feat: add clone for dataframes (#406)

* add clone

* add to lazy frame too

docs/api-reference/dataframe.md

@@ -4,6 +4,7 @@
     handler: python
     options:
       members:
+        - clone
         - columns
         - drop
         - drop_nulls

docs/api-reference/lazyframe.md

@@ -4,6 +4,7 @@
     handler: python
     options:
       members:
+        - clone
         - collect
         - columns
         - drop

narwhals/_arrow/dataframe.py

@@ -151,3 +151,6 @@ def lazy(self) -> Self:
 
     def collect(self) -> ArrowDataFrame:
         return ArrowDataFrame(self._dataframe)
+
+    def clone(self) -> Self:
+        raise NotImplementedError("clone is not yet supported on PyArrow tables")

narwhals/_pandas_like/dataframe.py

@@ -452,3 +452,6 @@ def item(self: Self, row: int | None = None, column: int | str | None = None) ->
 
         _col = self.columns.index(column) if isinstance(column, str) else column
         return self._dataframe.iat[row, _col]
+
+    def clone(self: Self) -> Self:
+        return self._from_dataframe(self._dataframe.copy())

narwhals/dataframe.py

@@ -198,6 +198,9 @@ def join(
             )
         )
 
+    def clone(self) -> Self:
+        return self._from_dataframe(self._dataframe.clone())
+
 
 class DataFrame(BaseFrame):
     """
@@ -1732,6 +1735,42 @@ def item(self: Self, row: int | None = None, column: int | str | None = None) ->
         """
         return self._dataframe.item(row=row, column=column)
 
+    def clone(self) -> Self:
+        r"""
+        Create a copy of this DataFrame.
+
+        Examples:
+            >>> import narwhals as nw
+            >>> import pandas as pd
+            >>> import polars as pl
+            >>> data = {"a": [1, 2], "b": [3, 4]}
+            >>> df_pd = pd.DataFrame(data)
+            >>> df_pl = pl.DataFrame(data)
+
+            Let's define a dataframe-agnostic function in which we clone the DataFrame:
+
+            >>> @nw.narwhalify
+            ... def func(df):
+            ...     return df.clone()
+
+            >>> func(df_pd)
+               a  b
+            0  1  3
+            1  2  4
+
+            >>> func(df_pl)
+            shape: (2, 2)
+            ┌─────┬─────┐
+            │ a   ┆ b   │
+            │ --- ┆ --- │
+            │ i64 ┆ i64 │
+            ╞═════╪═════╡
+            │ 1   ┆ 3   │
+            │ 2   ┆ 4   │
+            └─────┴─────┘
+        """
+        return super().clone()
+
 
 class LazyFrame(BaseFrame):
     """
@@ -2889,3 +2928,38 @@ def join(
             └─────┴─────┴─────┴───────┘
         """
         return super().join(other, how=how, left_on=left_on, right_on=right_on)
+
+    def clone(self) -> Self:
+        r"""
+        Create a copy of this DataFrame.
+
+        >>> import narwhals as nw
+        >>> import pandas as pd
+        >>> import polars as pl
+        >>> data = {"a": [1, 2], "b": [3, 4]}
+        >>> df_pd = pd.DataFrame(data)
+        >>> df_pl = pl.LazyFrame(data)
+
+        Let's define a dataframe-agnostic function in which we copy the DataFrame:
+
+        >>> @nw.narwhalify
+        ... def func(df):
+        ...     return df.clone()
+
+        >>> func(df_pd)
+           a  b
+        0  1  3
+        1  2  4
+
+        >>> func(df_pl).collect()
+        shape: (2, 2)
+        ┌─────┬─────┐
+        │ a   ┆ b   │
+        │ --- ┆ --- │
+        │ i64 ┆ i64 │
+        ╞═════╪═════╡
+        │ 1   ┆ 3   │
+        │ 2   ┆ 4   │
+        └─────┴─────┘
+        """
+        return super().clone()

tests/conftest.py

@@ -52,6 +52,10 @@ def polars_constructor(obj: Any) -> IntoDataFrame:
     return pl.DataFrame(obj)
 
 
+def polars_lazy_constructor(obj: Any) -> pl.LazyFrame:
+    return pl.LazyFrame(obj)
+
+
 if parse_version(pd.__version__) >= parse_version("2.0.0"):
     params = [pandas_constructor, pandas_nullable_constructor, pandas_pyarrow_constructor]
 else:  # pragma: no cover
@@ -66,6 +70,11 @@ def constructor(request: Any) -> Callable[[Any], IntoDataFrame]:
     return request.param  # type: ignore[no-any-return]
 
 
+@pytest.fixture(params=[*params, polars_lazy_constructor])
+def constructor_with_lazy(request: Any) -> Callable[[Any], Any]:
+    return request.param  # type: ignore[no-any-return]
+
+
 # TODO: once pyarrow has complete coverage, we can remove this one,
 # and just put `pa.table` into `constructor`
 @pytest.fixture(params=[*params, pa.table])

tests/frame/clone_test.py

@@ -0,0 +1,13 @@
+from typing import Any
+
+import narwhals as nw
+from tests.utils import compare_dicts
+
+
+def test_clone(constructor_with_lazy: Any) -> None:
+    expected = {"a": [1, 2], "b": [3, 4]}
+    df = nw.from_native(constructor_with_lazy(expected))
+    df_clone = df.clone()
+    assert df is not df_clone
+    assert df._dataframe is not df_clone._dataframe
+    compare_dicts(df_clone, expected)