Implement business_start/end cases for shift_months (#18489)

Author: jbrockmendel

asv_bench/benchmarks/offset.py

@@ -38,6 +38,25 @@ def time_apply_series(self, param):
         self.ser + self.offset
 
 
+class OnOffset(object):
+    goal_time = 0.2
+
+    params = [pd.offsets.QuarterBegin(), pd.offsets.QuarterEnd(),
+              pd.offsets.BQuarterBegin(), pd.offsets.BQuarterEnd()]
+    param_names = ['offset']
+
+    def setup(self, offset):
+        self.offset = offset
+        self.dates = [datetime(2016, m, d)
+                      for m in [10, 11, 12]
+                      for d in [1, 2, 3, 28, 29, 30, 31]
+                      if not (m == 11 and d == 31)]
+
+    def time_on_offset(self, offset):
+        for date in self.dates:
+            self.offset.onOffset(date)
+
+
 class DatetimeIndexArithmetic(object):
     goal_time = 0.2
 

doc/source/whatsnew/v0.22.0.txt

@@ -116,6 +116,7 @@ Performance Improvements
 - ``Series`` construction will reduce the number of copies made of the input data in certain cases (:issue:`17449`)
 - Improved performance of :func:`Series.dt.date` and :func:`DatetimeIndex.date` (:issue:`18058`)
 - Improved performance of ``IntervalIndex.symmetric_difference()`` (:issue:`18475`)
+- Improved performance of ``DatetimeIndex`` and ``Series`` arithmetic operations with Business-Month and Business-Quarter frequencies (:issue:`18489`)
 
 .. _whatsnew_0220.docs:
 

pandas/_libs/tslibs/offsets.pyx

@@ -554,8 +554,58 @@ def shift_months(int64_t[:] dtindex, int months, object day=None):
 
                 dts.day = get_days_in_month(dts.year, dts.month)
                 out[i] = dtstruct_to_dt64(&dts)
+
+    elif day == 'business_start':
+        for i in range(count):
+            if dtindex[i] == NPY_NAT:
+                out[i] = NPY_NAT
+                continue
+
+            dt64_to_dtstruct(dtindex[i], &dts)
+            months_to_roll = months
+            wkday, days_in_month = monthrange(dts.year, dts.month)
+            compare_day = get_firstbday(wkday, days_in_month)
+
+            if months_to_roll > 0 and dts.day < compare_day:
+                months_to_roll -= 1
+            elif months_to_roll <= 0 and dts.day > compare_day:
+                # as if rolled forward already
+                months_to_roll += 1
+
+            dts.year = year_add_months(dts, months_to_roll)
+            dts.month = month_add_months(dts, months_to_roll)
+
+            wkday, days_in_month = monthrange(dts.year, dts.month)
+            dts.day = get_firstbday(wkday, days_in_month)
+            out[i] = dtstruct_to_dt64(&dts)
+
+    elif day == 'business_end':
+        for i in range(count):
+            if dtindex[i] == NPY_NAT:
+                out[i] = NPY_NAT
+                continue
+
+            dt64_to_dtstruct(dtindex[i], &dts)
+            months_to_roll = months
+            wkday, days_in_month = monthrange(dts.year, dts.month)
+            compare_day = get_lastbday(wkday, days_in_month)
+
+            if months_to_roll > 0 and dts.day < compare_day:
+                months_to_roll -= 1
+            elif months_to_roll <= 0 and dts.day > compare_day:
+                # as if rolled forward already
+                months_to_roll += 1
+
+            dts.year = year_add_months(dts, months_to_roll)
+            dts.month = month_add_months(dts, months_to_roll)
+
+            wkday, days_in_month = monthrange(dts.year, dts.month)
+            dts.day = get_lastbday(wkday, days_in_month)
+            out[i] = dtstruct_to_dt64(&dts)
+
     else:
-        raise ValueError("day must be None, 'start' or 'end'")
+        raise ValueError("day must be None, 'start', 'end', "
+                         "'business_start', or 'business_end'")
 
     return np.asarray(out)
 

pandas/tests/tseries/offsets/test_yqm_offsets.py

@@ -6,6 +6,7 @@
 
 import pytest
 
+import pandas as pd
 from pandas import Timestamp
 from pandas import compat
 
@@ -32,6 +33,35 @@ def test_quarterly_dont_normalize():
         assert (result.time() == date.time())
 
