feat: use ruff to drive typing of submodules (#1448)

* classify ann

* mypy

* fix(comment): #1445 (comment)

Author: cmp0xff

pandas-stubs/_testing/__init__.pyi

@@ -92,16 +92,6 @@ def assert_timedelta_array_equal(
     obj: str = "TimedeltaArray",
     check_freq: bool = True,
 ) -> None: ...
-def assert_numpy_array_equal(
-    left,
-    right,
-    strict_nan: bool = False,
-    check_dtype: bool | Literal["equiv"] = True,
-    err_msg: str | None = None,
-    check_same: Literal["copy", "same"] | None = None,
-    obj: str = "numpy array",
-    index_values: Index | np.ndarray | None = None,
-) -> None: ...
 def assert_extension_array_equal(
     left: ExtensionArray,
     right: ExtensionArray,
@@ -173,7 +163,6 @@ def assert_frame_equal(
     atol: float = 1e-8,
     obj: str = "DataFrame",
 ) -> None: ...
-def assert_equal(left, right, **kwargs: Any) -> None: ...
 def assert_sp_array_equal(left: SparseArray, right: SparseArray) -> None: ...
 def assert_contains_all(iterable: Iterable[T], dic: Container[T]) -> None: ...
 def assert_copy(iter1: Iterable[T], iter2: Iterable[T], **eql_kwargs: Any) -> None: ...

pandas-stubs/core/algorithms.pyi

@@ -1,4 +1,5 @@
 from typing import (
+    Any,
     Literal,
     overload,
 )
@@ -72,9 +73,9 @@ def value_counts(
     dropna: bool = True,
 ) -> Series: ...
 def take(
-    arr,
+    arr: np.ndarray | ExtensionArray | Index | Series,
     indices: TakeIndexer,
     axis: Literal[0, 1] = 0,
     allow_fill: bool = False,
-    fill_value=None,
-): ...
+    fill_value: Any = None,
+) -> np_1darray | ExtensionArray: ...

pandas-stubs/core/groupby/groupby.pyi

@@ -302,7 +302,7 @@ class GroupBy(BaseGroupBy[NDFrameT]):
         periods: int | Sequence[int] = 1,
         freq: Frequency | None = ...,
         axis: Axis | _NoDefaultDoNotUse = 0,
-        fill_value=...,
+        fill_value: Scalar | None = None,
         suffix: str | None = ...,
     ) -> NDFrameT: ...
     @final

pandas-stubs/core/groupby/ops.pyi

@@ -39,9 +39,6 @@ class BaseGrouper:
     def get_iterator(
         self, data: NDFrameT, axis: AxisInt = ...
     ) -> Iterator[tuple[Hashable, NDFrameT]]: ...
-    @final
-    @cache_readonly
-    def group_keys_seq(self): ...
     @cache_readonly
     def indices(self) -> dict[Hashable, npt.NDArray[np.intp]]: ...
     @final

pandas-stubs/core/interchange/dataframe_protocol.pyi

@@ -14,6 +14,8 @@ from typing import (
     cast,
 )
 
+from typing_extensions import Self
+
 class DlpackDeviceType(enum.IntEnum):
     CPU = cast(int, ...)
     CUDA = cast(int, ...)
@@ -58,7 +60,7 @@ class Buffer(ABC, metaclass=abc.ABCMeta):
     @abstractmethod
     def ptr(self) -> int: ...
     @abstractmethod
-    def __dlpack__(self): ...
+    def __dlpack__(self) -> Any: ...
     @abstractmethod
     def __dlpack_device__(self) -> tuple[DlpackDeviceType, int | None]: ...
 
