BUG: to_datetime with mixed-string-and-numeric

doc/source/whatsnew/v2.2.0.rst

@@ -321,7 +321,9 @@ Categorical
 
 Datetimelike
 ^^^^^^^^^^^^
+- Bug in :class:`DatetimeIndex` when passing an object-dtype ndarray of float objects and a ``tz`` incorrectly localizing the result (:issue:`55780`)
 - Bug in :func:`concat` raising ``AttributeError`` when concatenating all-NA DataFrame with :class:`DatetimeTZDtype` dtype DataFrame. (:issue:`52093`)
+- Bug in :func:`to_datetime` and :class:`DatetimeIndex` when passing a list of mixed-string-and-numeric types incorrectly raising (:issue:`55780`)
 - Bug in :meth:`DatetimeIndex.union` returning object dtype for tz-aware indexes with the same timezone but different units (:issue:`55238`)
 - Bug in :meth:`Index.is_monotonic_increasing` and :meth:`Index.is_monotonic_decreasing` always caching :meth:`Index.is_unique` as ``True`` when first value in index is ``NaT`` (:issue:`55755`)
 - Bug in :meth:`Index.view` to a datetime64 dtype with non-supported resolution incorrectly raising (:issue:`55710`)

pandas/_libs/tslib.pyx

@@ -700,15 +700,15 @@ def array_to_datetime_with_tz(ndarray values, tzinfo tz, NPY_DATETIMEUNIT creso)
             ival = NPY_NAT
 
         else:
-            ts = Timestamp(item)
+            if PyDateTime_Check(item) and item.tzinfo is not None:
+                # We can't call Timestamp constructor with a tz arg, have to
+                #  do 2-step
+                ts = Timestamp(item).tz_convert(tz)
+            else:
+                ts = Timestamp(item, tz=tz)
             if ts is NaT:
                 ival = NPY_NAT
             else:
-                if ts.tzinfo is not None:
-                    ts = ts.tz_convert(tz)
-                else:
-                    # datetime64, tznaive pydatetime, int, float
-                    ts = ts.tz_localize(tz)
                 ts = (<_Timestamp>ts)._as_creso(creso)
                 ival = ts._value
 

pandas/core/arrays/datetimelike.py

@@ -81,6 +81,7 @@
 )
 from pandas.util._exceptions import find_stack_level
 
+from pandas.core.dtypes.cast import construct_1d_object_array_from_listlike
 from pandas.core.dtypes.common import (
     is_all_strings,
     is_integer_dtype,
@@ -2358,7 +2359,8 @@ def ensure_arraylike_for_datetimelike(data, copy: bool, cls_name: str):
         if not isinstance(data, (list, tuple)) and np.ndim(data) == 0:
             # i.e. generator
             data = list(data)
-        data = np.asarray(data)
+
+        data = construct_1d_object_array_from_listlike(data)
         copy = False
     elif isinstance(data, ABCMultiIndex):
         raise TypeError(f"Cannot create a {cls_name} from a MultiIndex.")

pandas/tests/dtypes/test_missing.py

@@ -418,12 +418,10 @@ def test_array_equivalent(dtype_equal):
     assert not array_equivalent(
         Index([0, np.nan]), Index([1, np.nan]), dtype_equal=dtype_equal
     )
-    assert array_equivalent(
-        DatetimeIndex([0, np.nan]), DatetimeIndex([0, np.nan]), dtype_equal=dtype_equal
-    )
-    assert not array_equivalent(
-        DatetimeIndex([0, np.nan]), DatetimeIndex([1, np.nan]), dtype_equal=dtype_equal
-    )
+
+
+@pytest.mark.parametrize("dtype_equal", [True, False])
+def test_array_equivalent_tdi(dtype_equal):
     assert array_equivalent(
         TimedeltaIndex([0, np.nan]),
         TimedeltaIndex([0, np.nan]),
@@ -435,6 +433,16 @@ def test_array_equivalent(dtype_equal):
         dtype_equal=dtype_equal,
     )
 
