BUG: vectorized DateOffset match non-vectorized

Author: chris-b1

doc/source/timeseries.rst

@@ -954,6 +954,52 @@ These can be used as arguments to ``date_range``, ``bdate_range``, constructors
 for ``DatetimeIndex``, as well as various other timeseries-related functions
 in pandas.
 
+Anchored Offset Semantics
+~~~~~~~~~~~~~~~~~~~~~~~~~
+
+For those offsets that are anchored to the start or end of specific
+frequency (``MonthEnd``, ``MonthBegin``, ``WeekEnd``, etc) the following
+rules apply to rolling forward and backwards.
+
+When ``n`` is not 0, if the given date is not on an anchor point, it snapped to the next(previous)
+anchor point, and moved ``|n|-1`` additional steps forwards or backwards.
+
+.. ipython:: python
+
+   pd.Timestamp('2014-01-02') + MonthBegin(n=1)
+   pd.Timestamp('2014-01-02') + MonthEnd(n=1)
+
+   pd.Timestamp('2014-01-02') - MonthBegin(n=1)
+   pd.Timestamp('2014-01-02') - MonthEnd(n=1)
+
+   pd.Timestamp('2014-01-02') + MonthBegin(n=4)
+   pd.Timestamp('2014-01-02') - MonthBegin(n=4)
+
+If the given date *is* on an anchor point, it is moved ``|n|`` points forwards
+or backwards.
+
+.. ipython:: python
+
+   pd.Timestamp('2014-01-01') + MonthBegin(n=1)
+   pd.Timestamp('2014-01-31') + MonthEnd(n=1)
+
+   pd.Timestamp('2014-01-01') - MonthBegin(n=1)
+   pd.Timestamp('2014-01-31') - MonthEnd(n=1)
+
+   pd.Timestamp('2014-01-01') + MonthBegin(n=4)
+   pd.Timestamp('2014-01-31') - MonthBegin(n=4)
+
+For the case when ``n=0``, the date is not moved if on an anchor point, otherwise
+it is rolled forward to the next anchor point.
+
+.. ipython:: python
+
+   pd.Timestamp('2014-01-02') + MonthBegin(n=0)
+   pd.Timestamp('2014-01-02') + MonthEnd(n=0)
+
+   pd.Timestamp('2014-01-01') + MonthBegin(n=0)
+   pd.Timestamp('2014-01-31') + MonthEnd(n=0)
+
 .. _timeseries.legacyaliases:
 
 Legacy Aliases

doc/source/whatsnew/v0.18.0.txt

@@ -190,7 +190,7 @@ Bug Fixes
 
 
 
-
+ - Bug in vectorized ``DateOffset`` when ``n`` parameter is ``0`` (:issue:`11370`)
 
 
 

pandas/tseries/offsets.py

@@ -444,7 +444,7 @@ def _beg_apply_index(self, i, freq):
         from pandas.tseries.frequencies import get_freq_code
         base, mult = get_freq_code(freq)
         base_period = i.to_period(base)
-        if self.n < 0:
+        if self.n <= 0:
             # when subtracting, dates on start roll to prior
             roll = np.where(base_period.to_timestamp() == i - off,
                             self.n, self.n + 1)
@@ -464,7 +464,7 @@ def _end_apply_index(self, i, freq):
         base, mult = get_freq_code(freq)
         base_period = i.to_period(base)
         if self.n > 0:
-            # when adding, dtates on end roll to next
+            # when adding, dates on end roll to next
             roll = np.where(base_period.to_timestamp(how='end') == i - off,
                             self.n, self.n - 1)
         else:
@@ -1081,8 +1081,7 @@ def apply(self, other):
 
     @apply_index_wraps
     def apply_index(self, i):
-        months = self.n - 1 if self.n >= 0 else self.n
-        shifted = tslib.shift_months(i.asi8, months, 'end')
+        shifted = tslib.shift_months(i.asi8, self.n, 'end')
         return i._shallow_copy(shifted)
 
     def onOffset(self, dt):
@@ -1108,8 +1107,7 @@ def apply(self, other):
 
     @apply_index_wraps
     def apply_index(self, i):
-        months = self.n + 1 if self.n < 0 else self.n
-        shifted = tslib.shift_months(i.asi8, months, 'start')
+        shifted = tslib.shift_months(i.asi8, self.n, 'start')
         return i._shallow_copy(shifted)
 
     def onOffset(self, dt):
@@ -1777,6 +1775,7 @@ def apply(self, other):
     @apply_index_wraps
     def apply_index(self, i):
         freq_month = 12 if self.startingMonth == 1 else self.startingMonth - 1
+        # freq_month = self.startingMonth
         freqstr =  'Q-%s' % (_int_to_month[freq_month],)
         return self._beg_apply_index(i, freqstr)
 

pandas/tseries/tests/test_timeseries.py

@@ -2622,7 +2622,8 @@ def test_datetime64_with_DateOffset(self):
                     assert_func(result, exp)
 
             s = klass([Timestamp('2000-01-05 00:15:00'), Timestamp('2000-01-31 00:23:00'),
-                       Timestamp('2000-01-01'), Timestamp('2000-02-29'), Timestamp('2000-12-31')])
+                       Timestamp('2000-01-01'), Timestamp('2000-03-31'),
+                       Timestamp('2000-02-29'), Timestamp('2000-12-31')])
 
             #DateOffset relativedelta fastpath
             relative_kwargs = [('years', 2), ('months', 5), ('days', 3),
@@ -2659,11 +2660,15 @@ def test_datetime64_with_DateOffset(self):
                         else:
                             do = do
                             kwargs = {}
-                        op = getattr(pd.offsets,do)(5, normalize=normalize, **kwargs)
-                        assert_func(klass([x + op for x in s]), s + op)
-                        assert_func(klass([x - op for x in s]), s - op)
-                        assert_func(klass([op + x for x in s]), op + s)
 
+                        for n in [0, 5]:
+                            if (do in ['WeekOfMonth','LastWeekOfMonth',
+                                       'FY5253Quarter','FY5253'] and n == 0):
+                                continue
+                            op = getattr(pd.offsets,do)(n, normalize=normalize, **kwargs)
+                            assert_func(klass([x + op for x in s]), s + op)
+                            assert_func(klass([x - op for x in s]), s - op)
+                            assert_func(klass([op + x for x in s]), op + s)
     # def test_add_timedelta64(self):
     #     rng = date_range('1/1/2000', periods=5)
     #     delta = rng.values[3] - rng.values[1]

pandas/tslib.pyx

@@ -4458,7 +4458,8 @@ def shift_months(int64_t[:] dtindex, int months, object day=None):
         Py_ssize_t i
         pandas_datetimestruct dts
         int count = len(dtindex)
-        int days_in_current_month
+        int months_to_roll
+        bint roll_check
         int64_t[:] out = np.empty(count, dtype='int64')
 
     if day is None:
@@ -4472,36 +4473,44 @@ def shift_months(int64_t[:] dtindex, int months, object day=None):
                 dts.day = min(dts.day, days_in_month(dts))
                 out[i] = pandas_datetimestruct_to_datetime(PANDAS_FR_ns, &dts)
     elif day == 'start':
+        roll_check = False
+        if months <= 0:
+            months += 1
+            roll_check = True
         with nogil:
             for i in range(count):
                 if dtindex[i] == NPY_NAT: out[i] = NPY_NAT; continue
                 pandas_datetime_to_datetimestruct(dtindex[i], PANDAS_FR_ns, &dts)
-                dts.year = _year_add_months(dts, months)
-                dts.month = _month_add_months(dts, months)
+                months_to_roll = months
+
+                # offset semantics - if on the anchor point and going backwards
+                # shift to next
+                if roll_check and dts.day == 1:
+                    months_to_roll -= 1
+
+                dts.year = _year_add_months(dts, months_to_roll)
+                dts.month = _month_add_months(dts, months_to_roll)
+                dts.day = 1
 
-                # offset semantics - when subtracting if at the start anchor
-                # point, shift back by one more month
-                if months <= 0 and dts.day == 1:
-                    dts.year = _year_add_months(dts, -1)
-                    dts.month = _month_add_months(dts, -1)
-                else:
-                    dts.day = 1
                 out[i] = pandas_datetimestruct_to_datetime(PANDAS_FR_ns, &dts)
     elif day == 'end':
+        roll_check = False
+        if months > 0:
+            months -= 1
+            roll_check = True
         with nogil:
             for i in range(count):
                 if dtindex[i] == NPY_NAT: out[i] = NPY_NAT; continue
                 pandas_datetime_to_datetimestruct(dtindex[i], PANDAS_FR_ns, &dts)
-                days_in_current_month = days_in_month(dts)
-
-                dts.year = _year_add_months(dts, months)
-                dts.month = _month_add_months(dts, months)
+                months_to_roll = months
 
                 # similar semantics - when adding shift forward by one
                 # month if already at an end of month
-                if months >= 0 and dts.day == days_in_current_month:
-                    dts.year = _year_add_months(dts, 1)
-                    dts.month = _month_add_months(dts, 1)
+                if roll_check and dts.day == days_in_month(dts):
+                    months_to_roll += 1
+
+                dts.year = _year_add_months(dts, months_to_roll)
+                dts.month = _month_add_months(dts, months_to_roll)
 
                 dts.day = days_in_month(dts)
                 out[i] = pandas_datetimestruct_to_datetime(PANDAS_FR_ns, &dts)