TYP: Upgrade mypy to 1.0 (#51204)

Author: phofl

doc/source/whatsnew/v2.0.0.rst

@@ -650,7 +650,7 @@ If installed, we now require:
 +-------------------+-----------------+----------+---------+
 | Package           | Minimum Version | Required | Changed |
 +===================+=================+==========+=========+
-| mypy (dev)        | 0.991           |          |    X    |
+| mypy (dev)        | 1.0             |          |    X    |
 +-------------------+-----------------+----------+---------+
 | pytest (dev)      | 7.0.0           |          |    X    |
 +-------------------+-----------------+----------+---------+

environment.yml

@@ -79,7 +79,7 @@ dependencies:
   - cpplint
   - flake8=6.0.0
   - isort>=5.2.1  # check that imports are in the right order
-  - mypy=0.991
+  - mypy=1.0
   - pre-commit>=2.15.0
   - pyupgrade
   - ruff=0.0.215

pandas/core/arrays/arrow/array.py

@@ -329,10 +329,7 @@ def __getitem__(self, item: PositionalIndexer):
         elif isinstance(item, tuple):
             item = unpack_tuple_and_ellipses(item)
 
-        # error: Non-overlapping identity check (left operand type:
-        # "Union[Union[int, integer[Any]], Union[slice, List[int],
-        # ndarray[Any, Any]]]", right operand type: "ellipsis")
-        if item is Ellipsis:  # type: ignore[comparison-overlap]
+        if item is Ellipsis:
             # TODO: should be handled by pyarrow?
             item = slice(None)
 

pandas/core/arrays/boolean.py

@@ -288,8 +288,10 @@ class BooleanArray(BaseMaskedArray):
     # The value used to fill '_data' to avoid upcasting
     _internal_fill_value = False
     # Fill values used for any/all
-    _truthy_value = True
-    _falsey_value = False
+    # Incompatible types in assignment (expression has type "bool", base class
+    # "BaseMaskedArray" defined the type as "<typing special form>")
+    _truthy_value = True  # type: ignore[assignment]
+    _falsey_value = False  # type: ignore[assignment]
     _TRUE_VALUES = {"True", "TRUE", "true", "1", "1.0"}
     _FALSE_VALUES = {"False", "FALSE", "false", "0", "0.0"}
 

pandas/core/arrays/datetimes.py

@@ -2500,19 +2500,15 @@ def _generate_range(
     # Argument 1 to "Timestamp" has incompatible type "Optional[Timestamp]";
     # expected "Union[integer[Any], float, str, date, datetime64]"
     start = Timestamp(start)  # type: ignore[arg-type]
-    # Non-overlapping identity check (left operand type: "Timestamp", right
-    # operand type: "NaTType")
-    if start is not NaT:  # type: ignore[comparison-overlap]
+    if start is not NaT:
         start = start.as_unit(unit)
     else:
         start = None
 
     # Argument 1 to "Timestamp" has incompatible type "Optional[Timestamp]";
     # expected "Union[integer[Any], float, str, date, datetime64]"
     end = Timestamp(end)  # type: ignore[arg-type]
-    # Non-overlapping identity check (left operand type: "Timestamp", right
-    # operand type: "NaTType")
-    if end is not NaT:  # type: ignore[comparison-overlap]
+    if end is not NaT:
         end = end.as_unit(unit)
     else:
         end = None

pandas/core/arrays/floating.py

@@ -116,8 +116,10 @@ class FloatingArray(NumericArray):
     # The value used to fill '_data' to avoid upcasting
     _internal_fill_value = np.nan
     # Fill values used for any/all
-    _truthy_value = 1.0
-    _falsey_value = 0.0
+    # Incompatible types in assignment (expression has type "float", base class
+    # "BaseMaskedArray" defined the type as "<typing special form>")
+    _truthy_value = 1.0  # type: ignore[assignment]
+    _falsey_value = 0.0  # type: ignore[assignment]
 
 
 _dtype_docstring = """

pandas/core/arrays/integer.py

@@ -132,8 +132,10 @@ class IntegerArray(NumericArray):
     # The value used to fill '_data' to avoid upcasting
     _internal_fill_value = 1
     # Fill values used for any/all
-    _truthy_value = 1
-    _falsey_value = 0
+    # Incompatible types in assignment (expression has type "int", base class
+    # "BaseMaskedArray" defined the type as "<typing special form>")
+    _truthy_value = 1  # type: ignore[assignment]
+    _falsey_value = 0  # type: ignore[assignment]
 
 
 _dtype_docstring = """

pandas/core/arrays/sparse/array.py

@@ -912,11 +912,7 @@ def __getitem__(
 
         if isinstance(key, tuple):
             key = unpack_tuple_and_ellipses(key)
-            # Non-overlapping identity check (left operand type:
-            # "Union[Union[Union[int, integer[Any]], Union[slice, List[int],
-            # ndarray[Any, Any]]], Tuple[Union[int, ellipsis], ...]]",
-            # right operand type: "ellipsis")
-            if key is Ellipsis:  # type: ignore[comparison-overlap]
+            if key is Ellipsis:
                 raise ValueError("Cannot slice with Ellipsis")
 
         if is_integer(key):

pandas/core/dtypes/cast.py

@@ -787,16 +787,12 @@ def infer_dtype_from_scalar(val, pandas_dtype: bool = False) -> tuple[DtypeObj,
     elif isinstance(val, (np.datetime64, dt.datetime)):
         try:
             val = Timestamp(val)
-            # error: Non-overlapping identity check (left operand type:
-            # "Timestamp", right operand type: "NaTType")
-            if val is not NaT:  # type: ignore[comparison-overlap]
+            if val is not NaT:
                 val = val.as_unit("ns")
         except OutOfBoundsDatetime:
             return _dtype_obj, val
 
