DEPR: disallow parsing datetimes with mixed time zones unless utc=True

asv_bench/benchmarks/inference.py

@@ -200,7 +200,7 @@ def time_same_offset(self):
         to_datetime(self.same_offset)
 
     def time_different_offset(self):
-        to_datetime(self.diff_offset)
+        to_datetime(self.diff_offset, utc=True)
 
 
 class ToDatetimeFormatQuarters:
@@ -231,9 +231,6 @@ def time_no_exact(self):
     def time_same_offset(self):
         to_datetime(self.same_offset, format="%m/%d/%Y %H:%M:%S.%f%z")
 
-    def time_different_offset(self):
-        to_datetime(self.diff_offset, format="%m/%d/%Y %H:%M:%S.%f%z")
-
     def time_same_offset_to_utc(self):
         to_datetime(self.same_offset, format="%m/%d/%Y %H:%M:%S.%f%z", utc=True)
 

doc/source/whatsnew/v3.0.0.rst

@@ -113,6 +113,7 @@ Removal of prior version deprecations/changes
 - All arguments in :meth:`Index.sort_values` are now keyword only (:issue:`56493`)
 - All arguments in :meth:`Series.to_dict` are now keyword only (:issue:`56493`)
 - Changed the default value of ``observed`` in :meth:`DataFrame.groupby` and :meth:`Series.groupby` to ``True`` (:issue:`51811`)
+- Enforced deprecation disallowing parsing datetimes with mixed time zones unless user passes ``utc=True`` to :func:`to_datetime` (:issue:`57275`)
 - Enforced silent-downcasting deprecation for :ref:`all relevant methods <whatsnew_220.silent_downcasting>` (:issue:`54710`)
 - In :meth:`DataFrame.stack`, the default value of ``future_stack`` is now ``True``; specifying ``False`` will raise a ``FutureWarning`` (:issue:`55448`)
 - Removed ``DataFrame.applymap``, ``Styler.applymap`` and ``Styler.applymap_index`` (:issue:`52364`)

pandas/_libs/tslib.pyx

@@ -744,15 +744,7 @@ cdef _array_to_datetime_object(
 
         cnp.PyArray_MultiIter_NEXT(mi)
 
-    warnings.warn(
-        "In a future version of pandas, parsing datetimes with mixed time "
-        "zones will raise an error unless `utc=True`. "
-        "Please specify `utc=True` to opt in to the new behaviour "
-        "and silence this warning. To create a `Series` with mixed offsets and "
-        "`object` dtype, please use `apply` and `datetime.datetime.strptime`",
-        FutureWarning,
-        stacklevel=find_stack_level(),
-    )
+    raise ValueError("cannot parse datetimes with mixed time zones unless `utc=True`")
     return oresult_nd, None
 
 

pandas/_libs/tslibs/strptime.pyx

@@ -923,18 +923,7 @@ def _array_strptime_object_fallback(
             else:
                 raise
 
-    import warnings
-
-    from pandas.util._exceptions import find_stack_level
-    warnings.warn(
-        "In a future version of pandas, parsing datetimes with mixed time "
-        "zones will raise an error unless `utc=True`. Please specify `utc=True` "
-        "to opt in to the new behaviour and silence this warning. "
-        "To create a `Series` with mixed offsets and `object` dtype, "
-        "please use `apply` and `datetime.datetime.strptime`",
-        FutureWarning,
-        stacklevel=find_stack_level(),
-    )
+    raise ValueError("cannot parse datetimes with mixed time zones unless `utc=True`")
 
     return result
 

pandas/core/tools/datetimes.py

@@ -723,14 +723,6 @@ def to_datetime(
           offsets (typically, daylight savings), see :ref:`Examples
           <to_datetime_tz_examples>` section for details.
 
-        .. warning::
-
-            In a future version of pandas, parsing datetimes with mixed time
-            zones will raise an error unless `utc=True`.
-            Please specify `utc=True` to opt in to the new behaviour
-            and silence this warning. To create a `Series` with mixed offsets and
-            `object` dtype, please use `apply` and `datetime.datetime.strptime`.
-
         See also: pandas general documentation about `timezone conversion and
         localization
         <https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html
@@ -812,7 +804,9 @@ def to_datetime(
         When another datetime conversion error happens. For example when one
         of 'year', 'month', day' columns is missing in a :class:`DataFrame`, or
         when a Timezone-aware :class:`datetime.datetime` is found in an array-like
-        of mixed time offsets, and ``utc=False``.
+        of mixed time offsets, and ``utc=False``, or when parsing datetimes
+        with mixed time zones unless ``utc=True``. Parsing datetimes with mixed
+        time zones, please specify ``utc=True`` to opt in to the new behaviour.
 
