BUG: Fix naive timestamps inheriting timezone from previous timestamps in to_datetime with ISO8601 format

myenugula · myenugula · commit 98113f372097 · 2025-05-06T21:48:42.000+07:00
diff --git a/doc/source/whatsnew/v3.0.0.rst b/doc/source/whatsnew/v3.0.0.rst
@@ -658,6 +658,7 @@ Datetimelike
 - Bug in :meth:`to_datetime` on float array with missing values throwing ``FloatingPointError`` (:issue:`58419`)
 - Bug in :meth:`to_datetime` on float32 df with year, month, day etc. columns leads to precision issues and incorrect result. (:issue:`60506`)
 - Bug in :meth:`to_datetime` reports incorrect index in case of any failure scenario. (:issue:`58298`)
+- 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 setting scalar values with mismatched resolution into arrays with non-nanosecond ``datetime64``, ``timedelta64`` or :class:`DatetimeTZDtype` incorrectly truncating those scalars (:issue:`56410`)
 
diff --git a/pandas/_libs/tslibs/strptime.pyx b/pandas/_libs/tslibs/strptime.pyx
@@ -444,6 +444,9 @@ def array_strptime(
             else:
                 val = str(val)
 
+            out_local = 0
+            out_tzoffset = 0
+
             if fmt == "ISO8601":
                 string_to_dts_succeeded = not string_to_dts(
                     val, &dts, &out_bestunit, &out_local,
diff --git a/pandas/tests/tools/test_to_datetime.py b/pandas/tests/tools/test_to_datetime.py
@@ -3514,6 +3514,54 @@ def test_to_datetime_mixed_not_necessarily_iso8601_coerce():
     tm.assert_index_equal(result, DatetimeIndex(["2020-01-01 00:00:00", NaT]))
 
 
+def test_to_datetime_iso8601_utc_single_naive():
+    # GH#61389
+    result = to_datetime("2023-10-15T14:30:00", utc=True, format="ISO8601")
+    expected = Timestamp("2023-10-15 14:30:00+00:00")
+    assert result == expected
+
+
+def test_to_datetime_iso8601_utc_mixed_negative_offset():
+    # GH#61389
+    data = ["2023-10-15T10:30:00-12:00", "2023-10-15T14:30:00"]
+    result = to_datetime(data, utc=True, format="ISO8601")
+
+    expected = DatetimeIndex(
+        [Timestamp("2023-10-15 22:30:00+00:00"), Timestamp("2023-10-15 14:30:00+00:00")]
+    )
+    tm.assert_index_equal(result, expected)
+
+
+def test_to_datetime_iso8601_utc_mixed_positive_offset():
+    # GH#61389
+    data = ["2023-10-15T10:30:00+08:00", "2023-10-15T14:30:00"]
+    result = to_datetime(data, utc=True, format="ISO8601")
+
+    expected = DatetimeIndex(
+        [Timestamp("2023-10-15 02:30:00+00:00"), Timestamp("2023-10-15 14:30:00+00:00")]
+    )
+    tm.assert_index_equal(result, expected)
+
+
+def test_to_datetime_iso8601_utc_mixed_both_offsets():
+    # GH#61389
+    data = [
+        "2023-10-15T10:30:00+08:00",
+        "2023-10-15T12:30:00-05:00",
+        "2023-10-15T14:30:00",
+    ]
+    result = to_datetime(data, utc=True, format="ISO8601")
+
+    expected = DatetimeIndex(
+        [
+            Timestamp("2023-10-15 02:30:00+00:00"),
+            Timestamp("2023-10-15 17:30:00+00:00"),
+            Timestamp("2023-10-15 14:30:00+00:00"),
+        ]
+    )
+    tm.assert_index_equal(result, expected)
+
+
 def test_unknown_tz_raises():
     # GH#18702, GH#51476
     dtstr = "2014 Jan 9 05:15 FAKE"
