Merge branch 'main' into tguard

Author: topper-123

ci/code_checks.sh

@@ -91,7 +91,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.Series.size \
         pandas.Series.T \
         pandas.Series.hasnans \
-        pandas.Series.to_timestamp \
         pandas.Series.to_list \
         pandas.Series.__iter__ \
         pandas.Series.keys \
@@ -218,7 +217,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.Period.year \
         pandas.Period.asfreq \
         pandas.Period.now \
-        pandas.Period.to_timestamp \
         pandas.arrays.PeriodArray \
         pandas.Interval.closed \
         pandas.Interval.left \
@@ -562,7 +560,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.DataFrame.swapaxes \
         pandas.DataFrame.first_valid_index \
         pandas.DataFrame.last_valid_index \
-        pandas.DataFrame.to_timestamp \
         pandas.DataFrame.attrs \
         pandas.DataFrame.plot \
         pandas.DataFrame.sparse.density \
@@ -576,7 +573,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
     $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=EX02 --ignore_functions \
         pandas.DataFrame.plot.line \
         pandas.Series.plot.line \
-        pandas.Timestamp.fromtimestamp \
         pandas.api.types.infer_dtype \
         pandas.api.types.is_datetime64_any_dtype \
         pandas.api.types.is_datetime64_ns_dtype \
@@ -590,7 +586,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.api.types.is_timedelta64_dtype \
         pandas.api.types.is_timedelta64_ns_dtype \
         pandas.api.types.is_unsigned_integer_dtype \
-        pandas.core.groupby.DataFrameGroupBy.take \
         pandas.io.formats.style.Styler.concat \
         pandas.io.formats.style.Styler.export \
         pandas.io.formats.style.Styler.set_td_classes \

pandas/_libs/tslibs/nattype.pyx

@@ -570,7 +570,7 @@ class NaTType(_NaT):
 
         Examples
         --------
-        >>> pd.Timestamp.fromtimestamp(1584199972)
+        >>> pd.Timestamp.fromtimestamp(1584199972)  # doctest: +SKIP
         Timestamp('2020-03-14 15:32:52')
 
         Note that the output may change depending on your local time.

pandas/_libs/tslibs/period.pyx

@@ -1841,6 +1841,13 @@ cdef class _Period(PeriodMixin):
         Returns
         -------
         Timestamp
+
+        Examples
+        --------
+        >>> period = pd.Period('2023-1-1', freq='D')
+        >>> timestamp = period.to_timestamp()
+        >>> timestamp
+        Timestamp('2023-01-01 00:00:00')
         """
         how = validate_end_alias(how)
 

pandas/_libs/tslibs/timestamps.pyx

@@ -1451,7 +1451,7 @@ class Timestamp(_Timestamp):
 
         Examples
         --------
-        >>> pd.Timestamp.fromtimestamp(1584199972)
+        >>> pd.Timestamp.fromtimestamp(1584199972)  # doctest: +SKIP
         Timestamp('2020-03-14 15:32:52')
 
         Note that the output may change depending on your local time.

pandas/core/arrays/arrow/array.py

@@ -11,7 +11,6 @@
     TypeVar,
     cast,
 )
-import warnings
 
 import numpy as np
 
@@ -890,12 +889,13 @@ def to_numpy(
             result = np.empty(len(self), dtype=object)
             mask = ~self.isna()
             result[mask] = np.asarray(self[mask]._data)
+        elif self._hasna:
+            data = self.copy()
+            data[self.isna()] = na_value
+            return np.asarray(data._data, dtype=dtype)
         else:
-            with warnings.catch_warnings():
-                # int dtype with NA raises Warning
-                warnings.filterwarnings("ignore", category=RuntimeWarning)
-                result = np.asarray(self._data, dtype=dtype)
-            if copy or self._hasna:
+            result = np.asarray(self._data, dtype=dtype)
+            if copy:
                 result = result.copy()
         if self._hasna:
             result[self.isna()] = na_value

pandas/core/frame.py

@@ -1396,10 +1396,7 @@ def iterrows(self) -> Iterable[tuple[Hashable, Series]]:
         for k, v in zip(self.index, self.values):
             s = klass(v, index=columns, name=k).__finalize__(self)
             if using_cow and self._mgr.is_single_block:
-                s._mgr.blocks[0].refs = self._mgr.blocks[0].refs  # type: ignore[union-attr]  # noqa
-                s._mgr.blocks[0].refs.add_reference(  # type: ignore[union-attr]
-                    s._mgr.blocks[0]  # type: ignore[arg-type, union-attr]
-                )
+                s._mgr.add_references(self._mgr)  # type: ignore[arg-type]
             yield k, s
 
