Merge branch 'dst-date-offset' of https://github.com/adamgreenhall/pandas into adamgreenhall-dst-date-offset

Conflicts:
	doc/source/v0.15.0.txt

Author: jreback

doc/source/v0.15.0.txt

@@ -620,6 +620,8 @@ Bug Fixes
 
 - Bug in ``DataFrame.to_latex`` formatting when columns or index is a ``MultiIndex`` (:issue:`7982`).
 
+- Bug in ``DateOffset`` around Daylight Savings Time produces unexpected results (:issue:`5175`).
+
 
 
 

pandas/tseries/offsets.py

@@ -152,6 +152,12 @@ def __add__(date):
     """
     _cacheable = False
     _normalize_cache = True
+    _kwds_use_relativedelta = (
+        'years', 'months', 'weeks', 'days',
+        'year', 'month', 'week', 'day', 'weekday',
+        'hour', 'minute', 'second', 'microsecond'
+        )
+    _use_relativedelta = False
 
     # default for prior pickles
     normalize = False
@@ -160,21 +166,52 @@ def __init__(self, n=1, normalize=False, **kwds):
         self.n = int(n)
         self.normalize = normalize
         self.kwds = kwds
-        if len(kwds) > 0:
-            self._offset = relativedelta(**kwds)
+        self._offset, self._use_relativedelta = self._determine_offset()
+
+    def _determine_offset(self):
+        # timedelta is used for sub-daily plural offsets and all singular offsets
+        # relativedelta is used for plural offsets of daily length or more
+        # nanosecond(s) are handled by apply_wraps
+        kwds_no_nanos = dict(
+            (k, v) for k, v in self.kwds.items()
+            if k not in ('nanosecond', 'nanoseconds')
+            )
+        use_relativedelta = False
+
+        if len(kwds_no_nanos) > 0:
+            if any(k in self._kwds_use_relativedelta for k in kwds_no_nanos):
+                use_relativedelta = True
+                offset = relativedelta(**kwds_no_nanos)
+            else:
+                # sub-daily offset - use timedelta (tz-aware)
+                offset = timedelta(**kwds_no_nanos)
         else:
-            self._offset = timedelta(1)
+            offset = timedelta(1)
+        return offset, use_relativedelta
 
     @apply_wraps
     def apply(self, other):
+        if self._use_relativedelta:
+            other = as_datetime(other)
+
         if len(self.kwds) > 0:
+            tzinfo = getattr(other, 'tzinfo', None)
+            if tzinfo is not None and self._use_relativedelta:
+                # perform calculation in UTC
+                other = other.replace(tzinfo=None)
+
             if self.n > 0:
                 for i in range(self.n):
                     other = other + self._offset
             else:
                 for i in range(-self.n):
                     other = other - self._offset
-            return other
+
+            if tzinfo is not None and self._use_relativedelta:
+                # bring tz back from UTC calculation
+                other = tslib._localize_pydatetime(other, tzinfo)
+
+            return as_timestamp(other)
         else:
             return other + timedelta(self.n)
 

pandas/tseries/tests/test_offsets.py

@@ -3104,6 +3104,134 @@ def test_str_for_named_is_name(self):
             self.assertEqual(str(offset), name)
 
