annotation, missing test case, perf DTA.mode (#47418)

Author: jbrockmendel

pandas/_libs/tslibs/tzconversion.pyx

@@ -519,7 +519,7 @@ cdef ndarray[int64_t] _get_dst_hours(
     trans_idx = mismatch.nonzero()[0]
 
     if trans_idx.size == 1:
-        # TODO: not reached in tests 2022-05-02; possible?
+        # see test_tz_localize_to_utc_ambiguous_infer
         stamp = _render_tstamp(vals[trans_idx[0]], reso=reso)
         raise pytz.AmbiguousTimeError(
             f"Cannot infer dst time from {stamp} as there "
@@ -541,15 +541,15 @@ cdef ndarray[int64_t] _get_dst_hours(
 
             delta = np.diff(result_a[grp])
             if grp.size == 1 or np.all(delta > 0):
-                # TODO: not reached in tests 2022-05-02; possible?
+                # see test_tz_localize_to_utc_ambiguous_infer
                 stamp = _render_tstamp(vals[grp[0]], reso=reso)
                 raise pytz.AmbiguousTimeError(stamp)
 
             # Find the index for the switch and pull from a for dst and b
             # for standard
             switch_idxs = (delta <= 0).nonzero()[0]
             if switch_idxs.size > 1:
-                # TODO: not reached in tests 2022-05-02; possible?
+                # see test_tz_localize_to_utc_ambiguous_infer
                 raise pytz.AmbiguousTimeError(
                     f"There are {switch_idxs.size} dst switches when "
                     "there should only be 1."

pandas/core/arrays/datetimelike.py

@@ -1088,12 +1088,13 @@ def _cmp_method(self, other, op):
 
     @final
     def _add_datetimelike_scalar(self, other):
-        # Overridden by TimedeltaArray
         if not is_timedelta64_dtype(self.dtype):
             raise TypeError(
                 f"cannot add {type(self).__name__} and {type(other).__name__}"
             )
 
+        self = cast("TimedeltaArray", self)
+
         from pandas.core.arrays import DatetimeArray
 
         assert other is not NaT
@@ -1115,7 +1116,7 @@ def _add_datetimelike_scalar(self, other):
         return DatetimeArray(result, dtype=dtype, freq=self.freq)
 
     @final
-    def _add_datetime_arraylike(self, other):
+    def _add_datetime_arraylike(self, other) -> DatetimeArray:
         if not is_timedelta64_dtype(self.dtype):
             raise TypeError(
                 f"cannot add {type(self).__name__} and {type(other).__name__}"
@@ -1679,12 +1680,11 @@ def median(self, *, axis: int | None = None, skipna: bool = True, **kwargs):
         return self._wrap_reduction_result(axis, result)
 
     def _mode(self, dropna: bool = True):
-        values = self
+        mask = None
         if dropna:
-            mask = values.isna()
-            values = values[~mask]
+            mask = self.isna()
 
-        i8modes = mode(values.view("i8"))
+        i8modes = mode(self.view("i8"), mask=mask)
         npmodes = i8modes.view(self._ndarray.dtype)
         npmodes = cast(np.ndarray, npmodes)
         return self._from_backing_data(npmodes)

pandas/tests/tslibs/test_tzconversion.py

@@ -0,0 +1,23 @@
+import numpy as np
+import pytest
+import pytz
+
+from pandas._libs.tslibs.tzconversion import tz_localize_to_utc
+
+
+class TestTZLocalizeToUTC:
+    def test_tz_localize_to_utc_ambiguous_infer(self):
+        # val is a timestamp that is ambiguous when localized to US/Eastern
+        val = 1_320_541_200_000_000_000
+        vals = np.array([val, val - 1, val], dtype=np.int64)
+
+        with pytest.raises(pytz.AmbiguousTimeError, match="2011-11-06 01:00:00"):
+            tz_localize_to_utc(vals, pytz.timezone("US/Eastern"), ambiguous="infer")
+
+        with pytest.raises(pytz.AmbiguousTimeError, match="are no repeated times"):
+            tz_localize_to_utc(vals[:1], pytz.timezone("US/Eastern"), ambiguous="infer")
+
+        vals[1] += 1
+        msg = "There are 2 dst switches when there should only be 1"
+        with pytest.raises(pytz.AmbiguousTimeError, match=msg):
+            tz_localize_to_utc(vals, pytz.timezone("US/Eastern"), ambiguous="infer")