Merge branch 'main' into more-dedup-1

Author: dangotbanned

.github/workflows/typing.yml

@@ -32,7 +32,7 @@ jobs:
         # TODO: add more dependencies/backends incrementally
         run: |
           source .venv/bin/activate
-          uv pip install -e ".[tests, typing, core]"
+          uv pip install -e ".[tests, typing, core, pyspark, sqlframe]"
       - name: show-deps
         run: |
           source .venv/bin/activate

docs/api-reference/dataframe.md

@@ -23,6 +23,7 @@
         - is_empty
         - is_unique
         - item
+        - iter_columns
         - iter_rows
         - join
         - join_asof

docs/api-reference/expr_str.md

@@ -11,6 +11,7 @@
         - replace
         - replace_all
         - slice
+        - split
         - starts_with
         - strip_chars
         - tail

docs/api-reference/implementation.md

@@ -0,0 +1,6 @@
+# `narwhals.Implementation`
+
+::: narwhals.Implementation
+    handler: python
+    options:
+      show_source: false

docs/api-reference/index.md

@@ -18,6 +18,7 @@
 - [narwhals.Series.list](series_list.md)
 - [narwhals.Series.str](series_str.md)
 - [narwhals.dependencies](dependencies.md)
+- [narwhals.Implementation](implementation.md)
 - [narwhals.dtypes](dtypes.md)
 - [narwhals.exceptions](exceptions.md)
 - [narwhals.selectors](selectors.md)

docs/api-reference/series_str.md

@@ -11,6 +11,7 @@
         - replace
         - replace_all
         - slice
+        - split
         - starts_with
         - strip_chars
         - tail

mkdocs.yml

@@ -59,6 +59,7 @@ nav:
     - api-reference/series_list.md
     - api-reference/series_str.md
     - api-reference/dependencies.md
+    - api-reference/implementation.md
     - api-reference/dtypes.md
     - api-reference/exceptions.md
     - api-reference/selectors.md

narwhals/_arrow/dataframe.py

@@ -153,6 +153,17 @@ def rows(self: Self, *, named: bool) -> list[tuple[Any, ...]] | list[dict[str, A
             return list(self.iter_rows(named=False, buffer_size=512))  # type: ignore[return-value]
         return self._native_frame.to_pylist()
 
+    def iter_columns(self) -> Iterator[ArrowSeries]:
+        from narwhals._arrow.series import ArrowSeries
+
+        for name, series in zip(self.columns, self._native_frame.itercolumns()):
+            yield ArrowSeries(
+                series,
+                name=name,
+                backend_version=self._backend_version,
+                version=self._version,
+            )
+
     def iter_rows(
         self: Self, *, named: bool, buffer_size: int
     ) -> Iterator[tuple[Any, ...]] | Iterator[dict[str, Any]]:

narwhals/_arrow/expr_str.py

@@ -67,6 +67,11 @@ def slice(self: Self, offset: int, length: int | None) -> ArrowExpr:
             self._compliant_expr, "str", "slice", offset=offset, length=length
         )
 
+    def split(self: Self, by: str) -> ArrowExpr:
+        return reuse_series_namespace_implementation(
+            self._compliant_expr, "str", "split", by=by
+        )
+
     def to_datetime(self: Self, format: str | None) -> ArrowExpr:  # noqa: A002
         return reuse_series_namespace_implementation(
             self._compliant_expr, "str", "to_datetime", format=format

narwhals/_arrow/series_str.py

@@ -72,6 +72,10 @@ def slice(self: Self, offset: int, length: int | None) -> ArrowSeries:
             )
         )
 
+    def split(self: Self, by: str) -> ArrowSeries:
+        split_series = pc.split_pattern(self._compliant_series._native_series, by)  # type: ignore[call-overload]
+        return self._compliant_series._from_native_series(split_series)
+
     def to_datetime(self: Self, format: str | None) -> ArrowSeries:  # noqa: A002
         native = self._compliant_series._native_series
         format = parse_datetime_format(native) if format is None else format