     See Also
     --------
@@ -932,35 +926,32 @@ def to_datetime(
     - However, timezone-aware inputs *with mixed time offsets* (for example
       issued from a timezone with daylight savings, such as Europe/Paris)
       are **not successfully converted** to a :class:`DatetimeIndex`.
-      Parsing datetimes with mixed time zones will show a warning unless
-      `utc=True`. If you specify `utc=False` the warning below will be shown
-      and a simple :class:`Index` containing :class:`datetime.datetime`
-      objects will be returned:
+      Parsing datetimes with mixed time zones will raise a ValueError unless
+      ``utc=True``:
 
     >>> pd.to_datetime(
     ...     ["2020-10-25 02:00 +0200", "2020-10-25 04:00 +0100"]
     ... )  # doctest: +SKIP
-    FutureWarning: In a future version of pandas, parsing datetimes with mixed
-    time zones will raise an error unless `utc=True`. Please specify `utc=True`
-    to opt in to the new behaviour and silence this warning. To create a `Series`
-    with mixed offsets and `object` dtype, please use `apply` and
-    `datetime.datetime.strptime`.
-    Index([2020-10-25 02:00:00+02:00, 2020-10-25 04:00:00+01:00],
-          dtype='object')
+    ValueError: cannot parse datetimes with mixed time zones unless `utc=True`
+
+    - To create a :class:`Series` with mixed offsets and ``object`` dtype, please use
+      :meth:`Series.apply` and :func:`datetime.datetime.strptime`:
+
+    >>> import datetime as dt
+    >>> ser = pd.Series(["2020-10-25 02:00 +0200", "2020-10-25 04:00 +0100"])
+    >>> ser.apply(lambda x: dt.datetime.strptime(x, "%Y-%m-%d %H:%M %z"))
+    0    2020-10-25 02:00:00+02:00
+    1    2020-10-25 04:00:00+01:00
+    dtype: object
 
-    - A mix of timezone-aware and timezone-naive inputs is also converted to
-      a simple :class:`Index` containing :class:`datetime.datetime` objects:
+    - A mix of timezone-aware and timezone-naive inputs will also raise a ValueError
+      unless ``utc=True``:
 
     >>> from datetime import datetime
     >>> pd.to_datetime(
     ...     ["2020-01-01 01:00:00-01:00", datetime(2020, 1, 1, 3, 0)]
     ... )  # doctest: +SKIP
-    FutureWarning: In a future version of pandas, parsing datetimes with mixed
-    time zones will raise an error unless `utc=True`. Please specify `utc=True`
-    to opt in to the new behaviour and silence this warning. To create a `Series`
-    with mixed offsets and `object` dtype, please use `apply` and
-    `datetime.datetime.strptime`.
-    Index([2020-01-01 01:00:00-01:00, 2020-01-01 03:00:00], dtype='object')
+    ValueError: cannot parse datetimes with mixed time zones unless `utc=True`
 
     |
 

pandas/io/json/_json.py

@@ -1292,14 +1292,7 @@ def _try_convert_to_date(self, data: Series) -> tuple[Series, bool]:
         date_units = (self.date_unit,) if self.date_unit else self._STAMP_UNITS
         for date_unit in date_units:
             try:
-                with warnings.catch_warnings():
-                    warnings.filterwarnings(
-                        "ignore",
-                        ".*parsing datetimes with mixed time "
-                        "zones will raise an error",
-                        category=FutureWarning,
-                    )
-                    new_data = to_datetime(new_data, errors="raise", unit=date_unit)
+                new_data = to_datetime(new_data, errors="raise", unit=date_unit)
             except (ValueError, OverflowError, TypeError):
                 continue
             return new_data, True

pandas/io/parsers/base_parser.py

@@ -1158,24 +1158,18 @@ def converter(*date_cols, col: Hashable):
                 date_format.get(col) if isinstance(date_format, dict) else date_format
             )
 
-            with warnings.catch_warnings():
-                warnings.filterwarnings(
-                    "ignore",
-                    ".*parsing datetimes with mixed time zones will raise an error",
-                    category=FutureWarning,
+            str_objs = ensure_object(strs)
+            try:
+                result = tools.to_datetime(
+                    str_objs,
+                    format=date_fmt,
+                    utc=False,
+                    dayfirst=dayfirst,
+                    cache=cache_dates,
                 )
-                str_objs = ensure_object(strs)
-                try:
-                    result = tools.to_datetime(
-                        str_objs,
-                        format=date_fmt,
-                        utc=False,
-                        dayfirst=dayfirst,
-                        cache=cache_dates,
-                    )
-                except (ValueError, TypeError):
-                    # test_usecols_with_parse_dates4
-                    return str_objs
+            except (ValueError, TypeError):
+                # test_usecols_with_parse_dates4
+                return str_objs
 
