refactor: Move/remove private Compliant*Frame methods (#2934)

Author: dangotbanned

narwhals/_compliant/dataframe.py

@@ -258,13 +258,6 @@ def write_csv(self, file: str | Path | BytesIO) -> None: ...
     def write_csv(self, file: str | Path | BytesIO | None) -> str | None: ...
     def write_parquet(self, file: str | Path | BytesIO) -> None: ...
 
-    def _evaluate_aliases(self, *exprs: CompliantExprT_contra) -> list[str]:
-        it = (expr._evaluate_aliases(self) for expr in exprs)
-        return list(chain.from_iterable(it))
-
-    def _check_columns_exist(self, subset: Sequence[str]) -> ColumnNotFoundError | None:
-        return check_columns_exist(subset, available=self.columns)
-
 
 class CompliantLazyFrame(
     _StoresNative[NativeFrameT],
@@ -357,17 +350,6 @@ def unpivot(
     ) -> Self: ...
     def with_columns(self, *exprs: CompliantExprT_contra) -> Self: ...
     def with_row_index(self, name: str, order_by: Sequence[str]) -> Self: ...
-    def _evaluate_expr(self, expr: CompliantExprT_contra, /) -> Any:
-        result = expr(self)
-        assert len(result) == 1  # debug assertion  # noqa: S101
-        return result[0]
-
-    def _evaluate_aliases(self, *exprs: CompliantExprT_contra) -> list[str]:
-        it = (expr._evaluate_aliases(self) for expr in exprs)
-        return list(chain.from_iterable(it))
-
-    def _check_columns_exist(self, subset: Sequence[str]) -> ColumnNotFoundError | None:
-        return check_columns_exist(subset, available=self.columns)
 
 
 class EagerDataFrame(
@@ -391,6 +373,9 @@ def _with_native(
         self, df: NativeFrameT, *, validate_column_names: bool = True
     ) -> Self: ...
 
+    def _check_columns_exist(self, subset: Sequence[str]) -> ColumnNotFoundError | None:
+        return check_columns_exist(subset, available=self.columns)
+
     def _evaluate_expr(self, expr: EagerExprT, /) -> EagerSeriesT:
         """Evaluate `expr` and ensure it has a **single** output."""
         result: Sequence[EagerSeriesT] = expr(self)

narwhals/_compliant/group_by.py

@@ -1,12 +1,14 @@
 from __future__ import annotations
 
 import re
+from itertools import chain
 from typing import TYPE_CHECKING, Any, Callable, ClassVar, Protocol, TypeVar
 
 from narwhals._compliant.typing import (
     CompliantDataFrameAny,
     CompliantDataFrameT_co,
     CompliantExprT_contra,
+    CompliantFrameT,
     CompliantFrameT_co,
     CompliantLazyFrameAny,
     DepthTrackingExprAny,
@@ -17,7 +19,9 @@
 from narwhals._utils import is_sequence_of
 
 if TYPE_CHECKING:
-    from collections.abc import Iterator, Mapping, Sequence
+    from collections.abc import Iterable, Iterator, Mapping, Sequence
+
+    from narwhals._compliant.expr import CompliantExpr
 
     _SameFrameT = TypeVar("_SameFrameT", CompliantDataFrameAny, CompliantLazyFrameAny)
 
@@ -32,6 +36,13 @@
 _RE_LEAF_NAME: re.Pattern[str] = re.compile(r"(\w+->)")
 
 
+def _evaluate_aliases(
+    frame: CompliantFrameT, exprs: Iterable[CompliantExpr[CompliantFrameT, Any]], /
+) -> list[str]:
+    it = (expr._evaluate_aliases(frame) for expr in exprs)
+    return list(chain.from_iterable(it))
+
+
 class CompliantGroupBy(Protocol[CompliantFrameT_co, CompliantExprT_contra]):
     _compliant_frame: Any
 
@@ -98,7 +109,7 @@ def _temporary_name(key: str) -> str:
             key_str = str(key)  # pandas allows non-string column names :sob:
             return f"_{key_str}_tmp{'_' * (tmp_name_length - len(key_str) - 5)}"
 
-        output_names = compliant_frame._evaluate_aliases(*keys)
+        output_names = _evaluate_aliases(compliant_frame, keys)
 
         safe_keys = [
             # multi-output expression cannot have duplicate names, hence it's safe to suffix
@@ -110,7 +121,7 @@ def _temporary_name(key: str) -> str:
         ]
         return (
             compliant_frame.with_columns(*safe_keys),
-            compliant_frame._evaluate_aliases(*safe_keys),
+            _evaluate_aliases(compliant_frame, safe_keys),
             output_names,
         )
 

narwhals/_dask/dataframe.py

@@ -13,6 +13,7 @@
     ValidateBackendVersion,
     _remap_full_join_keys,
     check_column_names_are_unique,
+    check_columns_exist,
     generate_temporary_column_name,
     not_implemented,
     parse_columns_to_drop,
@@ -35,6 +36,7 @@
     from narwhals._utils import Version, _LimitedContext
     from narwhals.dataframe import LazyFrame
     from narwhals.dtypes import DType
+    from narwhals.exceptions import ColumnNotFoundError
     from narwhals.typing import AsofJoinStrategy, JoinStrategy, LazyUniqueKeepStrategy
 
 Incomplete: TypeAlias = "Any"
@@ -97,6 +99,9 @@ def _with_version(self, version: Version) -> Self:
     def _with_native(self, df: Any) -> Self:
         return self.__class__(df, version=self._version)
 