     def itertuples(
@@ -11014,6 +11011,37 @@ def to_timestamp(
         -------
         DataFrame
             The DataFrame has a DatetimeIndex.
+
+        Examples
+        --------
+        >>> idx = pd.PeriodIndex(['2023', '2024'], freq='Y')
+        >>> d = {'col1': [1, 2], 'col2': [3, 4]}
+        >>> df1 = pd.DataFrame(data=d, index=idx)
+        >>> df1
+              col1   col2
+        2023     1      3
+        2024	 2      4
+
+        The resulting timestamps will be at the beginning of the year in this case
+
+        >>> df1 = df1.to_timestamp()
+        >>> df1
+                    col1   col2
+        2023-01-01     1      3
+        2024-01-01     2      4
+        >>> df1.index
+        DatetimeIndex(['2023-01-01', '2024-01-01'], dtype='datetime64[ns]', freq=None)
+
+        Using `freq` which is the offset that the Timestamps will have
+
+        >>> df2 = pd.DataFrame(data=d, index=idx)
+        >>> df2 = df2.to_timestamp(freq='M')
+        >>> df2
+                    col1   col2
+        2023-01-31     1      3
+        2024-01-31     2      4
+        >>> df2.index
+        DatetimeIndex(['2023-01-31', '2024-01-31'], dtype='datetime64[ns]', freq=None)
         """
         new_obj = self.copy(deep=copy)
 

pandas/core/internals/array_manager.py

@@ -169,6 +169,12 @@ def set_axis(self, axis: AxisInt, new_labels: Index) -> None:
     def get_dtypes(self) -> np.ndarray:
         return np.array([arr.dtype for arr in self.arrays], dtype="object")
 
+    def add_references(self, mgr: BaseArrayManager) -> None:
+        """
+        Only implemented on the BlockManager level
+        """
+        return
+
     def __getstate__(self):
         return self.arrays, self._axes
 

pandas/core/internals/managers.py

@@ -247,6 +247,17 @@ def _has_no_reference_block(self, blkno: int) -> bool:
         """
         return not self.blocks[blkno].refs.has_reference()
 
+    def add_references(self, mgr: BaseBlockManager) -> None:
+        """
+        Adds the references from one manager to another. We assume that both
+        managers have the same block structure.
+        """
+        for i, blk in enumerate(self.blocks):
+            blk.refs = mgr.blocks[i].refs
+            # Argument 1 to "add_reference" of "BlockValuesRefs" has incompatible type
+            # "Block"; expected "SharedBlock"
+            blk.refs.add_reference(blk)  # type: ignore[arg-type]
+
     def get_dtypes(self):
         dtypes = np.array([blk.dtype for blk in self.blocks])
         return dtypes.take(self.blknos)

pandas/core/series.py

@@ -5710,6 +5710,35 @@ def to_timestamp(
         Returns
         -------
         Series with DatetimeIndex
+
+        Examples
+        --------
+        >>> idx = pd.PeriodIndex(['2023', '2024', '2025'], freq='Y')
+        >>> s1 = pd.Series([1, 2, 3], index=idx)
+        >>> s1
+        2023    1
+        2024    2
+        2025    3
+        Freq: A-DEC, dtype: int64
+
+        The resulting frequency of the Timestamps is `YearBegin`
+
+        >>> s1 = s1.to_timestamp()
+        >>> s1
+        2023-01-01    1
+        2024-01-01    2
+        2025-01-01    3
+        Freq: AS-JAN, dtype: int64
+
+        Using `freq` which is the offset that the Timestamps will have
+
+        >>> s2 = pd.Series([1, 2, 3], index=idx)
+        >>> s2 = s2.to_timestamp(freq='M')
+        >>> s2
+        2023-01-31    1
+        2024-01-31    2
+        2025-01-31    3
+        Freq: A-JAN, dtype: int64
         """
         if not isinstance(self.index, PeriodIndex):
             raise TypeError(f"unsupported Type {type(self.index).__name__}")

pandas/tests/scalar/test_nat.py

@@ -9,6 +9,7 @@
 import pytz
 
 from pandas._libs.tslibs import iNaT
+from pandas.compat import is_numpy_dev
 
 from pandas.core.dtypes.common import is_datetime64_any_dtype
 
@@ -524,27 +525,24 @@ def test_to_numpy_alias():
     [
         Timedelta(0),
         Timedelta(0).to_pytimedelta(),
-        pytest.param(
-            Timedelta(0).to_timedelta64(),
-            marks=pytest.mark.xfail(
-                reason="td64 doesn't return NotImplemented, see numpy#17017"
-            ),
-        ),
+        Timedelta(0).to_timedelta64(),
         Timestamp(0),
         Timestamp(0).to_pydatetime(),
-        pytest.param(
-            Timestamp(0).to_datetime64(),
-            marks=pytest.mark.xfail(
-                reason="dt64 doesn't return NotImplemented, see numpy#17017"
-            ),
-        ),
+        Timestamp(0).to_datetime64(),
         Timestamp(0).tz_localize("UTC"),
         NaT,
     ],
 )
-def test_nat_comparisons(compare_operators_no_eq_ne, other):
+def test_nat_comparisons(compare_operators_no_eq_ne, other, request):
     # GH 26039
     opname = compare_operators_no_eq_ne
+    if isinstance(other, (np.datetime64, np.timedelta64)) and (
+        opname in ["__eq__", "__ne__"] or not is_numpy_dev
+    ):
+        mark = pytest.mark.xfail(
+            reason="dt64/td64 don't return NotImplemented, see numpy#17017",
+        )
+        request.node.add_marker(mark)
 
     assert getattr(NaT, opname)(other) is False