Merge branch 'main' into man-group/set-module-stringdtype

Author: jorisvandenbossche

doc/source/development/contributing_docstring.rst

@@ -940,7 +940,7 @@ Finally, docstrings can also be appended to with the ``doc`` decorator.
 
 In this example, we'll create a parent docstring normally (this is like
 ``pandas.core.generic.NDFrame``). Then we'll have two children (like
-``pandas.core.series.Series`` and ``pandas.DataFrame``). We'll
+``pandas.Series`` and ``pandas.DataFrame``). We'll
 substitute the class names in this docstring.
 
 .. code-block:: python
@@ -995,5 +995,5 @@ mapping function names to docstrings. Wherever possible, we prefer using
 ``doc``, since the docstring-writing processes is slightly closer to normal.
 
 See ``pandas.core.generic.NDFrame.fillna`` for an example template, and
-``pandas.core.series.Series.fillna`` and ``pandas.core.generic.frame.fillna``
+``pandas.Series.fillna`` and ``pandas.core.generic.frame.fillna``
 for the filled versions.

environment.yml

@@ -77,7 +77,7 @@ dependencies:
 
   # code checks
   - flake8=7.1.0  # run in subprocess over docstring examples
-  - mypy=1.11.2  # pre-commit uses locally installed mypy
+  - mypy=1.13.0  # pre-commit uses locally installed mypy
   - tokenize-rt  # scripts/check_for_inconsistent_pandas_namespace.py
   - pre-commit>=4.0.1
 

pandas/core/computation/ops.py

@@ -76,8 +76,7 @@
 class Term:
     def __new__(cls, name, env, side=None, encoding=None):
         klass = Constant if not isinstance(name, str) else cls
-        # error: Argument 2 for "super" not an instance of argument 1
-        supr_new = super(Term, klass).__new__  # type: ignore[misc]
+        supr_new = super(Term, klass).__new__
         return supr_new(klass)
 
     is_local: bool

pandas/core/dtypes/dtypes.py

@@ -2130,9 +2130,11 @@ def _get_common_dtype(self, dtypes: list[DtypeObj]) -> DtypeObj | None:
                 PerformanceWarning,
                 stacklevel=find_stack_level(),
             )
-
         np_dtypes = (x.subtype if isinstance(x, SparseDtype) else x for x in dtypes)
-        return SparseDtype(np_find_common_type(*np_dtypes), fill_value=fill_value)
+        # error: Argument 1 to "np_find_common_type" has incompatible type
+        # "*Generator[Any | dtype[Any] | ExtensionDtype, None, None]";
+        # expected "dtype[Any]"  [arg-type]
+        return SparseDtype(np_find_common_type(*np_dtypes), fill_value=fill_value)  # type: ignore [arg-type]
 
 
 @register_extension_dtype

pandas/core/generic.py

@@ -8024,7 +8024,9 @@ def asof(self, where, subset=None):
                     np.nan, index=self.columns, name=where[0]
                 )
 
-        locs = self.index.asof_locs(where, ~(nulls._values))
+        # error: Unsupported operand type for
+        # ~ ("ExtensionArray | ndarray[Any, Any] | Any")
+        locs = self.index.asof_locs(where, ~nulls._values)  # type: ignore[operator]
 
         # mask the missing
         mask = locs == -1

pandas/core/indexes/interval.py

@@ -558,8 +558,7 @@ def _maybe_convert_i8(self, key):
             left = self._maybe_convert_i8(key.left)
             right = self._maybe_convert_i8(key.right)
             constructor = Interval if scalar else IntervalIndex.from_arrays
-            # error: "object" not callable
-            return constructor(left, right, closed=self.closed)  # type: ignore[operator]
+            return constructor(left, right, closed=self.closed)
 
         if scalar:
             # Timestamp/Timedelta

pandas/core/indexing.py

@@ -212,7 +212,7 @@ def iloc(self) -> _iLocIndexer:
         With a scalar integer.
 
