docs: update selectors docstrings (#1905)

* docs: update selector docstrings * mypy
narwhals-dev · Jan 31, 2025 · 562b213 · 562b213
1 parent 5f7fdab
commit 562b213
Show file tree

Hide file tree

Showing 5 changed files with 196 additions and 100 deletions.
diff --git a/narwhals/_dask/selectors.py b/narwhals/_dask/selectors.py
@@ -3,6 +3,7 @@
 import re
 from typing import TYPE_CHECKING
 from typing import Any
+from typing import Iterable
 from typing import Sequence
 
 from narwhals._dask.expr import DaskExpr
@@ -28,7 +29,7 @@ def __init__(
         self._backend_version = backend_version
         self._version = version
 
-    def by_dtype(self: Self, dtypes: list[DType | type[DType]]) -> DaskSelector:
+    def by_dtype(self: Self, dtypes: Iterable[DType | type[DType]]) -> DaskSelector:
         def func(df: DaskLazyFrame) -> list[dx.Series]:
             return [
                 df._native_frame[col] for col in df.columns if df.schema[col] in dtypes
@@ -73,7 +74,7 @@ def evalute_output_names(df: DaskLazyFrame) -> Sequence[str]:
     def numeric(self: Self) -> DaskSelector:
         dtypes = import_dtypes_module(self._version)
         return self.by_dtype(
-            [
+            {
                 dtypes.Int128,
                 dtypes.Int64,
                 dtypes.Int32,
@@ -86,20 +87,20 @@ def numeric(self: Self) -> DaskSelector:
                 dtypes.UInt8,
                 dtypes.Float64,
                 dtypes.Float32,
-            ],
+            },
         )
 
     def categorical(self: Self) -> DaskSelector:
         dtypes = import_dtypes_module(self._version)
-        return self.by_dtype([dtypes.Categorical])
+        return self.by_dtype({dtypes.Categorical})
 
     def string(self: Self) -> DaskSelector:
         dtypes = import_dtypes_module(self._version)
-        return self.by_dtype([dtypes.String])
+        return self.by_dtype({dtypes.String})
 
     def boolean(self: Self) -> DaskSelector:
         dtypes = import_dtypes_module(self._version)
-        return self.by_dtype([dtypes.Boolean])
+        return self.by_dtype({dtypes.Boolean})
 
     def all(self: Self) -> DaskSelector:
         def func(df: DaskLazyFrame) -> list[dx.Series]:

diff --git a/narwhals/_duckdb/selectors.py b/narwhals/_duckdb/selectors.py
@@ -3,6 +3,7 @@
 import re
 from typing import TYPE_CHECKING
 from typing import Any
+from typing import Iterable
 from typing import Sequence
 
 from duckdb import ColumnExpression
@@ -27,7 +28,7 @@ def __init__(
         self._backend_version = backend_version
         self._version = version
 
-    def by_dtype(self: Self, dtypes: list[DType | type[DType]]) -> DuckDBSelector:
+    def by_dtype(self: Self, dtypes: Iterable[DType | type[DType]]) -> DuckDBSelector:
         def func(df: DuckDBLazyFrame) -> list[duckdb.Expression]:
             return [
                 ColumnExpression(col) for col in df.columns if df.schema[col] in dtypes
@@ -68,7 +69,7 @@ def evalute_output_names(df: DuckDBLazyFrame) -> Sequence[str]:
     def numeric(self: Self) -> DuckDBSelector:
         dtypes = import_dtypes_module(self._version)
         return self.by_dtype(
-            [
+            {
                 dtypes.Int128,
                 dtypes.Int64,
                 dtypes.Int32,
@@ -81,20 +82,20 @@ def numeric(self: Self) -> DuckDBSelector:
                 dtypes.UInt8,
                 dtypes.Float64,
                 dtypes.Float32,
-            ],
+            },
         )
 
     def categorical(self: Self) -> DuckDBSelector:  # pragma: no cover
         dtypes = import_dtypes_module(self._version)
-        return self.by_dtype([dtypes.Categorical])
+        return self.by_dtype({dtypes.Categorical})
 
     def string(self: Self) -> DuckDBSelector:
         dtypes = import_dtypes_module(self._version)
-        return self.by_dtype([dtypes.String])
+        return self.by_dtype({dtypes.String})
 
     def boolean(self: Self) -> DuckDBSelector:
         dtypes = import_dtypes_module(self._version)
-        return self.by_dtype([dtypes.Boolean])
+        return self.by_dtype({dtypes.Boolean})
 
     def all(self: Self) -> DuckDBSelector:
         def func(df: DuckDBLazyFrame) -> list[duckdb.Expression]:

diff --git a/narwhals/_pandas_like/selectors.py b/narwhals/_pandas_like/selectors.py
@@ -3,6 +3,7 @@
 import re
 from typing import TYPE_CHECKING
 from typing import Any
+from typing import Iterable
 from typing import Sequence
 
 from narwhals._pandas_like.expr import PandasLikeExpr
@@ -30,7 +31,7 @@ def __init__(
         self._backend_version = backend_version
         self._version = version
 
