CLN: Use set_module decorator (#63164)

Author: rhshadrach

ci/code_checks.sh

@@ -73,12 +73,10 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Period.freq GL08" \
         -i "pandas.Period.ordinal GL08" \
         -i "pandas.errors.IncompatibleFrequency SA01,SS06,EX01" \
-        -i "pandas.errors.InvalidVersion GL08" \
         -i "pandas.api.extensions.ExtensionArray.value_counts EX01,RT03,SA01" \
         -i "pandas.api.typing.DataFrameGroupBy.plot PR02" \
         -i "pandas.api.typing.SeriesGroupBy.plot PR02" \
         -i "pandas.api.typing.Resampler.quantile PR01,PR07" \
-        -i "pandas.arrays.NumpyExtensionArray GL08" \
         -i "pandas.tseries.offsets.BDay PR02,SA01" \
         -i "pandas.tseries.offsets.BHalfYearBegin.is_on_offset GL08" \
         -i "pandas.tseries.offsets.BHalfYearBegin.n GL08" \

pandas/_libs/interval.pyx

@@ -445,7 +445,6 @@ cdef class Interval(IntervalMixin):
     >>> interval.closed
     'left'
     """
-    __module__ = "pandas"
 
     def __init__(self, left, right, str closed="right"):
         # note: it is faster to just do these checks than to use a special

pandas/_libs/tslibs/offsets.pyx

@@ -47,6 +47,7 @@ from pandas._libs.tslibs.ccalendar import (
     int_to_weekday,
     weekday_to_int,
 )
+from pandas.util._decorators import set_module
 from pandas.util._exceptions import find_stack_level
 
 from pandas._libs.tslibs.ccalendar cimport (
@@ -1695,6 +1696,7 @@ class OffsetMeta(type):
 
 
 # TODO: figure out a way to use a metaclass with a cdef class
+@set_module("pandas")
 class DateOffset(RelativeDeltaOffset, metaclass=OffsetMeta):
     """
     Standard kind of date increment used for a date range.
@@ -1822,8 +1824,6 @@ class DateOffset(RelativeDeltaOffset, metaclass=OffsetMeta):
     >>> ts + pd.DateOffset(hour=8)
     Timestamp('2017-01-01 08:10:11')
     """
-    __module__ = "pandas"
-
     def __setattr__(self, name, value):
         raise AttributeError("DateOffset objects are immutable.")
 

pandas/_libs/tslibs/period.pyx

@@ -1626,12 +1626,12 @@ DIFFERENT_FREQ = ("Input has different freq={other_freq} "
                   "from {cls}(freq={own_freq})")
 
 
+@set_module("pandas.errors")
 class IncompatibleFrequency(TypeError):
     """
     Raised when trying to compare or operate between Periods with different
     frequencies.
     """
-    __module__ = "pandas.errors"
     pass
 
 

pandas/core/apply.py

@@ -29,7 +29,10 @@
 )
 from pandas.compat._optional import import_optional_dependency
 from pandas.errors import SpecificationError
-from pandas.util._decorators import cache_readonly
+from pandas.util._decorators import (
+    cache_readonly,
+    set_module,
+)
 
 from pandas.core.dtypes.cast import is_nested_object
 from pandas.core.dtypes.common import (
@@ -75,6 +78,7 @@
 ResType: TypeAlias = dict[int, Any]
 
 
+@set_module("pandas.api.executors")
 class BaseExecutionEngine(abc.ABC):
     """
     Base class for execution engines for map and apply methods.
@@ -88,8 +92,6 @@ class BaseExecutionEngine(abc.ABC):
     simply runs the code with the Python interpreter and pandas.
     """
 
-    __module__ = "pandas.api.executors"
-
     @staticmethod
     @abc.abstractmethod
     def map(

pandas/core/arrays/arrow/array.py

@@ -36,7 +36,10 @@
     PYARROW_MIN_VERSION,
 )
 from pandas.errors import Pandas4Warning
-from pandas.util._decorators import doc
+from pandas.util._decorators import (
+    doc,
+    set_module,
+)
 from pandas.util._exceptions import find_stack_level
 
 from pandas.core.dtypes.cast import (
@@ -242,6 +245,7 @@ def to_pyarrow_type(
     return None
 
 
+@set_module("pandas.arrays")
 class ArrowExtensionArray(
     OpsMixin,
     ExtensionArraySupportsAnyAll,
@@ -297,8 +301,6 @@ class ArrowExtensionArray(
     Length: 3, dtype: int64[pyarrow]
     """  # noqa: E501 (http link too long)
 