         >>> type(df.iloc[0])
-        <class 'pandas.core.series.Series'>
+        <class 'pandas.Series'>
         >>> df.iloc[0]
         a    1
         b    2
@@ -914,7 +914,9 @@ def __setitem__(self, key, value) -> None:
         indexer = self._get_setitem_indexer(key)
         self._has_valid_setitem_indexer(key)
 
-        iloc = self if self.name == "iloc" else self.obj.iloc
+        iloc: _iLocIndexer = (
+            cast("_iLocIndexer", self) if self.name == "iloc" else self.obj.iloc
+        )
         iloc._setitem_with_indexer(indexer, value, self.name)
 
     def _validate_key(self, key, axis: AxisInt) -> None:

pandas/core/missing.py

@@ -413,13 +413,10 @@ def func(yvalues: np.ndarray) -> None:
             **kwargs,
         )
 
-    # error: Argument 1 to "apply_along_axis" has incompatible type
-    # "Callable[[ndarray[Any, Any]], None]"; expected "Callable[...,
-    # Union[_SupportsArray[dtype[<nothing>]], Sequence[_SupportsArray
-    # [dtype[<nothing>]]], Sequence[Sequence[_SupportsArray[dtype[<nothing>]]]],
-    # Sequence[Sequence[Sequence[_SupportsArray[dtype[<nothing>]]]]],
-    # Sequence[Sequence[Sequence[Sequence[_SupportsArray[dtype[<nothing>]]]]]]]]"
-    np.apply_along_axis(func, axis, data)  # type: ignore[arg-type]
+    # error: No overload variant of "apply_along_axis" matches
+    # argument types "Callable[[ndarray[Any, Any]], None]",
+    # "int", "ndarray[Any, Any]"
+    np.apply_along_axis(func, axis, data)  # type: ignore[call-overload]
 
 
 def _index_to_interp_indices(index: Index, method: str) -> np.ndarray:

pandas/core/nanops.py

@@ -726,7 +726,9 @@ def nanmean(
 
 
 @bottleneck_switch()
-def nanmedian(values, *, axis: AxisInt | None = None, skipna: bool = True, mask=None):
+def nanmedian(
+    values: np.ndarray, *, axis: AxisInt | None = None, skipna: bool = True, mask=None
+) -> float | np.ndarray:
     """
     Parameters
     ----------
@@ -738,7 +740,7 @@ def nanmedian(values, *, axis: AxisInt | None = None, skipna: bool = True, mask=
 
     Returns
     -------
-    result : float
+    result : float | ndarray
         Unless input is a float array, in which case use the same
         precision as the input array.
 
@@ -758,7 +760,7 @@ def nanmedian(values, *, axis: AxisInt | None = None, skipna: bool = True, mask=
     # cases we never need to set NaN to the masked values
     using_nan_sentinel = values.dtype.kind == "f" and mask is None
 
-    def get_median(x, _mask=None):
+    def get_median(x: np.ndarray, _mask=None):
         if _mask is None:
             _mask = notna(x)
         else:
@@ -794,6 +796,8 @@ def get_median(x, _mask=None):
 
     notempty = values.size
 
+    res: float | np.ndarray
+
     # an array from a frame
     if values.ndim > 1 and axis is not None:
         # there's a non-empty array to apply over otherwise numpy raises

pandas/core/series.py

@@ -50,6 +50,7 @@
     Substitution,
     deprecate_nonkeyword_arguments,
     doc,
+    set_module,
 )
 from pandas.util._validators import (
     validate_ascending,
@@ -229,6 +230,7 @@
 # error: Cannot override final attribute "size" (previously declared in base
 # class "NDFrame")
 # definition in base class "NDFrame"
+@set_module("pandas")
 class Series(base.IndexOpsMixin, NDFrame):  # type: ignore[misc]
     """
     One-dimensional ndarray with axis labels (including time series).