BUG: ArrowEA constructor with timestamp type

Author: jbrockmendel

doc/source/whatsnew/v3.0.0.rst

@@ -707,8 +707,8 @@ Datetimelike
 - Bug in :meth:`to_datetime` with ``format="ISO8601"`` and ``utc=True`` where naive timestamps incorrectly inherited timezone offset from previous timestamps in a series. (:issue:`61389`)
 - Bug in :meth:`to_datetime` wrongly converts when ``arg`` is a ``np.datetime64`` object with unit of ``ps``. (:issue:`60341`)
 - Bug in constructing arrays with :class:`ArrowDtype` with ``timestamp`` type incorrectly allowing ``Decimal("NaN")`` (:issue:`61773`)
+- Bug in constructing arrays with a timezone-aware :class:`ArrowDtype` from timezone-naive datetime objects incorrectly treating those as UTC times instead of wall times like :class:`DatetimeTZDtype` (:issue:`61775`)
 - Bug in setting scalar values with mismatched resolution into arrays with non-nanosecond ``datetime64``, ``timedelta64`` or :class:`DatetimeTZDtype` incorrectly truncating those scalars (:issue:`56410`)
--
 
 Timedelta
 ^^^^^^^^^

pandas/core/arrays/arrow/array.py

@@ -63,6 +63,7 @@
 from pandas.core.arrays.masked import BaseMaskedArray
 from pandas.core.arrays.string_ import StringDtype
 import pandas.core.common as com
+from pandas.core.construction import extract_array
 from pandas.core.indexers import (
     check_array_indexer,
     unpack_tuple_and_ellipses,
@@ -501,10 +502,31 @@ def _box_pa_array(
                 value = value.to_numpy()
 
             if pa_type is not None and pa.types.is_timestamp(pa_type):
-                # Use to_datetime to handle NaNs, disallow Decimal("NaN")
-                from pandas import to_datetime
+                # Use DatetimeArray to exclude Decimal(NaN) (GH#61774) and
+                #  ensure constructor treats tznaive the same as non-pyarrow
+                #  dtypes (GH#61775)
+                from pandas.core.arrays.datetimes import (
+                    DatetimeArray,
+                    tz_to_dtype,
+                )
 
-                value = to_datetime(value).as_unit(pa_type.unit)
+                pass_dtype = tz_to_dtype(tz=pa_type.tz, unit=pa_type.unit)
+                value = extract_array(value, extract_numpy=True)
+                if isinstance(value, DatetimeArray):
+                    dta = value
+                else:
+                    dta = DatetimeArray._from_sequence(
+                        value, copy=copy, dtype=pass_dtype
+                    )
+                mask = dta.isna()
+                value_i8 = dta.view("i8")
+                if not value_i8.flags["WRITEABLE"]:
+                    # e.g. test_setitem_frame_2d_values
+                    value_i8 = value_i8.copy()
+                    dta = DatetimeArray._from_sequence(value_i8, dtype=dta.dtype)
+                value_i8[mask] = 0  # GH#61776 avoid __sub__ overflow
+                pa_array = pa.array(dta._ndarray, type=pa_type, mask=mask)
+                return pa_array
 
             try:
                 pa_array = pa.array(value, type=pa_type, from_pandas=True)

pandas/tests/extension/test_arrow.py

@@ -2682,14 +2682,15 @@ def test_dt_tz_localize_unsupported_tz_options():
         ser.dt.tz_localize("UTC", nonexistent="NaT")
 
 
+@pytest.mark.xfail(reason="Converts to UTC before localizing GH#61780")
 def test_dt_tz_localize_none():
     ser = pd.Series(
         [datetime(year=2023, month=1, day=2, hour=3), None],
         dtype=ArrowDtype(pa.timestamp("ns", tz="US/Pacific")),
     )
     result = ser.dt.tz_localize(None)
     expected = pd.Series(
-        [datetime(year=2023, month=1, day=2, hour=3), None],
+        [ser[0].tz_localize(None), None],
         dtype=ArrowDtype(pa.timestamp("ns")),
     )
     tm.assert_series_equal(result, expected)
@@ -2749,7 +2750,7 @@ def test_dt_tz_convert_none():
     )
     result = ser.dt.tz_convert(None)
     expected = pd.Series(
-        [datetime(year=2023, month=1, day=2, hour=3), None],
+        [ser[0].tz_convert(None), None],
         dtype=ArrowDtype(pa.timestamp("ns")),
     )
     tm.assert_series_equal(result, expected)
@@ -2763,7 +2764,7 @@ def test_dt_tz_convert(unit):
     )
     result = ser.dt.tz_convert("US/Eastern")
     expected = pd.Series(
-        [datetime(year=2023, month=1, day=2, hour=3), None],
+        [ser[0].tz_convert("US/Eastern"), None],
         dtype=ArrowDtype(pa.timestamp(unit, "US/Eastern")),
     )
     tm.assert_series_equal(result, expected)
@@ -3558,3 +3559,16 @@ def test_timestamp_dtype_disallows_decimal():
 
     with pytest.raises(TypeError, match=msg):
         pd.array(vals, dtype=ArrowDtype(pa.timestamp("us")))
+
+
+def test_timestamp_dtype_matches_to_datetime():
+    # GH#61775
+    dtype1 = "datetime64[ns, US/Eastern]"
+    dtype2 = "timestamp[ns, US/Eastern][pyarrow]"
+
+    ts = pd.Timestamp("2025-07-03 18:10")
+
+    result = pd.Series([ts], dtype=dtype2)
+    expected = pd.Series([ts], dtype=dtype1).convert_dtypes(dtype_backend="pyarrow")
+
+    tm.assert_series_equal(result, expected)