RFC, feat: add .select (by str) for duckdb and ibis backend (#1266)

Author: FBruzzesi

docs/extending.md

@@ -37,6 +37,7 @@ def func(df: FrameT) -> FrameT:
         b_std=nw.col("b").std(),
     )
 ```
+
 will work for any of pandas, Polars, cuDF, Modin, and PyArrow.
 
 However, sometimes you don't need to do complex operations on dataframes - all you need
@@ -57,9 +58,21 @@ def func(df: Any) -> Schema:
     df = nw.from_native(df, eager_or_interchange_only=True)
     return df.schema
 ```
+
 is also supported, meaning that, in addition to the libraries mentioned above, you can
 also pass Ibis, DuckDB, Vaex, and any library which implements the protocol.
 
+#### Interchange-only support
+
+While libraries for which we have full support can benefit from the whole Narwhals API,
+libraries which have interchange only support can access the following methods after 
+converting to Narwhals DataFrame:
+
+- `.schema`, hence column names via `.schema.names()` and column types via `.schema.dtypes()`
+- `.to_pandas()` and `.to_arrow()`, for converting to Pandas and Arrow, respectively.
+- `.select(names)` (Ibis and DuckDB), where `names` is a list of (string) column names. This is useful for
+  selecting columns before converting to another library.
+
 ### Extending Narwhals
 
 If you want your own library to be recognised too, you're welcome open a PR (with tests)!.

docs/index.md

@@ -6,7 +6,7 @@ Extremely lightweight and extensible compatibility layer between dataframe libra
 
 - **Full API support**: cuDF, Modin, pandas, Polars, PyArrow
 - **Lazy-only support**: Dask
-- **Interchange-level support**: Ibis, Vaex, anything else which implements the DataFrame Interchange Protocol
+- **Interchange-level support**: Ibis, DuckDB, Vaex, anything else which implements the DataFrame Interchange Protocol
 
 Seamlessly support all, without depending on any!
 

narwhals/_duckdb/dataframe.py

@@ -90,6 +90,22 @@ def __getitem__(self, item: str) -> DuckDBInterchangeSeries:
             self._native_frame.select(item), dtypes=self._dtypes
         )
 
+    def select(
+        self: Self,
+        *exprs: Any,
+        **named_exprs: Any,
+    ) -> Self:
+        if named_exprs or not all(isinstance(x, str) for x in exprs):  # pragma: no cover
+            msg = (
+                "`select`-ing not by name is not supported for DuckDB backend.\n\n"
+                "If you would like to see this kind of object better supported in "
+                "Narwhals, please open a feature request "
+                "at https://github.com/narwhals-dev/narwhals/issues."
+            )
+            raise NotImplementedError(msg)
+
+        return self._from_native_frame(self._native_frame.select(*exprs))
+
     def __getattr__(self, attr: str) -> Any:
         if attr == "schema":
             return {
@@ -120,3 +136,6 @@ def to_pandas(self: Self) -> pd.DataFrame:
 
     def to_arrow(self: Self) -> pa.Table:
         return self._native_frame.arrow()
+
+    def _from_native_frame(self: Self, df: Any) -> Self:
+        return self.__class__(df, dtypes=self._dtypes)

narwhals/_ibis/dataframe.py

@@ -85,6 +85,24 @@ def to_pandas(self: Self) -> pd.DataFrame:
     def to_arrow(self: Self) -> pa.Table:
         return self._native_frame.to_pyarrow()
 
+    def select(
+        self: Self,
+        *exprs: Any,
+        **named_exprs: Any,
+    ) -> Self:
+        if named_exprs or not all(isinstance(x, str) for x in exprs):  # pragma: no cover
+            msg = (
+                "`select`-ing not by name is not supported for Ibis backend.\n\n"
+                "If you would like to see this kind of object better supported in "
+                "Narwhals, please open a feature request "
+                "at https://github.com/narwhals-dev/narwhals/issues."
+            )
+            raise NotImplementedError(msg)
+
+        import ibis.selectors as s
+
+        return self._from_native_frame(self._native_frame.select(s.cols(*exprs)))
+
     def __getattr__(self, attr: str) -> Any:
         if attr == "schema":
             return {
@@ -98,3 +116,6 @@ def __getattr__(self, attr: str) -> Any:
             "at https://github.com/narwhals-dev/narwhals/issues."
         )
         raise NotImplementedError(msg)
+
+    def _from_native_frame(self: Self, df: Any) -> Self:
+        return self.__class__(df, dtypes=self._dtypes)

tests/frame/interchange_select_test.py

@@ -0,0 +1,46 @@
+from __future__ import annotations
+
+import duckdb
+import polars as pl
+import pytest
+
+import narwhals.stable.v1 as nw
+
+data = {"a": [1, 2, 3], "b": [4.0, 5.0, 6.1], "z": ["x", "y", "z"]}
+
+
+def test_interchange() -> None:
+    df_pl = pl.DataFrame(data)
+    df = nw.from_native(df_pl.__dataframe__(), eager_or_interchange_only=True)
+    with pytest.raises(
+        NotImplementedError,
+        match="Attribute select is not supported for metadata-only dataframes",
+    ):
+        df.select("a", "z")
+
+
+def test_interchange_ibis(
+    tmpdir: pytest.TempdirFactory,
+) -> None:  # pragma: no cover
+    ibis = pytest.importorskip("ibis")
+    df_pl = pl.DataFrame(data)
+
+    filepath = str(tmpdir / "file.parquet")  # type: ignore[operator]
+    df_pl.write_parquet(filepath)
+
+    tbl = ibis.read_parquet(filepath)
+    df = nw.from_native(tbl, eager_or_interchange_only=True)
+
+    out_cols = df.select("a", "z").schema.names()
+
+    assert out_cols == ["a", "z"]
+
+
+def test_interchange_duckdb() -> None:
+    df_pl = pl.DataFrame(data)  # noqa: F841
+    rel = duckdb.sql("select * from df_pl")
+    df = nw.from_native(rel, eager_or_interchange_only=True)
+
+    out_cols = df.select("a", "z").schema.names()
+
+    assert out_cols == ["a", "z"]