 
+@pytest.mark.parametrize('offset', [MonthBegin(), MonthEnd(),
+                                    BMonthBegin(), BMonthEnd()])
+def test_apply_index(offset):
+    rng = pd.date_range(start='1/1/2000', periods=100000, freq='T')
+    ser = pd.Series(rng)
+
+    res = rng + offset
+    res_v2 = offset.apply_index(rng)
+    assert (res == res_v2).all()
+    assert res[0] == rng[0] + offset
+    assert res[-1] == rng[-1] + offset
+    res2 = ser + offset
+    # apply_index is only for indexes, not series, so no res2_v2
+    assert res2.iloc[0] == ser.iloc[0] + offset
+    assert res2.iloc[-1] == ser.iloc[-1] + offset
+
+
+@pytest.mark.parametrize('offset', [QuarterBegin(), QuarterEnd(),
+                                    BQuarterBegin(), BQuarterEnd()])
+def test_on_offset(offset):
+    dates = [datetime(2016, m, d)
+             for m in [10, 11, 12]
+             for d in [1, 2, 3, 28, 29, 30, 31] if not (m == 11 and d == 31)]
+    for date in dates:
+        res = offset.onOffset(date)
+        slow_version = date == (date + offset) - offset
+        assert res == slow_version
+
+
 # --------------------------------------------------------------------
 # Months
 

pandas/tseries/offsets.py

@@ -929,8 +929,9 @@ def name(self):
         if self.isAnchored:
             return self.rule_code
         else:
+            month = liboffsets._int_to_month[self.n]
             return "{code}-{month}".format(code=self.rule_code,
-                                           month=_int_to_month[self.n])
+                                           month=month)
 
     def onOffset(self, dt):
         if self.normalize and not _is_normalized(dt):
@@ -950,28 +951,23 @@ def apply(self, other):
 
         return shift_month(other, n, self._day_opt)
 
+    @apply_index_wraps
+    def apply_index(self, i):
+        shifted = liboffsets.shift_months(i.asi8, self.n, self._day_opt)
+        return i._shallow_copy(shifted)
+
 
 class MonthEnd(MonthOffset):
     """DateOffset of one month end"""
     _prefix = 'M'
     _day_opt = 'end'
 
-    @apply_index_wraps
-    def apply_index(self, i):
-        shifted = liboffsets.shift_months(i.asi8, self.n, self._day_opt)
-        return i._shallow_copy(shifted)
-
 
 class MonthBegin(MonthOffset):
     """DateOffset of one month at beginning"""
     _prefix = 'MS'
     _day_opt = 'start'
 
-    @apply_index_wraps
-    def apply_index(self, i):
-        shifted = liboffsets.shift_months(i.asi8, self.n, self._day_opt)
-        return i._shallow_copy(shifted)
-
 
 class BusinessMonthEnd(MonthOffset):
     """DateOffset increments between business EOM dates"""
@@ -1008,6 +1004,7 @@ class CustomBusinessMonthEnd(BusinessMixin, MonthOffset):
     _prefix = 'CBM'
 
     onOffset = DateOffset.onOffset  # override MonthOffset method
+    apply_index = DateOffset.apply_index  # override MonthOffset method
 
     def __init__(self, n=1, normalize=False, weekmask='Mon Tue Wed Thu Fri',
                  holidays=None, calendar=None, offset=timedelta(0)):
@@ -1083,6 +1080,7 @@ class CustomBusinessMonthBegin(BusinessMixin, MonthOffset):
     _prefix = 'CBMS'
 
     onOffset = DateOffset.onOffset  # override MonthOffset method
+    apply_index = DateOffset.apply_index  # override MonthOffset method
 
     def __init__(self, n=1, normalize=False, weekmask='Mon Tue Wed Thu Fri',
                  holidays=None, calendar=None, offset=timedelta(0)):
@@ -1603,15 +1601,15 @@ def isAnchored(self):
     def _from_name(cls, suffix=None):
         kwargs = {}
         if suffix:
-            kwargs['startingMonth'] = _month_to_int[suffix]
+            kwargs['startingMonth'] = liboffsets._month_to_int[suffix]
         else:
             if cls._from_name_startingMonth is not None:
                 kwargs['startingMonth'] = cls._from_name_startingMonth
         return cls(**kwargs)
 
