BUG: DatetimeIndex ignoring explicit tz=None (#48659)

* BUG: DatetimeIndex ignoring explicit tz=None

* GH ref

Author: jbrockmendel

doc/source/whatsnew/v1.6.0.rst

@@ -162,7 +162,7 @@ Categorical
 Datetimelike
 ^^^^^^^^^^^^
 - Bug in :func:`pandas.infer_freq`, raising ``TypeError`` when inferred on :class:`RangeIndex` (:issue:`47084`)
--
+- Bug in :class:`DatetimeIndex` constructor failing to raise when ``tz=None`` is explicitly specified in conjunction with timezone-aware ``dtype`` or data (:issue:`48659`)
 
 Timedelta
 ^^^^^^^^^

pandas/core/arrays/datetimes.py

@@ -294,7 +294,7 @@ def _from_sequence_not_strict(
         data,
         dtype=None,
         copy: bool = False,
-        tz=None,
+        tz=lib.no_default,
         freq: str | BaseOffset | lib.NoDefault | None = lib.no_default,
         dayfirst: bool = False,
         yearfirst: bool = False,
@@ -1986,7 +1986,7 @@ def _sequence_to_dt64ns(
     data,
     dtype=None,
     copy: bool = False,
-    tz=None,
+    tz=lib.no_default,
     dayfirst: bool = False,
     yearfirst: bool = False,
     ambiguous="raise",
@@ -2023,14 +2023,17 @@ def _sequence_to_dt64ns(
     ------
     TypeError : PeriodDType data is passed
     """
+    explicit_tz_none = tz is None
+    if tz is lib.no_default:
+        tz = None
 
     inferred_freq = None
 
     dtype = _validate_dt64_dtype(dtype)
     tz = timezones.maybe_get_tz(tz)
 
     # if dtype has an embedded tz, capture it
-    tz = validate_tz_from_dtype(dtype, tz)
+    tz = validate_tz_from_dtype(dtype, tz, explicit_tz_none)
 
     data, copy = dtl.ensure_arraylike_for_datetimelike(
         data, copy, cls_name="DatetimeArray"
@@ -2126,7 +2129,12 @@ def _sequence_to_dt64ns(
     assert result.dtype == "M8[ns]", result.dtype
 
     # We have to call this again after possibly inferring a tz above
-    validate_tz_from_dtype(dtype, tz)
+    validate_tz_from_dtype(dtype, tz, explicit_tz_none)
+    if tz is not None and explicit_tz_none:
+        raise ValueError(
+            "Passed data is timezone-aware, incompatible with 'tz=None'. "
+            "Use obj.tz_localize(None) instead."
+        )
 
     return result, tz, inferred_freq
 
@@ -2368,7 +2376,9 @@ def _validate_dt64_dtype(dtype):
     return dtype
 
 
-def validate_tz_from_dtype(dtype, tz: tzinfo | None) -> tzinfo | None:
+def validate_tz_from_dtype(
+    dtype, tz: tzinfo | None, explicit_tz_none: bool = False
+) -> tzinfo | None:
     """
     If the given dtype is a DatetimeTZDtype, extract the implied
     tzinfo object from it and check that it does not conflict with the given
@@ -2378,6 +2388,8 @@ def validate_tz_from_dtype(dtype, tz: tzinfo | None) -> tzinfo | None:
     ----------
     dtype : dtype, str
     tz : None, tzinfo
+    explicit_tz_none : bool, default False
+        Whether tz=None was passed explicitly, as opposed to lib.no_default.
 
     Returns
     -------
@@ -2401,6 +2413,8 @@ def validate_tz_from_dtype(dtype, tz: tzinfo | None) -> tzinfo | None:
         if dtz is not None:
             if tz is not None and not timezones.tz_compare(tz, dtz):
                 raise ValueError("cannot supply both a tz and a dtype with a tz")
+            elif explicit_tz_none:
+                raise ValueError("Cannot pass both a timezone-aware dtype and tz=None")
             tz = dtz
 
         if tz is not None and is_datetime64_dtype(dtype):

pandas/core/indexes/datetimes.py

@@ -315,7 +315,7 @@ def __new__(
         cls,
         data=None,
         freq: str | BaseOffset | lib.NoDefault = lib.no_default,
-        tz=None,
+        tz=lib.no_default,
         normalize: bool = False,
         closed=None,
         ambiguous="raise",
@@ -336,7 +336,7 @@ def __new__(
         if (
             isinstance(data, DatetimeArray)
             and freq is lib.no_default
-            and tz is None
+            and tz is lib.no_default
             and dtype is None
         ):
             # fastpath, similar logic in TimedeltaIndex.__new__;
@@ -347,7 +347,7 @@ def __new__(
         elif (
             isinstance(data, DatetimeArray)
             and freq is lib.no_default
-            and tz is None
+            and tz is lib.no_default
             and is_dtype_equal(data.dtype, dtype)
         ):
             # Reached via Index.__new__ when we call .astype

pandas/tests/indexes/datetimes/test_constructors.py

@@ -37,6 +37,21 @@
 
 
 class TestDatetimeIndex:
+    def test_explicit_tz_none(self):
+        # GH#48659
+        dti = date_range("2016-01-01", periods=10, tz="UTC")
+
+        msg = "Passed data is timezone-aware, incompatible with 'tz=None'"
+        with pytest.raises(ValueError, match=msg):
+            DatetimeIndex(dti, tz=None)
+
+        with pytest.raises(ValueError, match=msg):
+            DatetimeIndex(np.array(dti), tz=None)
+
+        msg = "Cannot pass both a timezone-aware dtype and tz=None"
+        with pytest.raises(ValueError, match=msg):
+            DatetimeIndex([], dtype="M8[ns, UTC]", tz=None)
+
     @pytest.mark.parametrize(
         "dt_cls", [DatetimeIndex, DatetimeArray._from_sequence_not_strict]
     )