TYP: type all arguments with bool default values (#48624)

* TYP: type all arguments with bool default values

* bool_t

* ignore type error in pandas/core/arrays/sparse/accessor.py

Author: twoertwein

.pre-commit-config.yaml

@@ -258,10 +258,10 @@ repos:
             |/_testing/
     -   id: autotyping
         name: autotyping
-        entry: python -m libcst.tool codemod autotyping.AutotypeCommand --none-return --scalar-return --annotate-magics --annotate-imprecise-magics
+        entry: python -m libcst.tool codemod autotyping.AutotypeCommand --none-return --scalar-return --annotate-magics --annotate-imprecise-magics --bool-param
         types_or: [python, pyi]
         files: ^pandas
-        exclude: ^(pandas/tests|pandas/io/clipboard)
+        exclude: ^(pandas/tests|pandas/_version.py|pandas/io/clipboard)
         language: python
         additional_dependencies:
         - autotyping==22.9.0

pandas/_testing/__init__.py

@@ -275,7 +275,7 @@ def equalContents(arr1, arr2) -> bool:
     return frozenset(arr1) == frozenset(arr2)
 
 
-def box_expected(expected, box_cls, transpose=True):
+def box_expected(expected, box_cls, transpose: bool = True):
     """
     Helper function to wrap the expected output of a test in a given box_class.
 
@@ -656,8 +656,8 @@ def keyfunc(x):
 def makeCustomDataframe(
     nrows,
     ncols,
-    c_idx_names=True,
-    r_idx_names=True,
+    c_idx_names: bool | list[str] = True,
+    r_idx_names: bool | list[str] = True,
     c_idx_nlevels=1,
     r_idx_nlevels=1,
     data_gen_f=None,
@@ -673,7 +673,7 @@ def makeCustomDataframe(
     Parameters
     ----------
     nrows,  ncols - number of data rows/cols
-    c_idx_names, idx_names  - False/True/list of strings,  yields No names ,
+    c_idx_names, r_idx_names  - False/True/list of strings,  yields No names ,
             default names or uses the provided names for the levels of the
             corresponding index. You can provide a single string when
             c_idx_nlevels ==1.

pandas/_testing/_io.py

@@ -113,12 +113,13 @@ def dec(f):
     return wrapper
 
 
-@optional_args
+# error: Untyped decorator makes function "network" untyped
+@optional_args  # type: ignore[misc]
 def network(
     t,
     url="https://www.google.com",
-    raise_on_error=False,
-    check_before_test=False,
+    raise_on_error: bool = False,
+    check_before_test: bool = False,
     error_classes=None,
     skip_errnos=_network_errno_vals,
     _skip_on_messages=_network_error_messages,

pandas/_testing/_random.py

@@ -14,7 +14,7 @@ def randbool(size=(), p: float = 0.5):
 )
 
 
-def rands_array(nchars, size, dtype="O", replace=True) -> np.ndarray:
+def rands_array(nchars, size, dtype="O", replace: bool = True) -> np.ndarray:
     """
     Generate an array of byte strings.
     """

pandas/_testing/asserters.py

@@ -523,7 +523,11 @@ def assert_is_sorted(seq) -> None:
 
 
 def assert_categorical_equal(
-    left, right, check_dtype=True, check_category_order=True, obj="Categorical"
+    left,
+    right,
+    check_dtype: bool = True,
+    check_category_order: bool = True,
+    obj="Categorical",
 ) -> None:
     """
     Test that Categoricals are equivalent.
@@ -618,7 +622,7 @@ def assert_period_array_equal(left, right, obj="PeriodArray") -> None:
 
 
 def assert_datetime_array_equal(
-    left, right, obj="DatetimeArray", check_freq=True
+    left, right, obj="DatetimeArray", check_freq: bool = True
 ) -> None:
     __tracebackhide__ = True
     _check_isinstance(left, right, DatetimeArray)
@@ -630,7 +634,7 @@ def assert_datetime_array_equal(
 
