feat(python)!: Restrict certain function parameters to be keyword-only (

#6464)
pola-rs · Jan 26, 2023 · bc9dc6d · bc9dc6d
1 parent c0d5139
commit bc9dc6d
Show file tree

Hide file tree

Showing 6 changed files with 18 additions and 9 deletions.
diff --git a/py-polars/polars/internals/dataframe/frame.py b/py-polars/polars/internals/dataframe/frame.py
@@ -2948,6 +2948,7 @@ def replace_at_idx(self: DF, index: int, series: pli.Series) -> DF:
     def sort(
         self: DF,
         by: str | pli.Expr | Sequence[str] | Sequence[pli.Expr],
+        *,
         reverse: bool | list[bool] = False,
         nulls_last: bool = False,
     ) -> DF | DataFrame:
@@ -3004,7 +3005,11 @@ def sort(
 
         """
         if not isinstance(by, str) and isinstance(by, (Sequence, pli.Expr)):
-            df = self.lazy().sort(by, reverse, nulls_last).collect(no_optimization=True)
+            df = (
+                self.lazy()
+                .sort(by, reverse=reverse, nulls_last=nulls_last)
+                .collect(no_optimization=True)
+            )
             return df
         return self._from_pydf(self._df.sort(by, reverse, nulls_last))
 
@@ -3439,6 +3444,7 @@ def with_row_count(self: DF, name: str = "row_nr", offset: int = 0) -> DF:
     def groupby(
         self: DF,
         by: str | pli.Expr | Sequence[str | pli.Expr],
+        *,
         maintain_order: bool = False,
     ) -> GroupBy[DF]:
         """
@@ -5228,8 +5234,8 @@ def unstack(
     def partition_by(
         self: DF,
         groups: str | Sequence[str],
-        maintain_order: bool = False,
         *,
+        maintain_order: bool = ...,
         as_dict: Literal[False] = ...,
     ) -> list[DF]:
         ...
@@ -5238,8 +5244,8 @@ def partition_by(
     def partition_by(
         self: DF,
         groups: str | Sequence[str],
-        maintain_order: bool = False,
         *,
+        maintain_order: bool = ...,
         as_dict: Literal[True],
     ) -> dict[Any, DF]:
         ...
@@ -5248,17 +5254,17 @@ def partition_by(
     def partition_by(
         self: DF,
         groups: str | Sequence[str],
-        maintain_order: bool,
         *,
+        maintain_order: bool,
         as_dict: bool,
     ) -> list[DF] | dict[Any, DF]:
         ...
 
     def partition_by(
         self: DF,
         groups: str | Sequence[str],
-        maintain_order: bool = True,
         *,
+        maintain_order: bool = True,
         as_dict: bool = False,
     ) -> list[DF] | dict[Any, DF]:
         """

diff --git a/py-polars/polars/internals/dataframe/groupby.py b/py-polars/polars/internals/dataframe/groupby.py
@@ -300,7 +300,7 @@ def head(self, n: int = 5) -> DF:
         df = (
             pli.wrap_df(self._df)
             .lazy()
-            .groupby(self.by, self.maintain_order)
+            .groupby(self.by, maintain_order=self.maintain_order)
             .head(n)
             .collect(no_optimization=True)
         )
@@ -355,7 +355,7 @@ def tail(self, n: int = 5) -> DF:
         df = (
             pli.wrap_df(self._df)
             .lazy()
-            .groupby(self.by, self.maintain_order)
+            .groupby(self.by, maintain_order=self.maintain_order)
             .tail(n)
             .collect(no_optimization=True)
         )

diff --git a/py-polars/polars/internals/expr/expr.py b/py-polars/polars/internals/expr/expr.py
@@ -1912,6 +1912,7 @@ def search_sorted(
     def sort_by(
         self,
         by: Expr | str | list[Expr | str],
+        *,
         reverse: bool | list[bool] = False,
     ) -> Expr:
         """

diff --git a/py-polars/polars/internals/lazyframe/frame.py b/py-polars/polars/internals/lazyframe/frame.py
@@ -855,6 +855,7 @@ def sort(
             | Sequence[pli.Expr]
             | Sequence[str | pli.Expr]
         ),
+        *,
         reverse: bool | Sequence[bool] = False,
         nulls_last: bool = False,
     ) -> LDF:
@@ -1684,6 +1685,7 @@ def select(
     def groupby(
         self: LDF,
         by: str | pli.Expr | Sequence[str | pli.Expr],
+        *,
         maintain_order: bool = False,
     ) -> LazyGroupBy[LDF]:
         """

diff --git a/py-polars/tests/unit/test_errors.py b/py-polars/tests/unit/test_errors.py
@@ -293,7 +293,7 @@ def test_invalid_sort_by() -> None:
         pl.ComputeError,
         match="The sortby operation produced a different length than the Series that has to be sorted.",  # noqa: E501
     ):
-        df.select(pl.col("a").filter(pl.col("b") == "M").sort_by("c", True))
+        df.select(pl.col("a").filter(pl.col("b") == "M").sort_by("c", reverse=True))
 
 
 def test_epoch_time_type() -> None:

diff --git a/py-polars/tests/unit/test_groupby.py b/py-polars/tests/unit/test_groupby.py
@@ -66,7 +66,7 @@ def test_groupby() -> None:
 
     # Invalid input: `by` not specified as a sequence
     with pytest.raises(TypeError):
-        df.groupby("a", "b")  # type: ignore[arg-type]
+        df.groupby("a", "b")  # type: ignore[arg-type, misc]
 
 
 def test_groupby_iteration() -> None: