DOC: Run all doctests

.github/workflows/code-checks.yml

@@ -57,7 +57,7 @@ jobs:
       run: sudo apt-get update && sudo apt-get install -y libegl1 libopengl0
 
     - name: Run doctests
-      run: cd ci && ./code_checks.sh doctests
+      run: cd ci && PANDAS_FUTURE_PYTHON_SCALARS="1" ./code_checks.sh doctests
       if: ${{ steps.build.outcome == 'success' && always() }}
 
     - name: Install pandas in editable mode

pandas/conftest.py

@@ -109,6 +109,20 @@ def pytest_addoption(parser) -> None:
     )
 
 
+def pytest_sessionstart(session):
+    import doctest
+    import inspect
+
+    orig = doctest.DocTestFinder._from_module  # type: ignore[attr-defined]
+
+    def _from_module(self, module, object):
+        if inspect.isfunction(object) and "." in object.__qualname__:
+            return True
+        return orig(self, module, object)
+
+    doctest.DocTestFinder._from_module = _from_module  # type: ignore[attr-defined]
+
+
 def ignore_doctest_warning(item: pytest.Item, path: str, message: str) -> None:
     """Ignore doctest warning.
 
@@ -135,14 +149,15 @@ def pytest_collection_modifyitems(items, config) -> None:
     # Warnings from doctests that can be ignored; place reason in comment above.
     # Each entry specifies (path, message) - see the ignore_doctest_warning function
     ignored_doctest_warnings = [
-        ("api.interchange.from_dataframe", ".*Interchange Protocol is deprecated"),
+        ("api.interchange.from_dataframe", "The DataFrame Interchange Protocol"),
         ("is_int64_dtype", "is_int64_dtype is deprecated"),
         ("is_interval_dtype", "is_interval_dtype is deprecated"),
         ("is_period_dtype", "is_period_dtype is deprecated"),
         ("is_datetime64tz_dtype", "is_datetime64tz_dtype is deprecated"),
         ("is_categorical_dtype", "is_categorical_dtype is deprecated"),
         ("is_sparse", "is_sparse is deprecated"),
-        ("DataFrame.__dataframe__", "Interchange Protocol is deprecated"),
+        ("CategoricalDtype._from_values_or_dtype", "Constructing a Categorical"),
+        ("DataFrame.__dataframe__", "The DataFrame Interchange Protocol"),
         ("DataFrameGroupBy.fillna", "DataFrameGroupBy.fillna is deprecated"),
         ("DataFrameGroupBy.corrwith", "DataFrameGroupBy.corrwith is deprecated"),
         ("NDFrame.replace", "Series.replace without 'value'"),

pandas/core/accessor.py

@@ -416,7 +416,7 @@ def register_dataframe_accessor(name: str) -> Callable[[TypeT], TypeT]:
 AttributeError: The series must contain integer data only.
 >>> df = pd.Series([1, 2, 3])
 >>> df.int_accessor.sum()
-np.int64(6)"""
+6"""
 
 
 @set_module("pandas.api.extensions")
@@ -481,7 +481,7 @@ def register_series_accessor(name: str) -> Callable[[TypeT], TypeT]:
     AttributeError: The series must contain integer data only.
     >>> df = pd.Series([1, 2, 3])
     >>> df.int_accessor.sum()
-    np.int64(6)
+    6
     """
     from pandas import Series
 

pandas/core/arrays/datetimes.py

@@ -894,13 +894,13 @@ def tz_convert(self, tz) -> Self:
         DatetimeIndex(['2014-08-01 09:00:00+02:00',
                        '2014-08-01 10:00:00+02:00',
                        '2014-08-01 11:00:00+02:00'],
-                      dtype='datetime64[ns, Europe/Berlin]', freq='h')
+                      dtype='datetime64[us, Europe/Berlin]', freq='h')
 
         >>> dti.tz_convert("US/Central")
         DatetimeIndex(['2014-08-01 02:00:00-05:00',
                        '2014-08-01 03:00:00-05:00',
                        '2014-08-01 04:00:00-05:00'],
-                      dtype='datetime64[ns, US/Central]', freq='h')
+                      dtype='datetime64[us, US/Central]', freq='h')
 