 
 def assert_timedelta_array_equal(
-    left, right, obj="TimedeltaArray", check_freq=True
+    left, right, obj="TimedeltaArray", check_freq: bool = True
 ) -> None:
     __tracebackhide__ = True
     _check_isinstance(left, right, TimedeltaArray)
@@ -685,7 +689,7 @@ def raise_assert_detail(
 def assert_numpy_array_equal(
     left,
     right,
-    strict_nan=False,
+    strict_nan: bool = False,
     check_dtype: bool | Literal["equiv"] = True,
     err_msg=None,
     check_same=None,
@@ -768,7 +772,7 @@ def assert_extension_array_equal(
     check_dtype: bool | Literal["equiv"] = True,
     index_values=None,
     check_less_precise=no_default,
-    check_exact=False,
+    check_exact: bool = False,
     rtol: float = 1.0e-5,
     atol: float = 1.0e-8,
 ) -> None:
@@ -872,21 +876,21 @@ def assert_series_equal(
     right,
     check_dtype: bool | Literal["equiv"] = True,
     check_index_type: bool | Literal["equiv"] = "equiv",
-    check_series_type=True,
+    check_series_type: bool = True,
     check_less_precise: bool | int | NoDefault = no_default,
-    check_names=True,
-    check_exact=False,
-    check_datetimelike_compat=False,
-    check_categorical=True,
-    check_category_order=True,
-    check_freq=True,
-    check_flags=True,
-    rtol=1.0e-5,
-    atol=1.0e-8,
+    check_names: bool = True,
+    check_exact: bool = False,
+    check_datetimelike_compat: bool = False,
+    check_categorical: bool = True,
+    check_category_order: bool = True,
+    check_freq: bool = True,
+    check_flags: bool = True,
+    rtol: float = 1.0e-5,
+    atol: float = 1.0e-8,
     obj="Series",
     *,
-    check_index=True,
-    check_like=False,
+    check_index: bool = True,
+    check_like: bool = False,
 ) -> None:
     """
     Check that left and right Series are equal.
@@ -1140,19 +1144,19 @@ def assert_frame_equal(
     right,
     check_dtype: bool | Literal["equiv"] = True,
     check_index_type: bool | Literal["equiv"] = "equiv",
-    check_column_type="equiv",
-    check_frame_type=True,
+    check_column_type: bool | Literal["equiv"] = "equiv",
+    check_frame_type: bool = True,
     check_less_precise=no_default,
-    check_names=True,
-    by_blocks=False,
-    check_exact=False,
-    check_datetimelike_compat=False,
-    check_categorical=True,
-    check_like=False,
-    check_freq=True,
-    check_flags=True,
-    rtol=1.0e-5,
-    atol=1.0e-8,
+    check_names: bool = True,
+    by_blocks: bool = False,
+    check_exact: bool = False,
+    check_datetimelike_compat: bool = False,
+    check_categorical: bool = True,
+    check_like: bool = False,
+    check_freq: bool = True,
+    check_flags: bool = True,
+    rtol: float = 1.0e-5,
+    atol: float = 1.0e-8,
     obj="DataFrame",
 ) -> None:
     """

pandas/conftest.py

@@ -449,10 +449,7 @@ def frame_or_series(request):
     return request.param
 
 
-# error: List item 0 has incompatible type "Type[Index]"; expected "Type[IndexOpsMixin]"
-@pytest.fixture(
-    params=[Index, Series], ids=["index", "series"]  # type: ignore[list-item]
-)
+@pytest.fixture(params=[Index, Series], ids=["index", "series"])
 def index_or_series(request):
     """
     Fixture to parametrize over Index and Series, made necessary by a mypy

pandas/core/arrays/arrow/array.py

@@ -219,7 +219,7 @@ def __init__(self, values: pa.Array | pa.ChunkedArray) -> None:
         self._dtype = ArrowDtype(self._data.type)
 
     @classmethod
-    def _from_sequence(cls, scalars, *, dtype: Dtype | None = None, copy=False):
+    def _from_sequence(cls, scalars, *, dtype: Dtype | None = None, copy: bool = False):
         """
         Construct a new ExtensionArray from a sequence of scalars.
         """
@@ -238,7 +238,7 @@ def _from_sequence(cls, scalars, *, dtype: Dtype | None = None, copy=False):
 
     @classmethod
     def _from_sequence_of_strings(
-        cls, strings, *, dtype: Dtype | None = None, copy=False
+        cls, strings, *, dtype: Dtype | None = None, copy: bool = False
     ):
         """
         Construct a new ExtensionArray from a sequence of strings.

pandas/core/arrays/base.py

@@ -247,7 +247,7 @@ class ExtensionArray:
     # ------------------------------------------------------------------------
 
     @classmethod
-    def _from_sequence(cls, scalars, *, dtype: Dtype | None = None, copy=False):
+    def _from_sequence(cls, scalars, *, dtype: Dtype | None = None, copy: bool = False):
         """
         Construct a new ExtensionArray from a sequence of scalars.
 