@@ -94,7 +96,9 @@ class Column(ABC, metaclass=abc.ABCMeta):
 class DataFrame(ABC, metaclass=abc.ABCMeta):
     version: int
     @abstractmethod
-    def __dataframe__(self, nan_as_null: bool = ..., allow_copy: bool = ...): ...
+    def __dataframe__(
+        self, nan_as_null: bool = ..., allow_copy: bool = ...
+    ) -> Self: ...
     @property
     @abstractmethod
     def metadata(self) -> dict[str, Any]: ...

pandas-stubs/core/resample.pyi

@@ -175,7 +175,7 @@ class Resampler(BaseGroupBy[NDFrameT]):
 # attributes via setattr
 class _GroupByMixin(Resampler[NDFrameT]):
     key: str | list[str] | None
-    def __getitem__(self, key) -> Self: ...  # type: ignore[override] # pyright: ignore[reportIncompatibleMethodOverride]
+    def __getitem__(self, key: str | list[str] | None) -> Self: ...  # type: ignore[override] # pyright: ignore[reportIncompatibleMethodOverride]
 
 class DatetimeIndexResampler(Resampler[NDFrameT]): ...
 

pandas-stubs/core/reshape/util.pyi

@@ -20,7 +20,7 @@ class MergeError(ValueError): ...
 class AccessorRegistrationWarning(Warning): ...
 
 class AbstractMethodError(NotImplementedError):
-    def __init__(self, class_instance, methodtype: str = ...) -> None: ...
+    def __init__(self, class_instance: type, methodtype: str = ...) -> None: ...
 
 class NumbaUtilError(Exception): ...
 class DuplicateLabelError(ValueError): ...
@@ -34,7 +34,7 @@ class IndexingError(Exception): ...
 class PyperclipException(RuntimeError): ...
 
 class PyperclipWindowsException(PyperclipException):
-    def __init__(self, message) -> None: ...
+    def __init__(self, message: str) -> None: ...
 
 class CSSWarning(UserWarning): ...
 class PossibleDataLossError(Exception): ...

pandas-stubs/errors/__init__.pyi

@@ -201,8 +201,60 @@ ignore = [
   "A004",    # https://docs.astral.sh/ruff/rules/builtin-import-shadowing/
   "PYI001",  # https://docs.astral.sh/ruff/rules/unprefixed-type-param/
   "PYI042",  # https://docs.astral.sh/ruff/rules/snake-case-type-alias/
-  "ERA001", "ANN001", "ANN201", "ANN204", "PLR0402",
-  ]
+  "ERA001", "PLR0402", "PLC0105"
+]
+"*range.pyi" = [
+  # TODO: remove when pandas-dev/pandas-stubs#1442 is resolved
+  "ANN001", "ANN201", "ANN204", "ANN206",
+]
+"*category.pyi" = [
+  # TODO: remove when pandas-dev/pandas-stubs#1443 is resolved
+  "ANN001", "ANN201", "ANN204", "ANN206",
+]
+"*series.pyi" = [
+  # TODO: remove when pandas-dev/pandas-stubs#1444 is resolved
+  "ANN001", "ANN201", "ANN204", "ANN206",
+]
+"*frame.pyi" = [
+  # TODO: remove when pandas-dev/pandas-stubs#1446 is resolved
+  "ANN001", "ANN201", "ANN204", "ANN206",
+]
+"*index*" = [
+  # TODO: remove when indexes are fully typed
+  "ANN001", "ANN201", "ANN204", "ANN206",
+]
+"*computation*" = [
+  # TODO: remove when computations are fully typed
+  "ANN001", "ANN201", "ANN204", "ANN206",
+]
+"*plotting*" = [
+  # TODO: remove when plottings are fully typed
+  "ANN001", "ANN201", "ANN204", "ANN206",
+]
+"*io*" = [
+  # TODO: remove when io is fully typed
+  "ANN001", "ANN201", "ANN204", "ANN206",
+]
+"*window*" = [
+  # TODO: remove when window is fully typed
+  "ANN001", "ANN201", "ANN204", "ANN206",
+]
+"*generic.pyi" = [
+  # TODO: remove when generic.pyi is fully typed
+  "ANN001", "ANN201", "ANN204", "ANN206",
+]
+"*array*" = [
+  # TODO: remove when array is fully typed
+  "ANN001", "ANN201", "ANN204", "ANN206",
+]
+"*_libs*" = [
+  # TODO: remove when _libs is fully typed
+  "ANN001", "ANN201", "ANN204", "ANN206",
+]
+"*base.pyi" = [
+  # TODO: remove when base.pyi's are fully typed
+  "ANN001", "ANN201", "ANN204", "ANN206",
+]
 "scripts/*" = [
   # The following rules are ignored permanently for good reasons
   "EM",      # https://docs.astral.sh/ruff/rules/#flake8-errmsg-em