+    def _check_columns_exist(self, subset: Sequence[str]) -> ColumnNotFoundError | None:
+        return check_columns_exist(subset, available=self.columns)
+
     def _iter_columns(self) -> Iterator[dx.Series]:
         for _col, ser in self.native.items():  # noqa: PERF102
             yield ser

narwhals/_ibis/dataframe.py

@@ -8,6 +8,7 @@
 import ibis.expr.types as ir
 
 from narwhals._ibis.utils import evaluate_exprs, native_to_narwhals_dtype
+from narwhals._sql.dataframe import SQLLazyFrame
 from narwhals._utils import (
     Implementation,
     ValidateBackendVersion,
@@ -16,7 +17,6 @@
     parse_columns_to_drop,
 )
 from narwhals.exceptions import ColumnNotFoundError, InvalidOperationError
-from narwhals.typing import CompliantLazyFrame
 
 if TYPE_CHECKING:
     from collections.abc import Iterable, Iterator, Mapping, Sequence
@@ -43,9 +43,7 @@
 
 
 class IbisLazyFrame(
-    CompliantLazyFrame[
-        "IbisExpr", "ir.Table", "LazyFrame[ir.Table] | DataFrameV1[ir.Table]"
-    ],
+    SQLLazyFrame["IbisExpr", "ir.Table", "LazyFrame[ir.Table] | DataFrameV1[ir.Table]"],
     ValidateBackendVersion,
 ):
     _implementation = Implementation.IBIS

narwhals/_polars/dataframe.py

@@ -15,7 +15,6 @@
 from narwhals._utils import (
     Implementation,
     _into_arrow_table,
-    check_columns_exist,
     convert_str_slice_to_int_slice,
     is_compliant_series,
     is_index_selector,
@@ -165,11 +164,6 @@ def _with_version(self, version: Version) -> Self:
     def from_native(cls, data: NativePolarsFrame, /, *, context: _LimitedContext) -> Self:
         return cls(data, version=context._version)
 
-    def _check_columns_exist(self, subset: Sequence[str]) -> ColumnNotFoundError | None:
-        return check_columns_exist(  # pragma: no cover
-            subset, available=self.columns
-        )
-
     def simple_select(self, *column_names: str) -> Self:
         return self._with_native(self.native.select(*column_names))
 
@@ -263,9 +257,6 @@ class PolarsDataFrame(PolarsBaseFrame[pl.DataFrame]):
     write_csv: Method[Any]
     write_parquet: Method[None]
 
-    # CompliantDataFrame
-    _evaluate_aliases: Any
-
     @classmethod
     def from_arrow(cls, data: IntoArrowTable, /, *, context: _LimitedContext) -> Self:
         if context._implementation._backend_version() >= (1, 3):
@@ -558,10 +549,7 @@ def join(
 
 
 class PolarsLazyFrame(PolarsBaseFrame[pl.LazyFrame]):
-    # CompliantLazyFrame
     sink_parquet: Method[None]
-    _evaluate_expr: Any
-    _evaluate_aliases: Any
 
     @staticmethod
     def _is_native(obj: pl.LazyFrame | Any) -> TypeIs[pl.LazyFrame]:

narwhals/_sql/dataframe.py

@@ -5,12 +5,16 @@
 from narwhals._compliant.dataframe import CompliantLazyFrame
 from narwhals._compliant.typing import CompliantExprT_contra, NativeExprT, NativeFrameT
 from narwhals._translate import ToNarwhalsT_co
+from narwhals._utils import check_columns_exist
 
 if TYPE_CHECKING:
+    from collections.abc import Sequence
+
     from typing_extensions import Self, TypeAlias
 
     from narwhals._compliant.window import WindowInputs
     from narwhals._sql.expr import SQLExpr
+    from narwhals.exceptions import ColumnNotFoundError
 
     Incomplete: TypeAlias = Any
 
@@ -28,3 +32,11 @@ def _evaluate_window_expr(
         result = expr.window_function(self, window_inputs)
         assert len(result) == 1  # debug assertion  # noqa: S101
         return result[0]
+
+    def _evaluate_expr(self, expr: CompliantExprT_contra, /) -> Any:
+        result = expr(self)
+        assert len(result) == 1  # debug assertion  # noqa: S101
+        return result[0]
+
+    def _check_columns_exist(self, subset: Sequence[str]) -> ColumnNotFoundError | None:
+        return check_columns_exist(subset, available=self.columns)

narwhals/dataframe.py

@@ -24,6 +24,7 @@
 from narwhals._utils import (
     Implementation,
     Version,
+    check_columns_exist,
     flatten,
     generate_repr,
     is_compliant_dataframe,
@@ -42,6 +43,7 @@
     is_pyarrow_table,
 )
 from narwhals.exceptions import (
+    ColumnNotFoundError,
     InvalidIntoExprError,
     InvalidOperationError,
     PerformanceWarning,
@@ -130,6 +132,9 @@ def _flatten_and_extract(
     def _extract_compliant(self, arg: Any) -> Any:
         raise NotImplementedError
 
+    def _check_columns_exist(self, subset: Sequence[str]) -> ColumnNotFoundError | None:
+        return check_columns_exist(subset, available=self.columns)
+
     @property
     def schema(self) -> Schema:
         return Schema(self._compliant_frame.schema.items())
@@ -177,7 +182,7 @@ def select(
                 )
             except Exception as e:
                 # Column not found is the only thing that can realistically be raised here.
-                if error := self._compliant_frame._check_columns_exist(flat_exprs):
+                if error := self._check_columns_exist(flat_exprs):
                     raise error from e
                 raise
         compliant_exprs, kinds = self._flatten_and_extract(*flat_exprs, **named_exprs)