doctest fixups

Author: rhshadrach

asv_bench/benchmarks/indexing_engines.py

@@ -67,7 +67,11 @@ class NumericEngineIndexing:
     def setup(self, engine_and_dtype, index_type, unique, N):
         engine, dtype = engine_and_dtype
 
-        if index_type == "non_monotonic" and dtype in ["int16", "int8", "uint8"]:
+        if (
+            index_type == "non_monotonic"
+            and dtype in [np.int16, np.int8, np.uint8]
+            and unique
+        ):
             # Values overflow
             raise NotImplementedError
 
@@ -119,6 +123,14 @@ def setup(self, engine_and_dtype, index_type, unique, N):
         engine, dtype = engine_and_dtype
         dtype = dtype.lower()
 
+        if (
+            index_type == "non_monotonic"
+            and dtype in ["int16", "int8", "uint8"]
+            and unique
+        ):
+            # Values overflow
+            raise NotImplementedError
+
         if index_type == "monotonic_incr":
             if unique:
                 arr = np.arange(N * 3, dtype=dtype)

pandas/core/accessor.py

@@ -351,7 +351,7 @@ 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()
-6"""
+np.int64(6)"""
 
 
 @doc(_register_accessor, klass="Series", examples=_register_series_examples)

pandas/core/algorithms.py

@@ -415,7 +415,7 @@ def unique(values):
 
     >>> pd.unique(pd.array([1 + 1j, 2, 3]))
     <NumpyExtensionArray>
-    [(1+1j), (2+0j), (3+0j)]
+    [np.complex128(1+1j), np.complex128(2+0j), np.complex128(3+0j)]
     Length: 3, dtype: complex128
     """
     return unique_with_mask(values)

pandas/core/arrays/base.py

@@ -1072,7 +1072,7 @@ def interpolate(
         ...     limit_area="inside",
         ... )
         <NumpyExtensionArray>
-        [0.0, 1.0, 2.0, 3.0]
+        [np.float64(0.0), np.float64(1.0), np.float64(2.0), np.float64(3.0)]
         Length: 4, dtype: float64
 
         Interpolating values in a FloatingArray:
@@ -1962,7 +1962,7 @@ def _formatter(self, boxed: bool = False) -> Callable[[Any], str | None]:
         ...         return lambda x: "*" + str(x) + "*" if boxed else repr(x) + "*"
         >>> MyExtensionArray(np.array([1, 2, 3, 4]))
         <MyExtensionArray>
-        [1*, 2*, 3*, 4*]
+        [np.int64(1)*, np.int64(2)*, np.int64(3)*, np.int64(4)*]
         Length: 4, dtype: int64
         """
         if boxed:
@@ -2176,11 +2176,11 @@ def _reduce(
         Examples
         --------
         >>> pd.array([1, 2, 3])._reduce("min")
-        1
+        np.int64(1)
         >>> pd.array([1, 2, 3])._reduce("max")
-        3
+        np.int64(3)
         >>> pd.array([1, 2, 3])._reduce("sum")
-        6
+        np.int64(6)
         >>> pd.array([1, 2, 3])._reduce("mean")
         2.0
         >>> pd.array([1, 2, 3])._reduce("median")

pandas/core/arrays/datetimelike.py

@@ -275,7 +275,7 @@ def _unbox_scalar(
         --------
         >>> arr = pd.array(np.array(["1970-01-01"], "datetime64[ns]"))
         >>> arr._unbox_scalar(arr[0])
-        numpy.datetime64('1970-01-01T00:00:00.000000000')
+        np.datetime64('1970-01-01T00:00:00.000000000')
         """
         raise AbstractMethodError(self)
 

pandas/core/arrays/interval.py

@@ -1775,7 +1775,8 @@ def to_tuples(self, na_tuple: bool = True) -> np.ndarray:
         [(0, 1], (1, 2]]
         Length: 2, dtype: interval[int64, right]
         >>> idx.to_tuples()
-        array([(0, 1), (1, 2)], dtype=object)
+        array([(np.int64(0), np.int64(1)), (np.int64(1), np.int64(2))],
+          dtype=object)
 
         For :class:`pandas.IntervalIndex`:
 

pandas/core/arrays/masked.py

@@ -1470,17 +1470,17 @@ def all(
         skips NAs):
 
         >>> pd.array([True, True, pd.NA]).all()
-        True
+        np.True_
         >>> pd.array([1, 1, pd.NA]).all()
-        True
+        np.True_
         >>> pd.array([True, False, pd.NA]).all()
-        False
+        np.False_
         >>> pd.array([], dtype="boolean").all()
-        True
+        np.True_
         >>> pd.array([pd.NA], dtype="boolean").all()
-        True
+        np.True_
         >>> pd.array([pd.NA], dtype="Float64").all()
-        True
+        np.True_
 
         With ``skipna=False``, the result can be NA if this is logically
         required (whether ``pd.NA`` is True or False influences the result):

pandas/core/arrays/numpy_.py

@@ -80,7 +80,7 @@ class NumpyExtensionArray(  # type: ignore[misc]
     --------
     >>> pd.arrays.NumpyExtensionArray(np.array([0, 1, 2, 3]))
     <NumpyExtensionArray>
-    [0, 1, 2, 3]
+    [np.int64(0), np.int64(1), np.int64(2), np.int64(3)]
     Length: 4, dtype: int64
     """
 

pandas/core/arrays/sparse/accessor.py

@@ -297,7 +297,7 @@ class SparseFrameAccessor(BaseAccessor, PandasDelegate):
     --------
     >>> df = pd.DataFrame({"a": [1, 2, 0, 0], "b": [3, 0, 0, 4]}, dtype="Sparse[int]")
     >>> df.sparse.density
-    0.5
+    np.float64(0.5)
     """
 
     def _validate(self, data) -> None:
@@ -459,7 +459,7 @@ def density(self) -> float:
         --------
         >>> df = pd.DataFrame({"A": pd.arrays.SparseArray([0, 1, 0, 1])})
         >>> df.sparse.density
-        0.5
+        np.float64(0.5)
         """
         tmp = np.mean([column.array.density for _, column in self._parent.items()])
         return tmp

pandas/core/base.py

@@ -558,7 +558,7 @@ def array(self) -> ExtensionArray:
 
         >>> pd.Series([1, 2, 3]).array
         <NumpyExtensionArray>
-        [1, 2, 3]
+        [np.int64(1), np.int64(2), np.int64(3)]
         Length: 3, dtype: int64
 
         For extension types, like Categorical, the actual ExtensionArray
@@ -804,9 +804,9 @@ def argmax(
         dtype: float64
 
         >>> s.argmax()
-        2
+        np.int64(2)
         >>> s.argmin()
-        0
+        np.int64(0)
 
         The maximum cereal calories is the third element and
         the minimum cereal calories is the first element,
@@ -1360,7 +1360,7 @@ def factorize(
         dtype: int64
 
         >>> ser.searchsorted(4)
-        3
+        np.int64(3)
 
         >>> ser.searchsorted([0, 4])
         array([0, 3])