pyproject.toml

@@ -4,6 +4,8 @@
 from collections.abc import (
     Callable,
     Iterable,
+    MutableSequence,
+    Sequence,
 )
 import decimal
 import numbers
@@ -37,6 +39,7 @@
 from pandas._typing import (
     ArrayLike,
     AstypeArg,
+    ListLike,
     ScalarIndexer,
     SequenceIndexer,
     SequenceNotStr,
@@ -91,7 +94,7 @@ class DecimalArray(OpsMixin, ExtensionScalarOpsMixin, ExtensionArray):
 
     def __init__(
         self,
-        values: list[decimal.Decimal | float] | np.ndarray,
+        values: MutableSequence[decimal._DecimalNew] | np.ndarray | ExtensionArray,
         dtype: DecimalDtype | None = None,
         copy: bool = False,
         context: decimal.Context | None = None,
@@ -123,7 +126,7 @@ def dtype(self) -> DecimalDtype:
     @classmethod
     def _from_sequence(
         cls,
-        scalars: list[decimal.Decimal | float] | np.ndarray,
+        scalars: list[decimal._DecimalNew] | np.ndarray | ExtensionArray,
         dtype: DecimalDtype | None = None,
         copy: bool = False,
     ) -> Self:
@@ -140,7 +143,9 @@ def _from_sequence_of_strings(
 
     @classmethod
     def _from_factorized(
-        cls, values: list[decimal.Decimal | float] | np.ndarray, original: Any
+        cls,
+        values: list[decimal._DecimalNew] | np.ndarray | ExtensionArray,
+        original: Any,
     ) -> Self:
         return cls(values)
 
@@ -186,7 +191,7 @@ def reconstruct(
             x: (
                 decimal.Decimal
                 | numbers.Number
-                | list[decimal.Decimal | float]
+                | list[decimal._DecimalNew]
                 | np.ndarray
             ),
         ) -> decimal.Decimal | numbers.Number | DecimalArray:
@@ -240,21 +245,24 @@ def astype(self, dtype, copy=True):
 
         return super().astype(dtype, copy=copy)
 
-    def __setitem__(self, key: object, value: decimal._DecimalNew) -> None:
+    def __setitem__(
+        self,
+        key: int | slice[Any, Any, Any] | ListLike,
+        value: decimal._DecimalNew | Sequence[decimal._DecimalNew],
+    ) -> None:
         if is_list_like(value):
+            assert isinstance(value, Iterable)
             if is_scalar(key):
                 raise ValueError("setting an array element with a sequence.")
-            value = [  # type: ignore[assignment]
-                decimal.Decimal(v)  # type: ignore[arg-type]
-                for v in value  # type: ignore[union-attr] # pyright: ignore[reportAssignmentType,reportGeneralTypeIssues]
+            value = [
+                decimal.Decimal(v)  # type: ignore[arg-type] # pyright: ignore[reportArgumentType]
+                for v in value
             ]
         else:
-            value = decimal.Decimal(value)
+            value = decimal.Decimal(value)  # type: ignore[arg-type] # pyright: ignore[reportArgumentType]
 
-        key = check_array_indexer(  # type: ignore[call-overload]
-            self, key  # pyright: ignore[reportArgumentType,reportCallIssue]
-        )
-        self._data[key] = value  # type: ignore[call-overload] # pyright: ignore[reportArgumentType,reportCallIssue]
+        key = check_array_indexer(self, key)
+        self._data[key] = value
 
     def __len__(self) -> int:
         return len(self._data)