-        # error: Non-overlapping identity check (left operand type: "Timestamp",
-        # right operand type: "NaTType")
-        if val is NaT or val.tz is None:  # type: ignore[comparison-overlap]
+        if val is NaT or val.tz is None:
             val = val.to_datetime64()
             dtype = val.dtype
             # TODO: test with datetime(2920, 10, 1) based on test_replace_dtypes

pandas/core/frame.py

@@ -2633,13 +2633,15 @@ def to_stata(
                 raise ValueError("strl is not supported in format 114")
             from pandas.io.stata import StataWriter as statawriter
         elif version == 117:
-            # mypy: Name 'statawriter' already defined (possibly by an import)
-            from pandas.io.stata import (  # type: ignore[no-redef]
+            # Incompatible import of "statawriter" (imported name has type
+            # "Type[StataWriter117]", local name has type "Type[StataWriter]")
+            from pandas.io.stata import (  # type: ignore[assignment]
                 StataWriter117 as statawriter,
             )
         else:  # versions 118 and 119
-            # mypy: Name 'statawriter' already defined (possibly by an import)
-            from pandas.io.stata import (  # type: ignore[no-redef]
+            # Incompatible import of "statawriter" (imported name has type
+            # "Type[StataWriter117]", local name has type "Type[StataWriter]")
+            from pandas.io.stata import (  # type: ignore[assignment]
                 StataWriterUTF8 as statawriter,
             )
 
@@ -5514,8 +5516,7 @@ def pop(self, item: Hashable) -> Series:
         """
         return super().pop(item=item)
 
-    # error: Signature of "replace" incompatible with supertype "NDFrame"
-    @overload  # type: ignore[override]
+    @overload
     def replace(
         self,
         to_replace=...,

pandas/core/reshape/merge.py

@@ -1325,9 +1325,7 @@ def _maybe_coerce_merge_keys(self) -> None:
 
                         mask = ~np.isnan(lk)
                         match = lk == casted
-                        # error: Item "ExtensionArray" of "Union[ExtensionArray,
-                        # ndarray[Any, Any], Any]" has no attribute "all"
-                        if not match[mask].all():  # type: ignore[union-attr]
+                        if not match[mask].all():
                             warnings.warn(
                                 "You are merging on int and float "
                                 "columns where the float values "
@@ -1347,9 +1345,7 @@ def _maybe_coerce_merge_keys(self) -> None:
 
                         mask = ~np.isnan(rk)
                         match = rk == casted
-                        # error: Item "ExtensionArray" of "Union[ExtensionArray,
-                        # ndarray[Any, Any], Any]" has no attribute "all"
-                        if not match[mask].all():  # type: ignore[union-attr]
+                        if not match[mask].all():
                             warnings.warn(
                                 "You are merging on int and float "
                                 "columns where the float values "

pandas/core/series.py

@@ -3370,8 +3370,7 @@ def update(self, other: Series | Sequence | Mapping) -> None:
     # ----------------------------------------------------------------------
     # Reindexing, sorting
 
-    # error: Signature of "sort_values" incompatible with supertype "NDFrame"
-    @overload  # type: ignore[override]
+    @overload
     def sort_values(
         self,
         *,
@@ -5131,8 +5130,7 @@ def pop(self, item: Hashable) -> Any:
         """
         return super().pop(item=item)
 
-    # error: Signature of "replace" incompatible with supertype "NDFrame"
-    @overload  # type: ignore[override]
+    @overload
     def replace(
         self,
         to_replace=...,

pandas/io/formats/format.py

@@ -1229,7 +1229,9 @@ def get_buffer(
         raise ValueError("buf is not a file name and encoding is specified.")
 
     if hasattr(buf, "write"):
-        yield buf
+        # Incompatible types in "yield" (actual type "Union[str, WriteBuffer[str],
+        # StringIO]", expected type "Union[WriteBuffer[str], StringIO]")
+        yield buf  # type: ignore[misc]
     elif isinstance(buf, str):
         check_parent_directory(str(buf))
         with open(buf, "w", encoding=encoding, newline="") as f:

pandas/io/json/_json.py

@@ -1138,12 +1138,7 @@ def _try_convert_data(
                     return data, False
                 return data.fillna(np.nan), True
 
-            # error: Non-overlapping identity check (left operand type:
-            # "Union[ExtensionDtype, str, dtype[Any], Type[object],
-            # Dict[Hashable, Union[ExtensionDtype, Union[str, dtype[Any]],
-            # Type[str], Type[float], Type[int], Type[complex], Type[bool],
-            # Type[object]]]]", right operand type: "Literal[True]")
-            elif self.dtype is True:  # type: ignore[comparison-overlap]
+            elif self.dtype is True:
                 pass
             else:
                 # dtype to force

requirements-dev.txt

@@ -56,7 +56,7 @@ black==22.10.0
 cpplint
 flake8==6.0.0
 isort>=5.2.1
-mypy==0.991
+mypy==1.0
 pre-commit>=2.15.0
 pyupgrade
 ruff==0.0.215