         With the ``tz=None``, we can remove the timezone (after converting
         to UTC if necessary):
@@ -1047,7 +1047,7 @@ def tz_localize(
         4   2018-10-28 02:30:00+01:00
         5   2018-10-28 03:00:00+01:00
         6   2018-10-28 03:30:00+01:00
-        dtype: datetime64[s, CET]
+        dtype: datetime64[us, CET]
 
         In some cases, inferring the DST is impossible. In such cases, you can
         pass an ndarray to the ambiguous parameter to set the DST explicitly
@@ -1059,7 +1059,7 @@ def tz_localize(
         0   2018-10-28 01:20:00+02:00
         1   2018-10-28 02:36:00+02:00
         2   2018-10-28 03:46:00+01:00
-        dtype: datetime64[s, CET]
+        dtype: datetime64[us, CET]
 
         If the DST transition causes nonexistent times, you can shift these
         dates forward or backwards with a timedelta object or `'shift_forward'`

pandas/core/arrays/sparse/array.py

@@ -1288,7 +1288,7 @@ def astype(self, dtype: AstypeArg | None = None, copy: bool = True):
         IntIndex
         Indices: array([2, 3], dtype=int32)
 
-        >>> arr.astype(SparseDtype(np.dtype("int32")))
+        >>> arr.astype(pd.SparseDtype(np.dtype("int32")))
         [0, 0, 1, 2]
         Fill: 0
         IntIndex
@@ -1297,7 +1297,7 @@ def astype(self, dtype: AstypeArg | None = None, copy: bool = True):
         Using a NumPy dtype with a different kind (e.g. float) will coerce
         just ``self.sp_values``.
 
-        >>> arr.astype(SparseDtype(np.dtype("float64")))
+        >>> arr.astype(pd.SparseDtype(np.dtype("float64")))
         ... # doctest: +NORMALIZE_WHITESPACE
         [nan, nan, 1.0, 2.0]
         Fill: nan
@@ -1306,7 +1306,7 @@ def astype(self, dtype: AstypeArg | None = None, copy: bool = True):
 
         Using a SparseDtype, you can also change the fill value as well.
 
-        >>> arr.astype(SparseDtype("float64", fill_value=0.0))
+        >>> arr.astype(pd.SparseDtype("float64", fill_value=0.0))
         ... # doctest: +NORMALIZE_WHITESPACE
         [0.0, 0.0, 1.0, 2.0]
         Fill: 0.0

pandas/core/arrays/timedeltas.py

@@ -813,7 +813,7 @@ def total_seconds(self) -> npt.NDArray[np.float64]:
         >>> idx = pd.to_timedelta(np.arange(5), unit="D")
         >>> idx
         TimedeltaIndex(['0 days', '1 days', '2 days', '3 days', '4 days'],
-                       dtype='timedelta64[us]', freq=None)
+                       dtype='timedelta64[ns]', freq=None)
 
         >>> idx.total_seconds()
         Index([0.0, 86400.0, 172800.0, 259200.0, 345600.0], dtype='float64')
@@ -855,7 +855,7 @@ def to_pytimedelta(self) -> npt.NDArray[np.object_]:
         >>> tidx = pd.TimedeltaIndex(data=["1 days 02:30:45", "3 days 04:15:10"])
         >>> tidx
         TimedeltaIndex(['1 days 02:30:45', '3 days 04:15:10'],
-               dtype='timedelta64[ns]', freq=None)
+               dtype='timedelta64[us]', freq=None)
         >>> tidx.to_pytimedelta()
         array([datetime.timedelta(days=1, seconds=9045),
                 datetime.timedelta(days=3, seconds=15310)], dtype=object)

pandas/core/dtypes/dtypes.py

@@ -2052,7 +2052,7 @@ def update_dtype(self, dtype) -> SparseDtype:
         Examples
         --------
         >>> SparseDtype(int, 0).update_dtype(float)
-        Sparse[float64, 0.0]
+        Sparse[float64, np.float64(0.0)]
 
         >>> SparseDtype(int, 1).update_dtype(SparseDtype(float, np.nan))
         Sparse[float64, nan]