TYP: return values in core/*.py (pandas-dev#47587)

* TYP: return values in core/*.py

* fix test

* to_html

* to_html part 2

* DataFrame.query

* more overloads

* fix query?

* increase stacklevel by one

* fix rename_axis

* and an overload for DataFrame.eval

* address comments

* fix typevar

Author: twoertwein

pandas/core/algorithms.py

@@ -948,7 +948,7 @@ def value_counts(
 # Called once from SparseArray, otherwise could be private
 def value_counts_arraylike(
     values: np.ndarray, dropna: bool, mask: npt.NDArray[np.bool_] | None = None
-):
+) -> tuple[ArrayLike, npt.NDArray[np.int64]]:
     """
     Parameters
     ----------

pandas/core/arrays/masked.py

@@ -945,9 +945,9 @@ def value_counts(self, dropna: bool = True) -> Series:
         index = index.astype(self.dtype)
 
         mask = np.zeros(len(counts), dtype="bool")
-        counts = IntegerArray(counts, mask)
+        counts_array = IntegerArray(counts, mask)
 
-        return Series(counts, index=index)
+        return Series(counts_array, index=index)
 
     @doc(ExtensionArray.equals)
     def equals(self, other) -> bool:

pandas/core/arrays/sparse/array.py

@@ -889,12 +889,20 @@ def value_counts(self, dropna: bool = True) -> Series:
             if mask.any():
                 counts[mask] += fcounts
             else:
-                keys = np.insert(keys, 0, self.fill_value)
+                # error: Argument 1 to "insert" has incompatible type "Union[
+                # ExtensionArray,ndarray[Any, Any]]"; expected "Union[
+                # _SupportsArray[dtype[Any]], Sequence[_SupportsArray[dtype
+                # [Any]]], Sequence[Sequence[_SupportsArray[dtype[Any]]]],
+                # Sequence[Sequence[Sequence[_SupportsArray[dtype[Any]]]]], Sequence
+                # [Sequence[Sequence[Sequence[_SupportsArray[dtype[Any]]]]]]]"
+                keys = np.insert(keys, 0, self.fill_value)  # type: ignore[arg-type]
                 counts = np.insert(counts, 0, fcounts)
 
         if not isinstance(keys, ABCIndex):
-            keys = Index(keys)
-        return Series(counts, index=keys)
+            index = Index(keys)
+        else:
+            index = keys
+        return Series(counts, index=index)
 
     def _quantile(self, qs: npt.NDArray[np.float64], interpolation: str):
 

pandas/core/base.py

@@ -81,7 +81,10 @@
         NumpyValueArrayLike,
     )
 
-    from pandas import Categorical
+    from pandas import (
+        Categorical,
+        Series,
+    )
 
 
 _shared_docs: dict[str, str] = {}
@@ -161,7 +164,7 @@ def _freeze(self):
         object.__setattr__(self, "__frozen", True)
 
     # prevent adding any attribute via s.xxx.new_attribute = ...
-    def __setattr__(self, key: str, value):
+    def __setattr__(self, key: str, value) -> None:
         # _cache is used by a decorator
         # We need to check both 1.) cls.__dict__ and 2.) getattr(self, key)
         # because
@@ -765,7 +768,7 @@ def hasnans(self) -> bool:
         # has no attribute "any"
         return bool(isna(self).any())  # type: ignore[union-attr]
 
-    def isna(self):
+    def isna(self) -> npt.NDArray[np.bool_]:
         return isna(self._values)
 
     def _reduce(
@@ -890,7 +893,7 @@ def value_counts(
         ascending: bool = False,
         bins=None,
         dropna: bool = True,
-    ):
+    ) -> Series:
         """
         Return a Series containing counts of unique values.
 

pandas/core/common.py

@@ -553,7 +553,7 @@ def temp_setattr(obj, attr: str, value) -> Iterator[None]:
         setattr(obj, attr, old_value)
 
 
-def require_length_match(data, index: Index):
+def require_length_match(data, index: Index) -> None:
     """
     Check the length of data matches the length of the index.
     """
@@ -665,7 +665,9 @@ def resolve_numeric_only(numeric_only: bool | None | lib.NoDefault) -> bool:
     return result
 
 
-def deprecate_numeric_only_default(cls: type, name: str, deprecate_none: bool = False):
+def deprecate_numeric_only_default(
+    cls: type, name: str, deprecate_none: bool = False
+) -> None:
     """Emit FutureWarning message for deprecation of numeric_only.
 
     See GH#46560 for details on the deprecation.

pandas/core/config_init.py

@@ -37,7 +37,7 @@
 """
 
 
-def use_bottleneck_cb(key):
+def use_bottleneck_cb(key) -> None:
     from pandas.core import nanops
 
     nanops.set_use_bottleneck(cf.get_option(key))
@@ -51,7 +51,7 @@ def use_bottleneck_cb(key):
 """
 
 
-def use_numexpr_cb(key):
+def use_numexpr_cb(key) -> None:
     from pandas.core.computation import expressions
 
     expressions.set_use_numexpr(cf.get_option(key))
@@ -65,7 +65,7 @@ def use_numexpr_cb(key):
 """
 
 
-def use_numba_cb(key):
+def use_numba_cb(key) -> None:
     from pandas.core.util import numba_
 
     numba_.set_use_numba(cf.get_option(key))
@@ -329,7 +329,7 @@ def use_numba_cb(key):
 """
 
 
-def table_schema_cb(key):
+def table_schema_cb(key) -> None:
     from pandas.io.formats.printing import enable_data_resource_formatter
 
     enable_data_resource_formatter(cf.get_option(key))
@@ -500,7 +500,7 @@ def _deprecate_negative_int_max_colwidth(key):
 # or we'll hit circular deps.
 
 
-def use_inf_as_na_cb(key):
+def use_inf_as_na_cb(key) -> None:
     from pandas.core.dtypes.missing import _use_inf_as_na
 
     _use_inf_as_na(key)
@@ -720,7 +720,7 @@ def use_inf_as_na_cb(key):
 """
 
 
-def register_plotting_backend_cb(key):
+def register_plotting_backend_cb(key) -> None:
     if key == "matplotlib":
         # We defer matplotlib validation, since it's the default
         return
@@ -746,7 +746,7 @@ def register_plotting_backend_cb(key):
 """
 
 
-def register_converter_cb(key):
+def register_converter_cb(key) -> None:
     from pandas.plotting import (
         deregister_matplotlib_converters,
         register_matplotlib_converters,

pandas/core/flags.py

@@ -81,7 +81,7 @@ def allows_duplicate_labels(self) -> bool:
         return self._allows_duplicate_labels
 
     @allows_duplicate_labels.setter
-    def allows_duplicate_labels(self, value: bool):
+    def allows_duplicate_labels(self, value: bool) -> None:
         value = bool(value)
         obj = self._obj()
         if obj is None:
@@ -99,12 +99,12 @@ def __getitem__(self, key):
 
         return getattr(self, key)
 
-    def __setitem__(self, key, value):
+    def __setitem__(self, key, value) -> None:
         if key not in self._keys:
             raise ValueError(f"Unknown flag {key}. Must be one of {self._keys}")
         setattr(self, key, value)
 
-    def __repr__(self):
+    def __repr__(self) -> str:
         return f"<Flags(allows_duplicate_labels={self.allows_duplicate_labels})>"
 
     def __eq__(self, other):