             if isinstance(result, DatetimeIndex):
                 arr = result.to_numpy()
@@ -1184,45 +1178,31 @@ def converter(*date_cols, col: Hashable):
             return result._values
         else:
             try:
-                with warnings.catch_warnings():
-                    warnings.filterwarnings(
-                        "ignore",
-                        ".*parsing datetimes with mixed time zones "
-                        "will raise an error",
-                        category=FutureWarning,
-                    )
-                    pre_parsed = date_parser(
-                        *(unpack_if_single_element(arg) for arg in date_cols)
+                pre_parsed = date_parser(
+                    *(unpack_if_single_element(arg) for arg in date_cols)
+                )
+                try:
+                    result = tools.to_datetime(
+                        pre_parsed,
+                        cache=cache_dates,
                     )
-                    try:
-                        result = tools.to_datetime(
-                            pre_parsed,
-                            cache=cache_dates,
-                        )
-                    except (ValueError, TypeError):
-                        # test_read_csv_with_custom_date_parser
-                        result = pre_parsed
+                except (ValueError, TypeError):
+                    # test_read_csv_with_custom_date_parser
+                    result = pre_parsed
                 if isinstance(result, datetime.datetime):
                     raise Exception("scalar parser")
                 return result
             except Exception:
                 # e.g. test_datetime_fractional_seconds
-                with warnings.catch_warnings():
-                    warnings.filterwarnings(
-                        "ignore",
-                        ".*parsing datetimes with mixed time zones "
-                        "will raise an error",
-                        category=FutureWarning,
-                    )
-                    pre_parsed = parsing.try_parse_dates(
-                        parsing.concat_date_cols(date_cols),
-                        parser=date_parser,
-                    )
-                    try:
-                        return tools.to_datetime(pre_parsed)
-                    except (ValueError, TypeError):
-                        # TODO: not reached in tests 2023-10-27; needed?
-                        return pre_parsed
+                pre_parsed = parsing.try_parse_dates(
+                    parsing.concat_date_cols(date_cols),
+                    parser=date_parser,
+                )
+                try:
+                    return tools.to_datetime(pre_parsed)
+                except (ValueError, TypeError):
+                    # TODO: not reached in tests 2023-10-27; needed?
+                    return pre_parsed
 
     return converter
 

pandas/tests/indexes/datetimes/test_constructors.py

@@ -296,11 +296,9 @@ def test_construction_index_with_mixed_timezones(self):
         tm.assert_index_equal(result, exp, exact=True)
         assert not isinstance(result, DatetimeIndex)
 
-        msg = "DatetimeIndex has mixed timezones"
-        msg_depr = "parsing datetimes with mixed time zones will raise an error"
-        with pytest.raises(TypeError, match=msg):
-            with tm.assert_produces_warning(FutureWarning, match=msg_depr):
-                DatetimeIndex(["2013-11-02 22:00-05:00", "2013-11-03 22:00-06:00"])
+        msg = "cannot parse datetimes with mixed time zones unless `utc=True`"
+        with pytest.raises(ValueError, match=msg):
+            DatetimeIndex(["2013-11-02 22:00-05:00", "2013-11-03 22:00-06:00"])
 
         # length = 1
         result = Index([Timestamp("2011-01-01")], name="idx")

pandas/tests/io/parser/common/test_read_errors.py

@@ -18,7 +18,10 @@
     ParserWarning,
 )
 
-from pandas import DataFrame
+from pandas import (
+    DataFrame,
+    Series,
+)
 import pandas._testing as tm
 
 xfail_pyarrow = pytest.mark.usefixtures("pyarrow_xfail")
@@ -161,10 +164,10 @@ def test_suppress_error_output(all_parsers):
     # see gh-15925
     parser = all_parsers
     data = "a\n1\n1,2,3\n4\n5,6,7"
-    expected = DataFrame({"a": [1, 4]})
+    expected = Series([1, 4], name="a", index=[0, 1])
 
-    result = parser.read_csv(StringIO(data), on_bad_lines="skip")
-    tm.assert_frame_equal(result, expected)
+    result = parser.read_csv(StringIO(data), on_bad_lines="skip")["a"]
+    tm.assert_series_equal(result, expected)
 
 
 def test_error_bad_lines(all_parsers):

pandas/tests/io/parser/test_parse_dates.py

@@ -2330,8 +2330,8 @@ def test_from_csv_with_mixed_offsets(all_parsers):
     result = parser.read_csv(StringIO(data), parse_dates=["a"])["a"]
     expected = Series(
         [
-            Timestamp("2020-01-01 00:00:00+01:00"),
-            Timestamp("2020-01-01 00:00:00+00:00"),
+            "2020-01-01T00:00:00+01:00",
+            "2020-01-01T00:00:00+00:00",
         ],
         name="a",
         index=[0, 1],