BUG: always strip .freq when putting DTI/TDI into Series/DataFrame (#41425)

Author: jbrockmendel

Diff for: doc/source/whatsnew/v1.3.0.rst

@@ -972,6 +972,7 @@ Other
 - Bug in :func:`pandas.util.show_versions` where console JSON output was not proper JSON (:issue:`39701`)
 - Bug in :meth:`DataFrame.convert_dtypes` incorrectly raised ValueError when called on an empty DataFrame (:issue:`40393`)
 - Bug in :meth:`DataFrame.clip` not interpreting missing values as no threshold (:issue:`40420`)
+- Bug in :class:`Series` backed by :class:`DatetimeArray` or :class:`TimedeltaArray` sometimes failing to set the array's ``freq`` to ``None`` (:issue:`41425`)
 
 .. ---------------------------------------------------------------------------
 

Diff for: pandas/core/base.py

@@ -498,8 +498,8 @@ def to_numpy(
 
         >>> ser = pd.Series(pd.date_range('2000', periods=2, tz="CET"))
         >>> ser.to_numpy(dtype=object)
-        array([Timestamp('2000-01-01 00:00:00+0100', tz='CET', freq='D'),
-               Timestamp('2000-01-02 00:00:00+0100', tz='CET', freq='D')],
+        array([Timestamp('2000-01-01 00:00:00+0100', tz='CET'),
+               Timestamp('2000-01-02 00:00:00+0100', tz='CET')],
               dtype=object)
 
         Or ``dtype='datetime64[ns]'`` to return an ndarray of native

Diff for: pandas/core/internals/array_manager.py

@@ -85,6 +85,7 @@
 from pandas.core.internals.blocks import (
     ensure_block_shape,
     external_values,
+    maybe_coerce_values,
     new_block,
     to_native_types,
 )
@@ -701,7 +702,7 @@ def __init__(
 
         if verify_integrity:
             self._axes = [ensure_index(ax) for ax in axes]
-            self.arrays = [ensure_wrapped_if_datetimelike(arr) for arr in arrays]
+            self.arrays = [maybe_coerce_values(arr) for arr in arrays]
             self._verify_integrity()
 
     def _verify_integrity(self) -> None:
@@ -814,7 +815,7 @@ def iset(self, loc: int | slice | np.ndarray, value: ArrayLike):
 
             # TODO we receive a datetime/timedelta64 ndarray from DataFrame._iset_item
             # but we should avoid that and pass directly the proper array
-            value = ensure_wrapped_if_datetimelike(value)
+            value = maybe_coerce_values(value)
 
             assert isinstance(value, (np.ndarray, ExtensionArray))
             assert value.ndim == 1
@@ -873,7 +874,7 @@ def insert(self, loc: int, item: Hashable, value: ArrayLike) -> None:
                 raise ValueError(
                     f"Expected a 1D array, got an array with shape {value.shape}"
                 )
-        value = ensure_wrapped_if_datetimelike(value)
+        value = maybe_coerce_values(value)
 
         # TODO self.arrays can be empty
         # assert len(value) == len(self.arrays[0])
@@ -1188,7 +1189,7 @@ def __init__(
             assert len(arrays) == 1
             self._axes = [ensure_index(ax) for ax in self._axes]
             arr = arrays[0]
-            arr = ensure_wrapped_if_datetimelike(arr)
+            arr = maybe_coerce_values(arr)
             if isinstance(arr, ABCPandasArray):
                 arr = arr.to_numpy()
             self.arrays = [arr]

Diff for: pandas/core/internals/blocks.py

@@ -1860,6 +1860,10 @@ def maybe_coerce_values(values) -> ArrayLike:
         if issubclass(values.dtype.type, str):
             values = np.array(values, dtype=object)
 
+    if isinstance(values, (DatetimeArray, TimedeltaArray)) and values.freq is not None:
+        # freq is only stored in DatetimeIndex/TimedeltaIndex, not in Series/DataFrame
+        values = values._with_freq(None)
+
     return values
 
 

Diff for: pandas/core/series.py

@@ -813,8 +813,8 @@ def __array__(self, dtype: NpDtype | None = None) -> np.ndarray:
 
         >>> tzser = pd.Series(pd.date_range('2000', periods=2, tz="CET"))
         >>> np.asarray(tzser, dtype="object")
-        array([Timestamp('2000-01-01 00:00:00+0100', tz='CET', freq='D'),
-               Timestamp('2000-01-02 00:00:00+0100', tz='CET', freq='D')],
+        array([Timestamp('2000-01-01 00:00:00+0100', tz='CET'),
+               Timestamp('2000-01-02 00:00:00+0100', tz='CET')],
               dtype=object)
 
         Or the values may be localized to UTC and the tzinfo discarded with

Diff for: pandas/tests/extension/test_datetime.py

@@ -97,7 +97,10 @@ class TestDatetimeDtype(BaseDatetimeTests, base.BaseDtypeTests):
 
 
 class TestConstructors(BaseDatetimeTests, base.BaseConstructorsTests):
-    pass
+    def test_series_constructor(self, data):
+        # Series construction drops any .freq attr
+        data = data._with_freq(None)
+        super().test_series_constructor(data)
 
 
 class TestGetitem(BaseDatetimeTests, base.BaseGetitemTests):

Diff for: pandas/tests/frame/methods/test_set_index.py

@@ -96,7 +96,7 @@ def test_set_index_cast_datetimeindex(self):
         idf = df.set_index("A")
         assert isinstance(idf.index, DatetimeIndex)
 
-    def test_set_index_dst(self, using_array_manager):
+    def test_set_index_dst(self):
         di = date_range("2006-10-29 00:00:00", periods=3, freq="H", tz="US/Pacific")
 
         df = DataFrame(data={"a": [0, 1, 2], "b": [3, 4, 5]}, index=di).reset_index()
@@ -106,8 +106,7 @@ def test_set_index_dst(self, using_array_manager):
             data={"a": [0, 1, 2], "b": [3, 4, 5]},
             index=Index(di, name="index"),
         )
-        if not using_array_manager:
-            exp.index = exp.index._with_freq(None)
+        exp.index = exp.index._with_freq(None)
         tm.assert_frame_equal(res, exp)
 
         # GH#12920

Diff for: pandas/tests/window/test_rolling.py

@@ -586,7 +586,7 @@ def test_rolling_datetime(axis_frame, tz_naive_fixture):
         ),
     ],
 )
-def test_rolling_window_as_string(center, expected_data, using_array_manager):
+def test_rolling_window_as_string(center, expected_data):
     # see gh-22590
     date_today = datetime.now()
     days = date_range(date_today, date_today + timedelta(365), freq="D")
@@ -602,9 +602,7 @@ def test_rolling_window_as_string(center, expected_data, using_array_manager):
     ].agg("max")
 
     index = days.rename("DateCol")
-    if not using_array_manager:
-        # INFO(ArrayManager) preserves the frequence of the index
-        index = index._with_freq(None)
+    index = index._with_freq(None)
     expected = Series(expected_data, index=index, name="metric")
     tm.assert_series_equal(result, expected)