CLN: resolve merge conflict in whatsnew

Author: AlexKirko

ci/code_checks.sh

@@ -39,7 +39,7 @@ function invgrep {
 }
 
 if [[ "$GITHUB_ACTIONS" == "true" ]]; then
-    FLAKE8_FORMAT="##[error]%(path)s:%(row)s:%(col)s:%(code):%(text)s"
+    FLAKE8_FORMAT="##[error]%(path)s:%(row)s:%(col)s:%(code)s:%(text)s"
     INVGREP_PREPEND="##[error]"
 else
     FLAKE8_FORMAT="default"

doc/source/user_guide/io.rst

@@ -35,7 +35,7 @@ The pandas I/O API is a set of top level ``reader`` functions accessed like
     binary;`SPSS <https://en.wikipedia.org/wiki/SPSS>`__;:ref:`read_spss<io.spss_reader>`;
     binary;`Python Pickle Format <https://docs.python.org/3/library/pickle.html>`__;:ref:`read_pickle<io.pickle>`;:ref:`to_pickle<io.pickle>`
     SQL;`SQL <https://en.wikipedia.org/wiki/SQL>`__;:ref:`read_sql<io.sql>`;:ref:`to_sql<io.sql>`
-    SQL;`Google Big Query <https://en.wikipedia.org/wiki/BigQuery>`__;:ref:`read_gbq<io.bigquery>`;:ref:`to_gbq<io.bigquery>`
+    SQL;`Google BigQuery <https://en.wikipedia.org/wiki/BigQuery>`__;:ref:`read_gbq<io.bigquery>`;:ref:`to_gbq<io.bigquery>`
 
 :ref:`Here <io.perf>` is an informal performance comparison for some of these IO methods.
 

doc/source/user_guide/text.rst

@@ -94,7 +94,11 @@ l. For ``StringDtype``, :ref:`string accessor methods<api.series.str>`
 2. Some string methods, like :meth:`Series.str.decode` are not available
    on ``StringArray`` because ``StringArray`` only holds strings, not
    bytes.
-
+3. In comparision operations, :class:`arrays.StringArray` and ``Series`` backed
+   by a ``StringArray`` will return an object with :class:`BooleanDtype`,
+   rather than a ``bool`` dtype object. Missing values in a ``StringArray``
+   will propagate in comparision operations, rather than always comparing
+   unequal like :attr:`numpy.nan`.
 
 Everything else that follows in the rest of this document applies equally to
 ``string`` and ``object`` dtype.