@@ -270,7 +270,7 @@ def _from_sequence(cls, scalars, *, dtype: Dtype | None = None, copy=False):
 
     @classmethod
     def _from_sequence_of_strings(
-        cls, strings, *, dtype: Dtype | None = None, copy=False
+        cls, strings, *, dtype: Dtype | None = None, copy: bool = False
     ):
         """
         Construct a new ExtensionArray from a sequence of strings.
@@ -1772,7 +1772,7 @@ class ExtensionScalarOpsMixin(ExtensionOpsMixin):
     """
 
     @classmethod
-    def _create_method(cls, op, coerce_to_dtype=True, result_dtype=None):
+    def _create_method(cls, op, coerce_to_dtype: bool = True, result_dtype=None):
         """
         A class method that returns a method that will correspond to an
         operator for an ExtensionArray subclass, by dispatching to the

pandas/core/arrays/categorical.py

@@ -493,7 +493,9 @@ def _constructor(self) -> type[Categorical]:
         return Categorical
 
     @classmethod
-    def _from_sequence(cls, scalars, *, dtype: Dtype | None = None, copy=False):
+    def _from_sequence(
+        cls, scalars, *, dtype: Dtype | None = None, copy: bool = False
+    ) -> Categorical:
         return Categorical(scalars, dtype=dtype, copy=copy)
 
     @overload
@@ -783,7 +785,7 @@ def codes(self) -> np.ndarray:
         v.flags.writeable = False
         return v
 
-    def _set_categories(self, categories, fastpath=False):
+    def _set_categories(self, categories, fastpath: bool = False) -> None:
         """
         Sets new categories inplace
 
@@ -951,7 +953,7 @@ def as_unordered(
         return self.set_ordered(False, inplace=inplace)
 
     def set_categories(
-        self, new_categories, ordered=None, rename=False, inplace=no_default
+        self, new_categories, ordered=None, rename: bool = False, inplace=no_default
     ):
         """
         Set the categories to the specified new_categories.
@@ -1821,8 +1823,11 @@ def check_for_ordered(self, op) -> None:
                 "Categorical to an ordered one\n"
             )
 
+    # error: Signature of "argsort" incompatible with supertype "ExtensionArray"
     @deprecate_nonkeyword_arguments(version=None, allowed_args=["self"])
-    def argsort(self, ascending=True, kind="quicksort", **kwargs):
+    def argsort(  # type: ignore[override]
+        self, ascending: bool = True, kind="quicksort", **kwargs
+    ):
         """
         Return the indices that would sort the Categorical.
 
@@ -2291,7 +2296,7 @@ def _reverse_indexer(self) -> dict[Hashable, npt.NDArray[np.intp]]:
     # Reductions
 
     @deprecate_kwarg(old_arg_name="numeric_only", new_arg_name="skipna")
-    def min(self, *, skipna=True, **kwargs):
+    def min(self, *, skipna: bool = True, **kwargs):
         """
         The minimum value of the object.
 
@@ -2328,7 +2333,7 @@ def min(self, *, skipna=True, **kwargs):
         return self._wrap_reduction_result(None, pointer)
 
     @deprecate_kwarg(old_arg_name="numeric_only", new_arg_name="skipna")
-    def max(self, *, skipna=True, **kwargs):
+    def max(self, *, skipna: bool = True, **kwargs):
         """
         The maximum value of the object.
 

pandas/core/arrays/datetimelike.py

@@ -184,7 +184,9 @@ class DatetimeLikeArrayMixin(OpsMixin, NDArrayBackedExtensionArray):
     def _can_hold_na(self) -> bool:
         return True
 
-    def __init__(self, data, dtype: Dtype | None = None, freq=None, copy=False) -> None:
+    def __init__(
+        self, data, dtype: Dtype | None = None, freq=None, copy: bool = False
+    ) -> None:
         raise AbstractMethodError(self)
 
     @property

pandas/core/arrays/datetimes.py

@@ -333,19 +333,21 @@ def _from_sequence_not_strict(
 
         return result
 
+    # error: Signature of "_generate_range" incompatible with supertype
+    # "DatetimeLikeArrayMixin"
     @classmethod
-    def _generate_range(
+    def _generate_range(  # type: ignore[override]
         cls,
         start,
         end,
         periods,
         freq,
         tz=None,
-        normalize=False,
+        normalize: bool = False,
         ambiguous="raise",
         nonexistent="raise",
         inclusive="both",
-    ):
+    ) -> DatetimeArray:
 
         periods = dtl.validate_periods(periods)
         if freq is None and any(x is None for x in [periods, start, end]):
@@ -2133,7 +2135,7 @@ def objects_to_datetime64ns(
     data: np.ndarray,
     dayfirst,
     yearfirst,
-    utc=False,
+    utc: bool = False,
     errors="raise",
     require_iso8601: bool = False,
     allow_object: bool = False,

pandas/core/arrays/interval.py

@@ -1517,7 +1517,7 @@ def __arrow_array__(self, type=None):
     @Appender(
         _interval_shared_docs["to_tuples"] % {"return_type": "ndarray", "examples": ""}
     )
-    def to_tuples(self, na_tuple=True) -> np.ndarray:
+    def to_tuples(self, na_tuple: bool = True) -> np.ndarray:
         tuples = com.asarray_tuplesafe(zip(self._left, self._right))
         if not na_tuple:
             # GH 18756