Self:
+        return self._with_window_function(
+            self._cum_window_func(reverse=reverse, func_name="max")
+        )
+
+    def cum_min(self, *, reverse: bool) -> Self:
+        return self._with_window_function(
+            self._cum_window_func(reverse=reverse, func_name="min")
+        )
 
     def rolling_sum(self, window_size: int, *, min_samples: int, center: bool) -> Self:
         if center:
@@ -564,6 +581,4 @@ def struct(self: Self) -> DuckDBExprStructNamespace:
     unique = not_implemented()
     is_unique = not_implemented()
     cum_count = not_implemented()
-    cum_min = not_implemented()
-    cum_max = not_implemented()
     cum_prod = not_implemented()

tests/expr_and_series/cum_max_test.py

@@ -3,6 +3,7 @@
 import pytest
 
 import narwhals.stable.v1 as nw
+from tests.utils import DUCKDB_VERSION
 from tests.utils import PANDAS_VERSION
 from tests.utils import POLARS_VERSION
 from tests.utils import PYARROW_VERSION
@@ -53,9 +54,6 @@ def test_lazy_cum_max_grouped(
     reverse: bool,
     expected_a: list[int],
 ) -> None:
-    if "duckdb" in str(constructor):
-        # no window function support yet in duckdb
-        request.applymarker(pytest.mark.xfail)
     if "pyarrow_table" in str(constructor):
         # grouped window functions not yet supported
         request.applymarker(pytest.mark.xfail)
@@ -64,7 +62,9 @@ def test_lazy_cum_max_grouped(
     if "dask" in str(constructor):
         # https://github.com/dask/dask/issues/11806
         request.applymarker(pytest.mark.xfail)
-    if "polars" in str(constructor) and POLARS_VERSION < (1, 9):
+    if ("polars" in str(constructor) and POLARS_VERSION < (1, 9)) or (
+        "duckdb" in str(constructor) and DUCKDB_VERSION < (1, 3)
+    ):
         pytest.skip(reason="too old version")
     if "cudf" in str(constructor):
         # https://github.com/rapidsai/cudf/issues/18159
@@ -101,9 +101,6 @@ def test_lazy_cum_max_ordered_by_nulls(
     reverse: bool,
     expected_a: list[int],
 ) -> None:
-    if "duckdb" in str(constructor):
-        # no window function support yet in duckdb
-        request.applymarker(pytest.mark.xfail)
     if "pyarrow_table" in str(constructor):
         # grouped window functions not yet supported
         request.applymarker(pytest.mark.xfail)
@@ -112,7 +109,9 @@ def test_lazy_cum_max_ordered_by_nulls(
     if "dask" in str(constructor):
         # https://github.com/dask/dask/issues/11806
         request.applymarker(pytest.mark.xfail)
-    if "polars" in str(constructor) and POLARS_VERSION < (1, 9):
+    if ("polars" in str(constructor) and POLARS_VERSION < (1, 9)) or (
+        "duckdb" in str(constructor) and DUCKDB_VERSION < (1, 3)
+    ):
         pytest.skip(reason="too old version")
     if "cudf" in str(constructor):
         # https://github.com/rapidsai/cudf/issues/18159
@@ -153,15 +152,14 @@ def test_lazy_cum_max_ungrouped(
     reverse: bool,
     expected_a: list[int],
 ) -> None:
-    if "duckdb" in str(constructor):
-        # no window function support yet in duckdb
-        request.applymarker(pytest.mark.xfail)
     if "dask" in str(constructor) and reverse:
         # https://github.com/dask/dask/issues/11802
         request.applymarker(pytest.mark.xfail)
     if "modin" in str(constructor):
         pytest.skip(reason="probably bugged")
-    if "polars" in str(constructor) and POLARS_VERSION < (1, 9):
+    if ("polars" in str(constructor) and POLARS_VERSION < (1, 9)) or (
+        "duckdb" in str(constructor) and DUCKDB_VERSION < (1, 3)
+    ):
         pytest.skip(reason="too old version")
     if PYARROW_VERSION < (13, 0, 0) and "pyarrow_table" in str(constructor):
         request.applymarker(pytest.mark.xfail)
@@ -196,15 +194,14 @@ def test_lazy_cum_max_ungrouped_ordered_by_nulls(
     reverse: bool,
     expected_a: list[int],
 ) -> None:
-    if "duckdb" in str(constructor):
-        # no window function support yet in duckdb
-        request.applymarker(pytest.mark.xfail)
     if "dask" in str(constructor):
         # https://github.com/dask/dask/issues/11806
         request.applymarker(pytest.mark.xfail)
     if "modin" in str(constructor):
         pytest.skip(reason="probably bugged")
-    if "polars" in str(constructor) and POLARS_VERSION < (1, 9):
+    if ("polars" in str(constructor) and POLARS_VERSION < (1, 9)) or (
+        "duckdb" in str(constructor) and DUCKDB_VERSION < (1, 3)
+    ):
         pytest.skip(reason="too old version")
     if PYARROW_VERSION < (13, 0, 0) and "pyarrow_table" in str(constructor):
         request.applymarker(pytest.mark.xfail)

