fix: pyarrow do not combine chunks

narwhals-dev · Dec 27, 2024 · aa63dc8 · aa63dc8
1 parent ecde246
commit aa63dc8
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 6 deletions.
diff --git a/narwhals/_arrow/namespace.py b/narwhals/_arrow/namespace.py
@@ -470,7 +470,7 @@ def __call__(self: Self, df: ArrowDataFrame) -> Sequence[ArrowSeries]:
         except TypeError:
             # `self._otherwise_value` is a scalar and can't be converted to an expression
             value_series = condition.__class__._from_iterable(
-                [self._then_value] * len(condition),
+                pa.repeat(pa.scalar(self._then_value), len(condition)),
                 name="literal",
                 backend_version=self._backend_version,
                 version=self._version,
@@ -480,8 +480,8 @@ def __call__(self: Self, df: ArrowDataFrame) -> Sequence[ArrowSeries]:
         condition_native = condition._native_series.combine_chunks()
 
         if self._otherwise_value is None:
-            otherwise_native = pa.array(
-                [None] * len(condition_native), type=value_series_native.type
+            otherwise_native = pa.repeat(
+                pa.scalar(None, type=value_series_native.type), len(condition_native)
             )
             return [
                 value_series._from_native_series(

diff --git a/narwhals/_arrow/utils.py b/narwhals/_arrow/utils.py
@@ -261,7 +261,7 @@ def vertical_concat(dfs: list[pa.Table]) -> pa.Table:
 
     import pyarrow as pa
 
-    return pa.concat_tables(dfs).combine_chunks()
+    return pa.concat_tables(dfs)
 
 
 def diagonal_concat(dfs: list[pa.Table], backend_version: tuple[int, ...]) -> pa.Table:
@@ -276,7 +276,7 @@ def diagonal_concat(dfs: list[pa.Table], backend_version: tuple[int, ...]) -> pa
         if backend_version < (14, 0, 0)
         else {"promote_options": "default"}  # type: ignore[dict-item]
     )
-    return pa.concat_tables(dfs, **kwargs).combine_chunks()
+    return pa.concat_tables(dfs, **kwargs)
 
 
 def floordiv_compat(left: Any, right: Any) -> Any:
@@ -530,7 +530,7 @@ def pad_series(
         pad_left = pa.array([None] * offset_left, type=native_series.type)
         pad_right = pa.array([None] * offset_right, type=native_series.type)
         padded_arr = series._from_native_series(
-            pa.concat_arrays([pad_left, native_series.combine_chunks(), pad_right])
+            pa.concat_arrays([pad_left, *native_series.chunks, pad_right])
         )
         offset = offset_left + offset_right
     else: