chore: run ruff (#316)

* run ruff

* add init file

* fixup

.github/workflows/mypy.yml

@@ -27,6 +27,8 @@ jobs:
             ~\AppData\Local\pip\Cache
           key: ${{ runner.os }}-build-${{ matrix.python-version }}
       - name: install-reqs
-        run: python -m pip install --upgrade mypy==1.4.0 typing-extensions
+        run: python -m pip install --upgrade mypy typing-extensions ruff
       - name: run mypy
         run: cd spec/API_specification && mypy dataframe_api && mypy examples
+      - name: run ruff
+        run: cd spec/API_specification && ruff format dataframe_api examples && ruff dataframe_api examples

spec/API_specification/dataframe_api/__init__.py

@@ -1,24 +1,39 @@
 # mypy: disable-error-code="empty-body"
-"""
-Function stubs and API documentation for the DataFrame API standard.
-"""
+"""Function stubs and API documentation for the DataFrame API standard."""
 from __future__ import annotations
 
-from typing import Dict, Sequence, Any, TYPE_CHECKING
+from typing import TYPE_CHECKING, Any
 
-from .column_object import *
+from .column_object import Column
 from .dataframe_object import DataFrame
-from .groupby_object import *
-from .dtypes import *
+from .dtypes import (
+    Bool,
+    Date,
+    Datetime,
+    Duration,
+    Float32,
+    Float64,
+    Int8,
+    Int16,
+    Int32,
+    Int64,
+    String,
+    UInt8,
+    UInt16,
+    UInt32,
+    UInt64,
+)
+from .groupby_object import Aggregation, GroupBy
 
 if TYPE_CHECKING:
+    from collections.abc import Sequence
+
     from .typing import DType, Scalar
 
 __all__ = [
+    "GroupBy",
     "Aggregation",
     "Bool",
-    "Column",
-    "DataFrame",
     "Date",
     "Datetime",
     "Duration",
@@ -33,6 +48,8 @@
     "UInt32",
     "UInt64",
     "UInt8",
+    "Column",
+    "DataFrame",
     "__dataframe_api_version__",
     "column_from_1d_array",
     "column_from_sequence",
@@ -53,9 +70,9 @@
 implementation of the dataframe API standard.
 """
 
+
 def concat(dataframes: Sequence[DataFrame]) -> DataFrame:
-    """
-    Concatenate DataFrames vertically.
+    """Concatenate DataFrames vertically.
 
     Parameters
     ----------
@@ -71,9 +88,14 @@ def concat(dataframes: Sequence[DataFrame]) -> DataFrame:
     """
     ...
 
-def column_from_sequence(sequence: Sequence[Any], *, dtype: DType, name: str = '') -> Column:
-    """
-    Construct Column from sequence of elements.
+
+def column_from_sequence(
+    sequence: Sequence[Any],
+    *,
+    dtype: DType,
+    name: str = "",
+) -> Column:
+    """Construct Column from sequence of elements.
 
     Parameters
     ----------
@@ -92,9 +114,9 @@ def column_from_sequence(sequence: Sequence[Any], *, dtype: DType, name: str = '
     """
     ...
 
+
 def dataframe_from_columns(*columns: Column) -> DataFrame:
-    """
-    Construct DataFrame from sequence of Columns.
+    """Construct DataFrame from sequence of Columns.
 
     Parameters
     ----------
@@ -110,9 +132,8 @@ def dataframe_from_columns(*columns: Column) -> DataFrame:
     ...
 
 
-def column_from_1d_array(array: Any, *, name: str = '') -> Column:
-    """
-    Construct Column from 1D array.
+def column_from_1d_array(array: Any, *, name: str = "") -> Column:
+    """Construct Column from 1D array.
 
     See `dataframe_from_2d_array` for related 2D function.
 
@@ -148,9 +169,9 @@ def column_from_1d_array(array: Any, *, name: str = '') -> Column:
     """
     ...
 
-def dataframe_from_2d_array(array: Any, *, schema: Dict[str, DType]) -> DataFrame:
-    """
-    Construct DataFrame from 2D array.
+
+def dataframe_from_2d_array(array: Any, *, schema: dict[str, DType]) -> DataFrame:
+    """Construct DataFrame from 2D array.
 
     See `column_from_1d_array` for related 1D function.
 
@@ -172,9 +193,9 @@ def dataframe_from_2d_array(array: Any, *, schema: Dict[str, DType]) -> DataFram
     """
     ...
 
-class null:
-    """
-    A `null` object to represent missing data.
+
+class null:  # noqa: N801
+    """A `null` object to represent missing data.
 
     ``null`` is a scalar, and may be used when constructing a `Column` from a
     Python sequence with `column_from_sequence`. It does not support ``is``,
@@ -198,11 +219,10 @@ class null:
     used to check if an object *is* the ``null`` object.
 
     """
-    ...
+
 
 def is_null(value: object, /) -> bool:
-    """
-    Check if an object is a `null` scalar.
+    """Check if an object is a `null` scalar.
 
     Parameters
     ----------
@@ -217,9 +237,9 @@ def is_null(value: object, /) -> bool:
     """
     ...
 
+
 def is_dtype(dtype: DType, kind: str | tuple[str, ...]) -> bool:
-    """
-    Returns a boolean indicating whether a provided dtype is of a specified data type “kind”.
+    """Indicate whether a provided dtype is of a specified data type "kind".
 
     Parameters
     ----------
@@ -233,9 +253,11 @@ def is_dtype(dtype: DType, kind: str | tuple[str, ...]) -> bool:
 
             - 'bool': boolean data type (Bool).
             - 'signed integer': signed integer data types (Int8, Int16, Int32, Int64).
-            - 'unsigned integer': unsigned integer data types (UInt8, UInt16, UInt32, UInt64).
+            - 'unsigned integer': unsigned integer data types
+              (UInt8, UInt16, UInt32, UInt64).
             - 'floating': floating-point data types (Float32, Float64).
-            - 'integral': integer data types. Shorthand for ('signed integer', 'unsigned integer').
+            - 'integral': integer data types. Shorthand for
+              ('signed integer', 'unsigned integer').
             - 'numeric': numeric data types. Shorthand for ('integral', 'floating').
 
             If kind is a tuple, the tuple specifies a union of dtypes and/or kinds,
@@ -249,11 +271,12 @@ def is_dtype(dtype: DType, kind: str | tuple[str, ...]) -> bool:
     """
     ...
 
+
 def date(year: int, month: int, day: int) -> Scalar:
-    """
-    Create date object which can be used for filtering.
+    """Create date object which can be used for filtering.
 
-    The full 32-bit signed integer range of days since epoch should be supported (between -5877641-06-23 and 5881580-07-11 inclusive).
+    The full 32-bit signed integer range of days since epoch should be supported
+    (between -5877641-06-23 and 5881580-07-11 inclusive).
 
     Examples
     --------
@@ -265,4 +288,3 @@ def date(year: int, month: int, day: int) -> Scalar:
     ... )
     >>> df.filter(mask)
     """
-