 
+def get_utc_offset_hours(ts):
+    # take a Timestamp and compute total hours of utc offset
+    o = ts.utcoffset()
+    return (o.days * 24 * 3600 + o.seconds) / 3600.0
+
+
+class TestDST(tm.TestCase):
+    """
+    test DateOffset additions over Daylight Savings Time
+    """
+    # one microsecond before the DST transition
+    ts_pre_fallback = "2013-11-03 01:59:59.999999"
+    ts_pre_springfwd = "2013-03-10 01:59:59.999999"
+
+    # test both basic names and dateutil timezones
+    timezone_utc_offsets = {
+        'US/Eastern': dict(
+            utc_offset_daylight=-4,
+            utc_offset_standard=-5,
+            ),
+        'dateutil/US/Pacific': dict(
+            utc_offset_daylight=-7,
+            utc_offset_standard=-8,
+            )
+        }
+    valid_date_offsets_singular = [
+        'weekday', 'day', 'hour', 'minute', 'second', 'microsecond'
+        ]
+    valid_date_offsets_plural = [
+        'weeks', 'days',
+        'hours', 'minutes', 'seconds',
+        'milliseconds', 'microseconds'
+        ]
+
+    def _test_all_offsets(self, n, **kwds):
+        valid_offsets = self.valid_date_offsets_plural if n > 1 \
+            else self.valid_date_offsets_singular
+
+        for name in valid_offsets:
+            self._test_offset(offset_name=name, offset_n=n, **kwds)
+
+    def _test_offset(self, offset_name, offset_n, tstart, expected_utc_offset):
+        offset = DateOffset(**{offset_name: offset_n})
+        t = tstart + offset
+        if expected_utc_offset is not None:
+            self.assertTrue(get_utc_offset_hours(t) == expected_utc_offset)
+
+        if offset_name == 'weeks':
+            # dates should match
+            self.assertTrue(
+                t.date() ==
+                timedelta(days=7 * offset.kwds['weeks']) + tstart.date()
+                )
+            # expect the same day of week, hour of day, minute, second, ...
+            self.assertTrue(
+                t.dayofweek == tstart.dayofweek and
+                t.hour == tstart.hour and
+                t.minute == tstart.minute and
+                t.second == tstart.second
+                )
+        elif offset_name == 'days':
+            # dates should match
+            self.assertTrue(timedelta(offset.kwds['days']) + tstart.date() == t.date())
+            # expect the same hour of day, minute, second, ...
+            self.assertTrue(
+                t.hour == tstart.hour and
+                t.minute == tstart.minute and
+                t.second == tstart.second
+                )
+        elif offset_name in self.valid_date_offsets_singular:
+            # expect the signular offset value to match between tstart and t
+            datepart_offset = getattr(t, offset_name if offset_name != 'weekday' else 'dayofweek')
+            self.assertTrue(datepart_offset == offset.kwds[offset_name])
+        else:
+            # the offset should be the same as if it was done in UTC
+            self.assertTrue(
+                t == (tstart.tz_convert('UTC') + offset).tz_convert('US/Pacific')
+                )
+
+    def _make_timestamp(self, string, hrs_offset, tz):
+        offset_string = '{hrs:02d}00'.format(hrs=hrs_offset) if hrs_offset >= 0 else \
+            '-{hrs:02d}00'.format(hrs=-1 * hrs_offset)
+        return Timestamp(string + offset_string).tz_convert(tz)
+
+    def test_fallback_plural(self):
+        """test moving from daylight savings to standard time"""
+        for tz, utc_offsets in self.timezone_utc_offsets.items():
+            hrs_pre = utc_offsets['utc_offset_daylight']
+            hrs_post = utc_offsets['utc_offset_standard']
+            self._test_all_offsets(
+                n=3,
+                tstart=self._make_timestamp(self.ts_pre_fallback, hrs_pre, tz),
+                expected_utc_offset=hrs_post
+                )
+
+    def test_springforward_plural(self):
+        """test moving from standard to daylight savings"""
+        for tz, utc_offsets in self.timezone_utc_offsets.items():
+            hrs_pre = utc_offsets['utc_offset_standard']
+            hrs_post = utc_offsets['utc_offset_daylight']
+            self._test_all_offsets(
+                n=3,
+                tstart=self._make_timestamp(self.ts_pre_springfwd, hrs_pre, tz),
+                expected_utc_offset=hrs_post
+                )
+
+    def test_fallback_singular(self):
+        # in the case of signular offsets, we dont neccesarily know which utc offset
+        # the new Timestamp will wind up in (the tz for 1 month may be different from 1 second)
+        # so we don't specify an expected_utc_offset
+        for tz, utc_offsets in self.timezone_utc_offsets.items():
+            hrs_pre = utc_offsets['utc_offset_standard']
+            self._test_all_offsets(
+                n=1,
+                tstart=self._make_timestamp(self.ts_pre_fallback, hrs_pre, tz),
+                expected_utc_offset=None
+                )
+
+    def test_springforward_singular(self):
+        for tz, utc_offsets in self.timezone_utc_offsets.items():
+            hrs_pre = utc_offsets['utc_offset_standard']
+            self._test_all_offsets(
+                n=1,
+                tstart=self._make_timestamp(self.ts_pre_springfwd, hrs_pre, tz),
+                expected_utc_offset=None
+                )
+
+
 if __name__ == '__main__':
     nose.runmodule(argv=[__file__, '-vvs', '-x', '--pdb', '--pdb-failure'],
                    exit=False)