     @property
     def rule_code(self):
-        month = _int_to_month[self.startingMonth]
+        month = liboffsets._int_to_month[self.startingMonth]
         return '{prefix}-{month}'.format(prefix=self._prefix, month=month)
 
     @apply_wraps
@@ -1631,6 +1629,12 @@ def apply(self, other):
 
         return shift_month(other, 3 * n - months_since, self._day_opt)
 
+    def onOffset(self, dt):
+        if self.normalize and not _is_normalized(dt):
+            return False
+        modMonth = (dt.month - self.startingMonth) % 3
+        return modMonth == 0 and dt.day == self._get_offset_day(dt)
+
 
 class BQuarterEnd(QuarterOffset):
     """DateOffset increments between business Quarter dates
@@ -1644,16 +1648,6 @@ class BQuarterEnd(QuarterOffset):
     _prefix = 'BQ'
     _day_opt = 'business_end'
 
-    def onOffset(self, dt):
-        if self.normalize and not _is_normalized(dt):
-            return False
-        modMonth = (dt.month - self.startingMonth) % 3
-        return modMonth == 0 and dt.day == self._get_offset_day(dt)
-
-
-_int_to_month = tslib._MONTH_ALIASES
-_month_to_int = {v: k for k, v in _int_to_month.items()}
-
 
 # TODO: This is basically the same as BQuarterEnd
 class BQuarterBegin(QuarterOffset):
@@ -1680,12 +1674,6 @@ class QuarterEnd(EndMixin, QuarterOffset):
     def apply_index(self, i):
         return self._end_apply_index(i, self.freqstr)
 
-    def onOffset(self, dt):
-        if self.normalize and not _is_normalized(dt):
-            return False
-        modMonth = (dt.month - self.startingMonth) % 3
-        return modMonth == 0 and dt.day == self._get_offset_day(dt)
-
 
 class QuarterBegin(BeginMixin, QuarterOffset):
     _outputName = 'QuarterBegin'
@@ -1697,7 +1685,8 @@ class QuarterBegin(BeginMixin, QuarterOffset):
     @apply_index_wraps
     def apply_index(self, i):
         freq_month = 12 if self.startingMonth == 1 else self.startingMonth - 1
-        freqstr = 'Q-{month}'.format(month=_int_to_month[freq_month])
+        month = liboffsets._int_to_month[freq_month]
+        freqstr = 'Q-{month}'.format(month=month)
         return self._beg_apply_index(i, freqstr)
 
 
@@ -1738,12 +1727,12 @@ def __init__(self, n=1, normalize=False, month=None):
     def _from_name(cls, suffix=None):
         kwargs = {}
         if suffix:
-            kwargs['month'] = _month_to_int[suffix]
+            kwargs['month'] = liboffsets._month_to_int[suffix]
         return cls(**kwargs)
 
     @property
     def rule_code(self):
-        month = _int_to_month[self.month]
+        month = liboffsets._int_to_month[self.month]
         return '{prefix}-{month}'.format(prefix=self._prefix, month=month)
 
 
@@ -1784,7 +1773,8 @@ class YearBegin(BeginMixin, YearOffset):
     @apply_index_wraps
     def apply_index(self, i):
         freq_month = 12 if self.month == 1 else self.month - 1
-        freqstr = 'A-{month}'.format(month=_int_to_month[freq_month])
+        month = liboffsets._int_to_month[freq_month]
+        freqstr = 'A-{month}'.format(month=month)
         return self._beg_apply_index(i, freqstr)
 
 
@@ -1969,7 +1959,7 @@ def _get_suffix_prefix(self):
 
     def get_rule_code_suffix(self):
         prefix = self._get_suffix_prefix()
-        month = _int_to_month[self.startingMonth]
+        month = liboffsets._int_to_month[self.startingMonth]
         weekday = _int_to_weekday[self.weekday]
         return '{prefix}-{month}-{weekday}'.format(prefix=prefix, month=month,
                                                    weekday=weekday)
@@ -1984,7 +1974,7 @@ def _parse_suffix(cls, varion_code, startingMonth_code, weekday_code):
             raise ValueError("Unable to parse varion_code: "
                              "{code}".format(code=varion_code))
 
-        startingMonth = _month_to_int[startingMonth_code]
+        startingMonth = liboffsets._month_to_int[startingMonth_code]
         weekday = _weekday_to_int[weekday_code]
 
         return {"weekday": weekday,