doc/source/whatsnew/v1.0.0.rst

@@ -486,6 +486,7 @@ Documentation Improvements
 Deprecations
 ~~~~~~~~~~~~
 
+- :meth:`Series.item` and :meth:`Index.item` have been _undeprecated_ (:issue:`29250`)
 - ``Index.set_value`` has been deprecated. For a given index ``idx``, array ``arr``,
   value in ``idx`` of ``idx_val`` and a new value of ``val``, ``idx.set_value(arr, idx_val, val)``
   is equivalent to ``arr[idx.get_loc(idx_val)] = val``, which should be used instead (:issue:`28621`).
@@ -681,6 +682,7 @@ Categorical
   same type as if one used the :meth:`.str.` / :meth:`.dt.` on a :class:`Series` of that type. E.g. when accessing :meth:`Series.dt.tz_localize` on a
   :class:`Categorical` with duplicate entries, the accessor was skipping duplicates (:issue:`27952`)
 - Bug in :meth:`DataFrame.replace` and :meth:`Series.replace` that would give incorrect results on categorical data (:issue:`26988`)
+- Bug where calling :meth:`Categorical.min` or :meth:`Categorical.max` on an empty Categorical would raise a numpy exception (:issue:`30227`)
 
 
 Datetimelike
@@ -703,6 +705,8 @@ Datetimelike
 - Bug in :func:`pandas.to_datetime` when called with ``None`` raising ``TypeError`` instead of returning ``NaT`` (:issue:`30011`)
 - Bug in :func:`pandas.to_datetime` failing for `deques` when using ``cache=True`` (the default) (:issue:`29403`)
 - Bug in :func:`pandas.to_datetime` when called with ``Series`` storing ``IntegerArray`` raising ``TypeError`` instead of returning ``Series`` (:issue:`30050`)
+- Bug in :meth:`Series.item` with ``datetime64`` or ``timedelta64`` dtype, :meth:`DatetimeIndex.item`, and :meth:`TimedeltaIndex.item` returning an integer instead of a :class:`Timestamp` or :class:`Timedelta` (:issue:`30175`)
+-
 
 Timedelta
 ^^^^^^^^^
@@ -863,7 +867,7 @@ ExtensionArray
 
 - Bug in :class:`arrays.PandasArray` when setting a scalar string (:issue:`28118`, :issue:`28150`).
 - Bug where nullable integers could not be compared to strings (:issue:`28930`)
--
+- Bug where :class:`DataFrame` constructor raised ValueError with list-like data and ``dtype`` specified (:issue:`30280`)
 
 
 Other

pandas/_config/config.py

@@ -462,6 +462,7 @@ def register_option(key: str, defval: object, doc="", validator=None, cb=None):
 
     cursor = _global_config
     msg = "Path prefix to option '{option}' is already an option"
+
     for i, p in enumerate(path[:-1]):
         if not isinstance(cursor, dict):
             raise OptionError(msg.format(option=".".join(path[:i])))
@@ -650,8 +651,9 @@ def _build_option_description(k):
         s += f"\n    [default: {o.defval}] [currently: {_get_option(k, True)}]"
 
     if d:
+        rkey = d.rkey if d.rkey else ""
         s += "\n    (Deprecated"
-        s += ", use `{rkey}` instead.".format(rkey=d.rkey if d.rkey else "")
+        s += f", use `{rkey}` instead."
         s += ")"
 
     return s

pandas/_config/localization.py

@@ -161,6 +161,6 @@ def get_locales(prefix=None, normalize=True, locale_getter=_default_locale_gette
     if prefix is None:
         return _valid_locales(out_locales, normalize)
 
-    pattern = re.compile("{prefix}.*".format(prefix=prefix))
+    pattern = re.compile(f"{prefix}.*")
     found = pattern.findall("\n".join(out_locales))
     return _valid_locales(found, normalize)

pandas/core/arrays/base.py

@@ -27,8 +27,6 @@
 from pandas.core.missing import backfill_1d, pad_1d
 from pandas.core.sorting import nargsort
 
-_not_implemented_message = "{} does not implement {}."
-
 _extension_array_shared_docs: Dict[str, str] = dict()
 
 
@@ -330,9 +328,7 @@ def __setitem__(self, key: Union[int, np.ndarray], value: Any) -> None:
         #   __init__ method coerces that value, then so should __setitem__
         # Note, also, that Series/DataFrame.where internally use __setitem__
         # on a copy of the data.
-        raise NotImplementedError(
-            _not_implemented_message.format(type(self), "__setitem__")
-        )
+        raise NotImplementedError(f"{type(self)} does not implement __setitem__.")
 
     def __len__(self) -> int:
         """

pandas/core/arrays/categorical.py

@@ -2115,6 +2115,10 @@ def min(self, skipna=True):
 
         Only ordered `Categoricals` have a minimum!
 
+        .. versionchanged:: 1.0.0
+
+           Returns an NA value on empty arrays
+
         Raises
         ------
         TypeError
@@ -2125,6 +2129,10 @@ def min(self, skipna=True):
         min : the minimum of this `Categorical`
         """
         self.check_for_ordered("min")
+
+        if not len(self._codes):
+            return self.dtype.na_value
+
         good = self._codes != -1
         if not good.all():
             if skipna:
@@ -2142,6 +2150,10 @@ def max(self, skipna=True):
 
         Only ordered `Categoricals` have a maximum!
 
+        .. versionchanged:: 1.0.0
+
+           Returns an NA value on empty arrays
+
         Raises
         ------
         TypeError
@@ -2152,6 +2164,10 @@ def max(self, skipna=True):
         max : the maximum of this `Categorical`
         """
         self.check_for_ordered("max")
+
+        if not len(self._codes):
+            return self.dtype.na_value
+
         good = self._codes != -1
         if not good.all():
             if skipna:

pandas/core/arrays/string_.py

@@ -134,6 +134,10 @@ class StringArray(PandasArray):
         The string methods are available on Series backed by
         a StringArray.
 
+    Notes
+    -----
+    StringArray returns a BooleanArray for comparison methods.
+
     Examples
     --------
     >>> pd.array(['This is', 'some text', None, 'data.'], dtype="string")
@@ -148,6 +152,13 @@ class StringArray(PandasArray):
     Traceback (most recent call last):
     ...
     ValueError: StringArray requires an object-dtype ndarray of strings.
+
+    For comparision methods, this returns a :class:`pandas.BooleanArray`
+
+    >>> pd.array(["a", None, "c"], dtype="string") == "a"
+    <BooleanArray>
+    [True, NA, False]
+    Length: 3, dtype: boolean
     """
 
     # undo the PandasArray hack
@@ -255,7 +266,12 @@ def value_counts(self, dropna=False):
     # Overrride parent because we have different return types.
     @classmethod
     def _create_arithmetic_method(cls, op):
+        # Note: this handles both arithmetic and comparison methods.
         def method(self, other):
+            from pandas.arrays import BooleanArray
+
+            assert op.__name__ in ops.ARITHMETIC_BINOPS | ops.COMPARISON_BINOPS
+
             if isinstance(other, (ABCIndexClass, ABCSeries, ABCDataFrame)):
                 return NotImplemented
 
@@ -275,15 +291,16 @@ def method(self, other):
                 other = np.asarray(other)
                 other = other[valid]
 
-            result = np.empty_like(self._ndarray, dtype="object")
-            result[mask] = StringDtype.na_value
-            result[valid] = op(self._ndarray[valid], other)
-
-            if op.__name__ in {"add", "radd", "mul", "rmul"}:
+            if op.__name__ in ops.ARITHMETIC_BINOPS:
+                result = np.empty_like(self._ndarray, dtype="object")
+                result[mask] = StringDtype.na_value
+                result[valid] = op(self._ndarray[valid], other)
                 return StringArray(result)
             else:
-                dtype = "object" if mask.any() else "bool"
-                return np.asarray(result, dtype=dtype)
+                # logical
+                result = np.zeros(len(self._ndarray), dtype="bool")
+                result[valid] = op(self._ndarray[valid], other)
+                return BooleanArray(result, mask)
 
         return compat.set_function_name(method, f"__{op.__name__}__", cls)
 

pandas/core/base.py

@@ -5,7 +5,6 @@
 from collections import OrderedDict
 import textwrap
 from typing import Dict, FrozenSet, List, Optional
-import warnings
 
 import numpy as np
 
@@ -26,6 +25,7 @@
     is_object_dtype,
     is_scalar,
     is_timedelta64_ns_dtype,
+    needs_i8_conversion,
 )
 from pandas.core.dtypes.generic import ABCDataFrame, ABCIndexClass, ABCSeries
 from pandas.core.dtypes.missing import isna
@@ -659,19 +659,27 @@ def item(self):
         """
         Return the first element of the underlying data as a python scalar.
 
-        .. deprecated:: 0.25.0
-
         Returns
         -------
         scalar
             The first element of %(klass)s.
+
+        Raises
+        ------
+        ValueError
+            If the data is not length-1.
         """
-        warnings.warn(
-            "`item` has been deprecated and will be removed in a future version",
-            FutureWarning,
-            stacklevel=2,
-        )
-        return self.values.item()
+        if not (
+            is_extension_array_dtype(self.dtype) or needs_i8_conversion(self.dtype)
+        ):
+            # numpy returns ints instead of datetime64/timedelta64 objects,
+            #  which we need to wrap in Timestamp/Timedelta/Period regardless.
+            return self.values.item()
+
+        if len(self) == 1:
+            return next(iter(self))
+        else:
+            raise ValueError("can only convert an array of size 1 to a Python scalar")
 
     @property
     def nbytes(self):

pandas/core/indexes/period.py

@@ -1,5 +1,4 @@
 from datetime import datetime, timedelta
-import warnings
 import weakref
 
 import numpy as np
@@ -862,27 +861,6 @@ def __setstate__(self, state):
 
     _unpickle_compat = __setstate__
 
-    def item(self):
-        """
-        Return the first element of the underlying data as a python
-        scalar
-
-        .. deprecated:: 0.25.0
-
-        """
-        warnings.warn(
-            "`item` has been deprecated and will be removed in a future version",
-            FutureWarning,
-            stacklevel=2,
-        )
-        # TODO(DatetimeArray): remove
-        if len(self) == 1:
-            return self[0]
-        else:
-            # TODO: is this still necessary?
-            # copy numpy's message here because Py26 raises an IndexError
-            raise ValueError("can only convert an array of size 1 to a Python scalar")
-
     def memory_usage(self, deep=False):
         result = super().memory_usage(deep=deep)
         if hasattr(self, "_cache") and "_int64index" in self._cache:

pandas/core/internals/construction.py

@@ -150,7 +150,7 @@ def init_ndarray(values, index, columns, dtype=None, copy=False):
 
         index, columns = _get_axes(len(values), 1, index, columns)
         return arrays_to_mgr([values], columns, index, columns, dtype=dtype)
-    elif is_extension_array_dtype(values):
+    elif is_extension_array_dtype(values) or is_extension_array_dtype(dtype):
         # GH#19157
         if columns is None:
             columns = [0]

pandas/core/ops/__init__.py

@@ -5,7 +5,7 @@
 """
 import datetime
 import operator
-from typing import Tuple, Union
+from typing import Set, Tuple, Union
 
 import numpy as np
 
@@ -59,6 +59,37 @@
     rxor,
 )
 
+# -----------------------------------------------------------------------------
+# constants
+ARITHMETIC_BINOPS: Set[str] = {
+    "add",
+    "sub",
+    "mul",
+    "pow",
+    "mod",
+    "floordiv",
+    "truediv",
+    "divmod",
+    "radd",
+    "rsub",
+    "rmul",
+    "rpow",
+    "rmod",
+    "rfloordiv",
+    "rtruediv",
+    "rdivmod",
+}
+
+
+COMPARISON_BINOPS: Set[str] = {
+    "eq",
+    "ne",
+    "lt",
+    "gt",
+    "le",
+    "ge",
+}
+
 # -----------------------------------------------------------------------------
 # Ops Wrapping Utilities