BUG: Avoid AmbiguousTime or NonExistentTime Error when resampling (#22809)

Author: mroeschke

doc/source/whatsnew/v0.24.0.txt

@@ -679,6 +679,7 @@ Timezones
 - Bug when setting a new value with :meth:`DataFrame.loc` with a :class:`DatetimeIndex` with a DST transition (:issue:`18308`, :issue:`20724`)
 - Bug in :meth:`DatetimeIndex.unique` that did not re-localize tz-aware dates correctly (:issue:`21737`)
 - Bug when indexing a :class:`Series` with a DST transition (:issue:`21846`)
+- Bug in :meth:`DataFrame.resample` and :meth:`Series.resample` where an ``AmbiguousTimeError`` or ``NonExistentTimeError`` would raise if a timezone aware timeseries ended on a DST transition (:issue:`19375`, :issue:`10117`)
 
 Offsets
 ^^^^^^^

pandas/core/resample.py

@@ -1328,8 +1328,7 @@ def _get_time_bins(self, ax):
                 data=[], freq=self.freq, name=ax.name)
             return binner, [], labels
 
-        first, last = ax.min(), ax.max()
-        first, last = _get_range_edges(first, last, self.freq,
+        first, last = _get_range_edges(ax.min(), ax.max(), self.freq,
                                        closed=self.closed,
                                        base=self.base)
         tz = ax.tz
@@ -1519,9 +1518,6 @@ def _take_new_index(obj, indexer, new_index, axis=0):
 
 
 def _get_range_edges(first, last, offset, closed='left', base=0):
-    if isinstance(offset, compat.string_types):
-        offset = to_offset(offset)
-
     if isinstance(offset, Tick):
         is_day = isinstance(offset, Day)
         day_nanos = delta_to_nanoseconds(timedelta(1))
@@ -1531,8 +1527,7 @@ def _get_range_edges(first, last, offset, closed='left', base=0):
             return _adjust_dates_anchored(first, last, offset,
                                           closed=closed, base=base)
 
-    if not isinstance(offset, Tick):  # and first.time() != last.time():
-        # hack!
+    else:
         first = first.normalize()
         last = last.normalize()
 
@@ -1553,19 +1548,16 @@ def _adjust_dates_anchored(first, last, offset, closed='right', base=0):
     #
     # See https://github.com/pandas-dev/pandas/issues/8683
 
-    # 14682 - Since we need to drop the TZ information to perform
-    # the adjustment in the presence of a DST change,
-    # save TZ Info and the DST state of the first and last parameters
-    # so that we can accurately rebuild them at the end.
+    # GH 10117 & GH 19375. If first and last contain timezone information,
+    # Perform the calculation in UTC in order to avoid localizing on an
+    # Ambiguous or Nonexistent time.
     first_tzinfo = first.tzinfo
     last_tzinfo = last.tzinfo
-    first_dst = bool(first.dst())
-    last_dst = bool(last.dst())
-
-    first = first.tz_localize(None)
-    last = last.tz_localize(None)
-
     start_day_nanos = first.normalize().value
+    if first_tzinfo is not None:
+        first = first.tz_convert('UTC')
+    if last_tzinfo is not None:
+        last = last.tz_convert('UTC')
 
     base_nanos = (base % offset.n) * offset.nanos // offset.n
     start_day_nanos += base_nanos
@@ -1598,9 +1590,13 @@ def _adjust_dates_anchored(first, last, offset, closed='right', base=0):
             lresult = last.value + (offset.nanos - loffset)
         else:
             lresult = last.value + offset.nanos
-
-    return (Timestamp(fresult).tz_localize(first_tzinfo, ambiguous=first_dst),
-            Timestamp(lresult).tz_localize(last_tzinfo, ambiguous=last_dst))
+    fresult = Timestamp(fresult)
+    lresult = Timestamp(lresult)
+    if first_tzinfo is not None:
+        fresult = fresult.tz_localize('UTC').tz_convert(first_tzinfo)
+    if last_tzinfo is not None:
+        lresult = lresult.tz_localize('UTC').tz_convert(last_tzinfo)
+    return fresult, lresult
 
 
 def asfreq(obj, freq, method=None, how=None, normalize=False, fill_value=None):

pandas/tests/test_resample.py

@@ -2485,6 +2485,22 @@ def test_with_local_timezone_dateutil(self):
         expected = Series(1, index=expected_index)
         assert_series_equal(result, expected)
 
+    def test_resample_nonexistent_time_bin_edge(self):
+        # GH 19375
+        index = date_range('2017-03-12', '2017-03-12 1:45:00', freq='15T')
+        s = Series(np.zeros(len(index)), index=index)
+        expected = s.tz_localize('US/Pacific')
+        result = expected.resample('900S').mean()
+        tm.assert_series_equal(result, expected)
+
+    def test_resample_ambiguous_time_bin_edge(self):
+        # GH 10117
+        idx = pd.date_range("2014-10-25 22:00:00", "2014-10-26 00:30:00",
+                            freq="30T", tz="Europe/London")
+        expected = Series(np.zeros(len(idx)), index=idx)
+        result = expected.resample('30T').mean()
+        tm.assert_series_equal(result, expected)
+
     def test_fill_method_and_how_upsample(self):
         # GH2073
         s = Series(np.arange(9, dtype='int64'),