-    def by_dtype(self: Self, dtypes: list[DType | type[DType]]) -> PandasSelector:
+    def by_dtype(self: Self, dtypes: Iterable[DType | type[DType]]) -> PandasSelector:
         def func(df: PandasLikeDataFrame) -> list[PandasLikeSeries]:
             return [df[col] for col in df.columns if df.schema[col] in dtypes]
 
@@ -71,7 +72,7 @@ def evalute_output_names(df: PandasLikeDataFrame) -> Sequence[str]:
     def numeric(self: Self) -> PandasSelector:
         dtypes = import_dtypes_module(self._version)
         return self.by_dtype(
-            [
+            {
                 dtypes.Int128,
                 dtypes.Int64,
                 dtypes.Int32,
@@ -84,20 +85,20 @@ def numeric(self: Self) -> PandasSelector:
                 dtypes.UInt8,
                 dtypes.Float64,
                 dtypes.Float32,
-            ],
+            }
         )
 
     def categorical(self: Self) -> PandasSelector:
         dtypes = import_dtypes_module(self._version)
-        return self.by_dtype([dtypes.Categorical])
+        return self.by_dtype({dtypes.Categorical})
 
     def string(self: Self) -> PandasSelector:
         dtypes = import_dtypes_module(self._version)
-        return self.by_dtype([dtypes.String])
+        return self.by_dtype({dtypes.String})
 
     def boolean(self: Self) -> PandasSelector:
         dtypes = import_dtypes_module(self._version)
-        return self.by_dtype([dtypes.Boolean])
+        return self.by_dtype({dtypes.Boolean})
 
     def all(self: Self) -> PandasSelector:
         def func(df: PandasLikeDataFrame) -> list[PandasLikeSeries]:

diff --git a/narwhals/_spark_like/selectors.py b/narwhals/_spark_like/selectors.py
@@ -3,6 +3,7 @@
 import re
 from typing import TYPE_CHECKING
 from typing import Any
+from typing import Iterable
 from typing import Sequence
 
 from narwhals._spark_like.expr import SparkLikeExpr
@@ -31,7 +32,7 @@ def __init__(
         self._version = version
         self._implementation = implementation
 
-    def by_dtype(self: Self, dtypes: list[DType | type[DType]]) -> SparkLikeSelector:
+    def by_dtype(self: Self, dtypes: Iterable[DType | type[DType]]) -> SparkLikeSelector:
         def func(df: SparkLikeLazyFrame) -> list[Column]:
             return [df._F.col(col) for col in df.columns if df.schema[col] in dtypes]
 
@@ -70,7 +71,7 @@ def evalute_output_names(df: SparkLikeLazyFrame) -> Sequence[str]:
     def numeric(self: Self) -> SparkLikeSelector:
         dtypes = import_dtypes_module(self._version)
         return self.by_dtype(
-            [
+            {
                 dtypes.Int128,
                 dtypes.Int64,
                 dtypes.Int32,
@@ -83,20 +84,20 @@ def numeric(self: Self) -> SparkLikeSelector:
                 dtypes.UInt8,
                 dtypes.Float64,
                 dtypes.Float32,
-            ],
+            },
         )
 
     def categorical(self: Self) -> SparkLikeSelector:
         dtypes = import_dtypes_module(self._version)
-        return self.by_dtype([dtypes.Categorical])
+        return self.by_dtype({dtypes.Categorical})
 
     def string(self: Self) -> SparkLikeSelector:
         dtypes = import_dtypes_module(self._version)
-        return self.by_dtype([dtypes.String])
+        return self.by_dtype({dtypes.String})
 
     def boolean(self: Self) -> SparkLikeSelector:
         dtypes = import_dtypes_module(self._version)
-        return self.by_dtype([dtypes.Boolean])
+        return self.by_dtype({dtypes.Boolean})
 
     def all(self: Self) -> SparkLikeSelector:
         def func(df: SparkLikeLazyFrame) -> list[Column]: