Merge branch 'bug-agg-nonunique-col' of https://github.com/luke396/pandas into bug-agg-nonunique-col

Author: luke

doc/source/development/contributing.rst

@@ -349,7 +349,7 @@ If using :ref:`mamba <contributing.mamba>`, do::
 If using :ref:`pip <contributing.pip>` , do::
 
     # activate the virtual environment based on your platform
-    pythom -m pip install --upgrade -r requirements-dev.txt
+    python -m pip install --upgrade -r requirements-dev.txt
 
 Tips for a successful pull request
 ==================================

doc/source/user_guide/basics.rst

@@ -329,16 +329,6 @@ You can test if a pandas object is empty, via the :attr:`~DataFrame.empty` prope
    df.empty
    pd.DataFrame(columns=list("ABC")).empty
 
-To evaluate single-element pandas objects in a boolean context, use the method
-:meth:`~DataFrame.bool`:
-
-.. ipython:: python
-
-   pd.Series([True]).bool()
-   pd.Series([False]).bool()
-   pd.DataFrame([[True]]).bool()
-   pd.DataFrame([[False]]).bool()
-
 .. warning::
 
    You might be tempted to do the following:

doc/source/user_guide/gotchas.rst

@@ -121,16 +121,6 @@ Below is how to check if any of the values are ``True``:
     if pd.Series([False, True, False]).any():
         print("I am any")
 
-To evaluate single-element pandas objects in a boolean context, use the method
-:meth:`~DataFrame.bool`:
-
-.. ipython:: python
-
-   pd.Series([True]).bool()
-   pd.Series([False]).bool()
-   pd.DataFrame([[True]]).bool()
-   pd.DataFrame([[False]]).bool()
-
 Bitwise boolean
 ~~~~~~~~~~~~~~~
 

doc/source/whatsnew/v0.13.0.rst

@@ -153,12 +153,16 @@ API changes
 
   Added the ``.bool()`` method to ``NDFrame`` objects to facilitate evaluating of single-element boolean Series:
 
-  .. ipython:: python
+  .. code-block:: python
 
-     pd.Series([True]).bool()
-     pd.Series([False]).bool()
-     pd.DataFrame([[True]]).bool()
-     pd.DataFrame([[False]]).bool()
+     >>> pd.Series([True]).bool()
+      True
+     >>> pd.Series([False]).bool()
+      False
+     >>> pd.DataFrame([[True]]).bool()
+      True
+     >>> pd.DataFrame([[False]]).bool()
+      False
 
 - All non-Index NDFrames (``Series``, ``DataFrame``, ``Panel``, ``Panel4D``,
   ``SparsePanel``, etc.), now support the entire set of arithmetic operators

doc/source/whatsnew/v2.1.0.rst

@@ -125,6 +125,7 @@ Deprecations
 - Deprecated the 'axis' keyword in :meth:`.GroupBy.idxmax`, :meth:`.GroupBy.idxmin`, :meth:`.GroupBy.fillna`, :meth:`.GroupBy.take`, :meth:`.GroupBy.skew`, :meth:`.GroupBy.rank`, :meth:`.GroupBy.cumprod`, :meth:`.GroupBy.cumsum`, :meth:`.GroupBy.cummax`, :meth:`.GroupBy.cummin`, :meth:`.GroupBy.pct_change`, :meth:`GroupBy.diff`, :meth:`.GroupBy.shift`, and :meth:`DataFrameGroupBy.corrwith`; for ``axis=1`` operate on the underlying :class:`DataFrame` instead (:issue:`50405`, :issue:`51046`)
 - Deprecated passing a dictionary to :meth:`.SeriesGroupBy.agg`; pass a list of aggregations instead (:issue:`50684`)
 - Deprecated logical operations (``|``, ``&``, ``^``) between pandas objects and dtype-less sequences (e.g. ``list``, ``tuple``), wrap a sequence in a :class:`Series` or numpy array before operating instead (:issue:`51521`)
+- Deprecated the methods :meth:`Series.bool` and :meth:`DataFrame.bool` (:issue:`51749`)
 - Deprecated :meth:`DataFrame.swapaxes` and :meth:`Series.swapaxes`, use :meth:`DataFrame.transpose` or :meth:`Series.transpose` instead (:issue:`51946`)
 - Deprecated parameter ``convert_type`` in :meth:`Series.apply` (:issue:`52140`)
 -

pandas/_libs/tslibs/offsets.pyx

@@ -1350,18 +1350,18 @@ class DateOffset(RelativeDeltaOffset, metaclass=OffsetMeta):
     valid dates.  For example, Bday(2) can be added to a date to move
     it two business days forward.  If the date does not start on a
     valid date, first it is moved to a valid date.  Thus pseudo code
-    is:
+    is::
 
-    def __add__(date):
-      date = rollback(date) # does nothing if date is valid
-      return date + <n number of periods>
+        def __add__(date):
+          date = rollback(date) # does nothing if date is valid
+          return date + <n number of periods>
 
     When a date offset is created for a negative number of periods,
-    the date is first rolled forward.  The pseudo code is:
+    the date is first rolled forward.  The pseudo code is::
 
-    def __add__(date):
-      date = rollforward(date) # does nothing is date is valid
-      return date + <n number of periods>
+        def __add__(date):
+          date = rollforward(date) # does nothing if date is valid
+          return date + <n number of periods>
 
     Zero presents a problem.  Should it roll forward or back?  We
     arbitrarily have it rollforward:

pandas/_libs/tslibs/timestamps.pyx

@@ -1293,6 +1293,9 @@ class Timestamp(_Timestamp):
         Unit used for conversion if ts_input is of type int or float. The
         valid values are 'D', 'h', 'm', 's', 'ms', 'us', and 'ns'. For
         example, 's' means seconds and 'ms' means milliseconds.
+
+        For float inputs, the result will be stored in nanoseconds, and
+        the unit attribute will be set as ``'ns'``.
     fold : {0, 1}, default None, keyword-only
         Due to daylight saving time, one wall clock time can occur twice
         when shifting from summer to winter time; fold describes whether the

pandas/conftest.py

@@ -137,6 +137,11 @@ def pytest_collection_modifyitems(items, config) -> None:
     ignored_doctest_warnings = [
         # Docstring divides by zero to show behavior difference
         ("missing.mask_zero_div_zero", "divide by zero encountered"),
+        (
+            "pandas.core.generic.NDFrame.bool",
+            "(Series|DataFrame).bool is now deprecated and will be removed "
+            "in future version of pandas",
+        ),
     ]
 
     for item in items:

pandas/core/algorithms.py

@@ -838,7 +838,7 @@ def value_counts(
     if bins is not None:
         from pandas.core.reshape.tile import cut
 
-        values = Series(values)
+        values = Series(values, copy=False)
         try:
             ii = cut(values, bins, include_lowest=True)
         except TypeError as err:
@@ -861,7 +861,7 @@ def value_counts(
     else:
         if is_extension_array_dtype(values):
             # handle Categorical and sparse,
-            result = Series(values)._values.value_counts(dropna=dropna)
+            result = Series(values, copy=False)._values.value_counts(dropna=dropna)
             result.name = name
             result.index.name = index_name
             counts = result._values
@@ -893,7 +893,7 @@ def value_counts(
                 idx = idx.astype(object)
             idx.name = index_name
 
-            result = Series(counts, index=idx, name=name)
+            result = Series(counts, index=idx, name=name, copy=False)
 
     if sort:
         result = result.sort_values(ascending=ascending)

pandas/core/arrays/_mixins.py

@@ -445,7 +445,7 @@ def value_counts(self, dropna: bool = True) -> Series:
 
         index_arr = self._from_backing_data(np.asarray(result.index._data))
         index = Index(index_arr, name=result.index.name)
-        return Series(result._values, index=index, name=result.name)
+        return Series(result._values, index=index, name=result.name, copy=False)
 
     def _quantile(
         self,

pandas/core/arrays/arrow/array.py

@@ -1124,7 +1124,7 @@ def value_counts(self, dropna: bool = True) -> Series:
 
         index = Index(type(self)(values))
 
-        return Series(counts, index=index, name="count")
+        return Series(counts, index=index, name="count", copy=False)
 
     @classmethod
     def _concat_same_type(cls, to_concat) -> Self:
@@ -1961,6 +1961,10 @@ def _str_wrap(self, width: int, **kwargs):
             "str.wrap not supported with pd.ArrowDtype(pa.string())."
         )
 
+    @property
+    def _dt_year(self):
+        return type(self)(pc.year(self._pa_array))
+
     @property
     def _dt_day(self):
         return type(self)(pc.day(self._pa_array))

pandas/core/arrays/categorical.py

@@ -1535,7 +1535,9 @@ def value_counts(self, dropna: bool = True) -> Series:
         ix = coerce_indexer_dtype(ix, self.dtype.categories)
         ix = self._from_backing_data(ix)
 
-        return Series(count, index=CategoricalIndex(ix), dtype="int64", name="count")
+        return Series(
+            count, index=CategoricalIndex(ix), dtype="int64", name="count", copy=False
+        )
 
     # error: Argument 2 of "_empty" is incompatible with supertype
     # "NDArrayBackedExtensionArray"; supertype defines the argument type as
@@ -1793,7 +1795,9 @@ def _values_for_rank(self):
             #  reorder the categories (so rank can use the float codes)
             #  instead of passing an object array to rank
             values = np.array(
-                self.rename_categories(Series(self.categories).rank().values)
+                self.rename_categories(
+                    Series(self.categories, copy=False).rank().values
+                )
             )
         return values
 

pandas/core/arrays/masked.py

@@ -995,7 +995,7 @@ def value_counts(self, dropna: bool = True) -> Series:
         )
 
         if dropna:
-            res = Series(value_counts, index=keys, name="count")
+            res = Series(value_counts, index=keys, name="count", copy=False)
             res.index = res.index.astype(self.dtype)
             res = res.astype("Int64")
             return res
@@ -1011,7 +1011,7 @@ def value_counts(self, dropna: bool = True) -> Series:
         mask = np.zeros(len(counts), dtype="bool")
         counts_array = IntegerArray(counts, mask)
 
-        return Series(counts_array, index=index, name="count")
+        return Series(counts_array, index=index, name="count", copy=False)
 
     @doc(ExtensionArray.equals)
     def equals(self, other) -> bool:

pandas/core/arrays/sparse/accessor.py

@@ -219,6 +219,7 @@ def to_dense(self) -> Series:
             self._parent.array.to_dense(),
             index=self._parent.index,
             name=self._parent.name,
+            copy=False,
         )
 
 

pandas/core/arrays/sparse/array.py

@@ -886,7 +886,7 @@ def value_counts(self, dropna: bool = True) -> Series:
             index = Index(keys)
         else:
             index = keys
-        return Series(counts, index=index)
+        return Series(counts, index=index, copy=False)
 
     # --------
     # Indexing

pandas/core/arrays/sparse/scipy_sparse.py

@@ -195,7 +195,7 @@ def coo_to_sparse_series(
     from pandas import SparseDtype
 
     try:
-        ser = Series(A.data, MultiIndex.from_arrays((A.row, A.col)))
+        ser = Series(A.data, MultiIndex.from_arrays((A.row, A.col)), copy=False)
     except AttributeError as err:
         raise TypeError(
             f"Expected coo_matrix. Got {type(A).__name__} instead."

pandas/core/base.py

@@ -907,17 +907,12 @@ def _map_values(self, mapper, na_action=None, convert: bool = True):
             If the function returns a tuple with more than one element
             a MultiIndex will be returned.
         """
-        arr = extract_array(self, extract_numpy=True, extract_range=True)
+        arr = self._values
 
         if isinstance(arr, ExtensionArray):
             return arr.map(mapper, na_action=na_action)
 
-        # Argument 1 to "map_array" has incompatible type
-        # "Union[IndexOpsMixin, ndarray[Any, Any]]";
-        # expected "Union[ExtensionArray, ndarray[Any, Any]]
-        return algorithms.map_array(
-            arr, mapper, na_action=na_action, convert=convert  # type: ignore[arg-type]
-        )
+        return algorithms.map_array(arr, mapper, na_action=na_action, convert=convert)
 
     @final
     def value_counts(

pandas/core/construction.py

@@ -55,8 +55,6 @@
     ABCDataFrame,
     ABCExtensionArray,
     ABCIndex,
-    ABCPandasArray,
-    ABCRangeIndex,
     ABCSeries,
 )
 from pandas.core.dtypes.missing import isna
@@ -379,6 +377,21 @@ def array(
     return PandasArray._from_sequence(data, dtype=dtype, copy=copy)
 
 
+_typs = frozenset(
+    {
+        "index",
+        "rangeindex",
+        "multiindex",
+        "datetimeindex",
+        "timedeltaindex",
+        "periodindex",
+        "categoricalindex",
+        "intervalindex",
+        "series",
+    }
+)
+
+
 @overload
 def extract_array(
     obj: Series | Index, extract_numpy: bool = ..., extract_range: bool = ...
@@ -438,19 +451,22 @@ def extract_array(
     >>> extract_array(pd.Series([1, 2, 3]), extract_numpy=True)
     array([1, 2, 3])
     """
-    if isinstance(obj, (ABCIndex, ABCSeries)):
-        if isinstance(obj, ABCRangeIndex):
+    typ = getattr(obj, "_typ", None)
+    if typ in _typs:
+        # i.e. isinstance(obj, (ABCIndex, ABCSeries))
+        if typ == "rangeindex":
             if extract_range:
-                return obj._values
-            # https://github.com/python/mypy/issues/1081
-            # error: Incompatible return value type (got "RangeIndex", expected
-            # "Union[T, Union[ExtensionArray, ndarray[Any, Any]]]")
-            return obj  # type: ignore[return-value]
+                # error: "T" has no attribute "_values"
+                return obj._values  # type: ignore[attr-defined]
+            return obj
 
-        return obj._values
+        # error: "T" has no attribute "_values"
+        return obj._values  # type: ignore[attr-defined]
 
-    elif extract_numpy and isinstance(obj, ABCPandasArray):
-        return obj.to_numpy()
+    elif extract_numpy and typ == "npy_extension":
+        # i.e. isinstance(obj, ABCPandasArray)
+        # error: "T" has no attribute "to_numpy"
+        return obj.to_numpy()  # type: ignore[attr-defined]
 
     return obj
 

pandas/core/generic.py

@@ -103,6 +103,7 @@
     validate_inclusive,
 )
 
+from pandas.core.dtypes.astype import astype_is_view
 from pandas.core.dtypes.common import (
     ensure_object,
     ensure_platform_int,
@@ -1513,6 +1514,13 @@ def bool(self) -> bool_t:
         >>> pd.DataFrame({'col': [False]}).bool()
         False
         """
+
+        warnings.warn(
+            f"{type(self).__name__}.bool is now deprecated and will be removed "
+            "in future version of pandas",
+            FutureWarning,
+            stacklevel=find_stack_level(),
+        )
         v = self.squeeze()
         if isinstance(v, (bool, np.bool_)):
             return bool(v)
@@ -2005,10 +2013,17 @@ def empty(self) -> bool_t:
     def __array__(self, dtype: npt.DTypeLike | None = None) -> np.ndarray:
         values = self._values
         arr = np.asarray(values, dtype=dtype)
-        if arr is values and using_copy_on_write():
-            # TODO(CoW) also properly handle extension dtypes
-            arr = arr.view()
-            arr.flags.writeable = False
+        if (
+            astype_is_view(values.dtype, arr.dtype)
+            and using_copy_on_write()
+            and self._mgr.is_single_block
+        ):
+            # Check if both conversions can be done without a copy
+            if astype_is_view(self.dtypes.iloc[0], values.dtype) and astype_is_view(
+                values.dtype, arr.dtype
+            ):
+                arr = arr.view()
+                arr.flags.writeable = False
         return arr
 
     @final

pandas/core/groupby/generic.py

@@ -720,7 +720,7 @@ def value_counts(
             llab = lambda lab, inc: lab[inc]
         else:
             # lab is a Categorical with categories an IntervalIndex
-            cat_ser = cut(Series(val), bins, include_lowest=True)
+            cat_ser = cut(Series(val, copy=False), bins, include_lowest=True)
             cat_obj = cast("Categorical", cat_ser._values)
             lev = cat_obj.categories
             lab = lev.take(

pandas/core/groupby/groupby.py

@@ -1570,7 +1570,7 @@ def _agg_py_fallback(
 
         if values.ndim == 1:
             # For DataFrameGroupBy we only get here with ExtensionArray
-            ser = Series(values)
+            ser = Series(values, copy=False)
         else:
             # We only get here with values.dtype == object
             # TODO: special case not needed with ArrayManager

pandas/core/indexes/accessors.py

@@ -105,7 +105,7 @@ def _delegate_property_get(self, name: str):  # type: ignore[override]
             index = self.orig.index
         else:
             index = self._parent.index
-        # return the result as a Series, which is by definition a copy
+        # return the result as a Series
         result = Series(result, index=index, name=self.name).__finalize__(self._parent)
 
         # setting this object will show a SettingWithCopyWarning/Error