-    __module__ = "pandas.arrays"
-
     _pa_array: pa.ChunkedArray
     _dtype: ArrowDtype
 

pandas/core/arrays/base.py

@@ -31,6 +31,7 @@
 from pandas.errors import AbstractMethodError
 from pandas.util._decorators import (
     cache_readonly,
+    set_module,
 )
 from pandas.util._validators import (
     validate_bool_kwarg,
@@ -106,6 +107,7 @@
 _extension_array_shared_docs: dict[str, str] = {}
 
 
+@set_module("pandas.api.extensions")
 class ExtensionArray:
     """
     Abstract base class for custom 1-D array types.
@@ -257,8 +259,6 @@ class ExtensionArray:
     https://github.com/pandas-dev/pandas/blob/main/pandas/tests/extension/list/array.py
     """
 
-    __module__ = "pandas.api.extensions"
-
     # '_typ' is for pandas.core.dtypes.generic.ABCExtensionArray.
     # Don't override this.
     _typ = "extension"
@@ -2804,6 +2804,7 @@ def _add_logical_ops(cls) -> None:
         setattr(cls, "__rxor__", cls._create_logical_method(roperator.rxor))
 
 
+@set_module("pandas.api.extensions")
 class ExtensionScalarOpsMixin(ExtensionOpsMixin):
     """
     A mixin for defining ops on an ExtensionArray.
@@ -2830,8 +2831,6 @@ class ExtensionScalarOpsMixin(ExtensionOpsMixin):
        with NumPy arrays.
     """
 
-    __module__ = "pandas.api.extensions"
-
     @classmethod
     def _create_method(cls, op, coerce_to_dtype: bool = True, result_dtype=None):
         """

pandas/core/arrays/boolean.py

@@ -262,6 +262,7 @@ def coerce_to_array(
     return values, mask
 
 
+@set_module("pandas.arrays")
 class BooleanArray(BaseMaskedArray):
     """
     Array of boolean (True/False) data with missing values.
@@ -321,8 +322,6 @@ class BooleanArray(BaseMaskedArray):
     Length: 3, dtype: boolean
     """
 
-    __module__ = "pandas.arrays"
-
     _TRUE_VALUES = {"True", "TRUE", "true", "1", "1.0"}
     _FALSE_VALUES = {"False", "FALSE", "false", "0", "0.0"}
 

pandas/core/arrays/categorical.py

@@ -26,6 +26,7 @@
 from pandas._libs.arrays import NDArrayBacked
 from pandas.compat.numpy import function as nv
 from pandas.errors import Pandas4Warning
+from pandas.util._decorators import set_module
 from pandas.util._exceptions import find_stack_level
 from pandas.util._validators import validate_bool_kwarg
 
@@ -245,6 +246,7 @@ def contains(cat, key, container) -> bool:
         return any(loc_ in container for loc_ in loc)
 
 
+@set_module("pandas")
 class Categorical(NDArrayBackedExtensionArray, PandasObject, ObjectStringArrayMixin):
     """
     Represent a categorical variable in classic R / S-plus fashion.
@@ -361,8 +363,6 @@ class Categorical(NDArrayBackedExtensionArray, PandasObject, ObjectStringArrayMi
     'c'
     """
 
-    __module__ = "pandas"
-
     # For comparisons, so that numpy uses our implementation if the compare
     # ops, which raise
     __array_priority__ = 1000

pandas/core/arrays/datetimes.py

@@ -46,6 +46,7 @@
 )
 from pandas._libs.tslibs.dtypes import abbrev_to_npy_unit
 from pandas.errors import PerformanceWarning
+from pandas.util._decorators import set_module
 from pandas.util._exceptions import find_stack_level
 from pandas.util._validators import validate_inclusive
 
@@ -171,6 +172,7 @@ def f(self):
     return property(f)
 
 
+@set_module("pandas.arrays")
 class DatetimeArray(dtl.TimelikeOps, dtl.DatelikeOps):
     """
     Pandas ExtensionArray for tz-naive or tz-aware datetime data.
@@ -223,8 +225,6 @@ class DatetimeArray(dtl.TimelikeOps, dtl.DatelikeOps):
     Length: 2, dtype: datetime64[us]
     """
 
-    __module__ = "pandas.arrays"
-
     _typ = "datetimearray"
     _internal_fill_value = np.datetime64("NaT", "ns")
     _recognized_scalars = (datetime, np.datetime64)