tests/expr_and_series/cum_min_test.py

@@ -3,6 +3,7 @@
 import pytest
 
 import narwhals.stable.v1 as nw
+from tests.utils import DUCKDB_VERSION
 from tests.utils import PANDAS_VERSION
 from tests.utils import POLARS_VERSION
 from tests.utils import PYARROW_VERSION
@@ -53,9 +54,6 @@ def test_lazy_cum_min_grouped(
     reverse: bool,
     expected_a: list[int],
 ) -> None:
-    if "duckdb" in str(constructor):
-        # no window function support yet in duckdb
-        request.applymarker(pytest.mark.xfail)
     if "pyarrow_table" in str(constructor):
         # grouped window functions not yet supported
         request.applymarker(pytest.mark.xfail)
@@ -64,7 +62,9 @@ def test_lazy_cum_min_grouped(
     if "dask" in str(constructor):
         # https://github.com/dask/dask/issues/11806
         request.applymarker(pytest.mark.xfail)
-    if "polars" in str(constructor) and POLARS_VERSION < (1, 9):
+    if ("polars" in str(constructor) and POLARS_VERSION < (1, 9)) or (
+        "duckdb" in str(constructor) and DUCKDB_VERSION < (1, 3)
+    ):
         pytest.skip(reason="too old version")
     if "cudf" in str(constructor):
         # https://github.com/rapidsai/cudf/issues/18159
@@ -101,9 +101,6 @@ def test_lazy_cum_min_ordered_by_nulls(
     reverse: bool,
     expected_a: list[int],
 ) -> None:
-    if "duckdb" in str(constructor):
-        # no window function support yet in duckdb
-        request.applymarker(pytest.mark.xfail)
     if "pyarrow_table" in str(constructor):
         # grouped window functions not yet supported
         request.applymarker(pytest.mark.xfail)
@@ -112,7 +109,9 @@ def test_lazy_cum_min_ordered_by_nulls(
     if "dask" in str(constructor):
         # https://github.com/dask/dask/issues/11806
         request.applymarker(pytest.mark.xfail)
-    if "polars" in str(constructor) and POLARS_VERSION < (1, 9):
+    if ("polars" in str(constructor) and POLARS_VERSION < (1, 9)) or (
+        "duckdb" in str(constructor) and DUCKDB_VERSION < (1, 3)
+    ):
         pytest.skip(reason="too old version")
     if "cudf" in str(constructor):
         # https://github.com/rapidsai/cudf/issues/18159
@@ -153,15 +152,14 @@ def test_lazy_cum_min_ungrouped(
     reverse: bool,
     expected_a: list[int],
 ) -> None:
-    if "duckdb" in str(constructor):
-        # no window function support yet in duckdb
-        request.applymarker(pytest.mark.xfail)
     if "dask" in str(constructor) and reverse:
         # https://github.com/dask/dask/issues/11802
         request.applymarker(pytest.mark.xfail)
     if "modin" in str(constructor):
         pytest.skip(reason="probably bugged")
-    if "polars" in str(constructor) and POLARS_VERSION < (1, 9):
+    if ("polars" in str(constructor) and POLARS_VERSION < (1, 9)) or (
+        "duckdb" in str(constructor) and DUCKDB_VERSION < (1, 3)
+    ):
         pytest.skip(reason="too old version")
     if PYARROW_VERSION < (13, 0, 0) and "pyarrow_table" in str(constructor):
         request.applymarker(pytest.mark.xfail)
@@ -196,15 +194,14 @@ def test_lazy_cum_min_ungrouped_ordered_by_nulls(
     reverse: bool,
     expected_a: list[int],
 ) -> None:
-    if "duckdb" in str(constructor):
-        # no window function support yet in duckdb
-        request.applymarker(pytest.mark.xfail)
     if "dask" in str(constructor):
         # https://github.com/dask/dask/issues/11806
         request.applymarker(pytest.mark.xfail)
     if "modin" in str(constructor):
         pytest.skip(reason="probably bugged")
-    if "polars" in str(constructor) and POLARS_VERSION < (1, 9):
+    if ("polars" in str(constructor) and POLARS_VERSION < (1, 9)) or (
+        "duckdb" in str(constructor) and DUCKDB_VERSION < (1, 3)
+    ):
         pytest.skip(reason="too old version")
     if PYARROW_VERSION < (13, 0, 0) and "pyarrow_table" in str(constructor):
         request.applymarker(pytest.mark.xfail)