+
+@pytest.mark.parametrize("dtype_equal", [True, False])
+def test_array_equivalent_dti(dtype_equal):
+    assert array_equivalent(
+        DatetimeIndex([0, np.nan]), DatetimeIndex([0, np.nan]), dtype_equal=dtype_equal
+    )
+    assert not array_equivalent(
+        DatetimeIndex([0, np.nan]), DatetimeIndex([1, np.nan]), dtype_equal=dtype_equal
+    )
+
     dti1 = DatetimeIndex([0, np.nan], tz="US/Eastern")
     dti2 = DatetimeIndex([0, np.nan], tz="CET")
     dti3 = DatetimeIndex([1, np.nan], tz="US/Eastern")

pandas/tests/frame/test_constructors.py

@@ -3154,9 +3154,9 @@ def test_from_scalar_datetimelike_mismatched(self, constructor, cls):
         dtype = {np.datetime64: "m8[ns]", np.timedelta64: "M8[ns]"}[cls]
 
         if cls is np.datetime64:
-            msg1 = r"dtype datetime64\[ns\] cannot be converted to timedelta64\[ns\]"
+            msg1 = "Invalid type for timedelta scalar: <class 'numpy.datetime64'>"
         else:
-            msg1 = r"dtype timedelta64\[ns\] cannot be converted to datetime64\[ns\]"
+            msg1 = "<class 'numpy.timedelta64'> is not convertible to datetime"
         msg = "|".join(["Cannot cast", msg1])
 
         with pytest.raises(TypeError, match=msg):

pandas/tests/indexes/datetimes/test_constructors.py

@@ -1024,8 +1024,11 @@ def test_dti_constructor_with_non_nano_dtype(self, tz):
         # to 2 microseconds
         vals = [ts, "2999-01-02 03:04:05.678910", 2500]
         result = DatetimeIndex(vals, dtype=dtype)
-        exp_arr = np.array([ts.asm8, vals[1], 2], dtype="M8[us]")
-        expected = DatetimeIndex(exp_arr, dtype="M8[us]").tz_localize(tz)
+        exp_vals = [Timestamp(x, tz=tz).as_unit("us").asm8 for x in vals]
+        exp_arr = np.array(exp_vals, dtype="M8[us]")
+        expected = DatetimeIndex(exp_arr, dtype="M8[us]")
+        if tz is not None:
+            expected = expected.tz_localize("UTC").tz_convert(tz)
         tm.assert_index_equal(result, expected)
 
         result2 = DatetimeIndex(np.array(vals, dtype=object), dtype=dtype)
@@ -1050,6 +1053,15 @@ def test_dti_constructor_with_non_nano_now_today(self):
         assert diff1 >= pd.Timedelta(0)
         assert diff1 < tolerance
 
+    def test_dti_constructor_object_float_matches_float_dtype(self):
+        # GH#55780
+        arr = np.array([0, np.nan], dtype=np.float64)
+        arr2 = arr.astype(object)
+
+        dti1 = DatetimeIndex(arr, tz="CET")
+        dti2 = DatetimeIndex(arr2, tz="CET")
+        tm.assert_index_equal(dti1, dti2)
+
 
 class TestTimeSeries:
     def test_dti_constructor_preserve_dti_freq(self):

pandas/tests/series/methods/test_astype.py

@@ -120,8 +120,11 @@ def test_astype_object_to_dt64_non_nano(self, tz):
         ser = Series(vals, dtype=object)
         result = ser.astype(dtype)
 
-        exp_arr = np.array([ts.asm8, vals[1], 2], dtype="M8[us]")
-        expected = Series(exp_arr, dtype="M8[us]").dt.tz_localize(tz)
+        exp_vals = [Timestamp(x, tz=tz).as_unit("us").asm8 for x in vals]
+        exp_arr = np.array(exp_vals, dtype="M8[us]")
+        expected = Series(exp_arr, dtype="M8[us]")
+        if tz is not None:
+            expected = expected.dt.tz_localize("UTC").dt.tz_convert(tz)
         tm.assert_series_equal(result, expected)
 
     def test_astype_mixed_object_to_dt64tz(self):

pandas/tests/tools/test_to_datetime.py

@@ -603,6 +603,20 @@ def test_to_datetime_mixed_datetime_and_string(self):
         expected = to_datetime([d1, d2]).tz_convert(timezone(timedelta(minutes=-60)))
         tm.assert_index_equal(res, expected)
 
+    def test_to_datetime_mixed_string_and_numeric(self):
+        # GH#55780 np.array(vals) would incorrectly cast the number to str
+        vals = ["2016-01-01", 0]
+        expected = DatetimeIndex([Timestamp(x) for x in vals])
+        result = to_datetime(vals, format="mixed")
+        result2 = to_datetime(vals[::-1], format="mixed")[::-1]
+        result3 = DatetimeIndex(vals)
+        result4 = DatetimeIndex(vals[::-1])[::-1]
+
+        tm.assert_index_equal(result, expected)
+        tm.assert_index_equal(result2, expected)
+        tm.assert_index_equal(result3, expected)
+        tm.assert_index_equal(result4, expected)
+
     @pytest.mark.parametrize(
         "format", ["%Y-%m-%d", "%Y-%d-%m"], ids=["ISO8601", "non-ISO8601"]
     )