Merge pull request #9605 from josham/days_in_month

ENH: Add days_in_month property to Timestamp/DatetimeIndex/... (GH9572)

Author: jreback

doc/source/whatsnew/v0.16.0.txt

@@ -61,6 +61,7 @@ New features
 - Added ``StringMethods.ljust()`` and ``rjust()`` which behave as the same as standard ``str`` (:issue:`9352`)
 - ``StringMethods.pad()`` and ``center()`` now accept ``fillchar`` option to specify filling character (:issue:`9352`)
 - Added ``StringMethods.zfill()`` which behave as the same as standard ``str`` (:issue:`9387`)
+- Added ``days_in_month`` (compatibility alias ``daysinmonth``) property to ``Timestamp``, ``DatetimeIndex``, ``Period``, ``PeriodIndex``, and ``Series.dt`` (:issue:`9572`)
 
 DataFrame Assign
 ~~~~~~~~~~~~~~~~

pandas/src/period.pyx

@@ -95,6 +95,7 @@ cdef extern from "period_helper.h":
     int phour(int64_t ordinal, int freq) except INT32_MIN
     int pminute(int64_t ordinal, int freq) except INT32_MIN
     int psecond(int64_t ordinal, int freq) except INT32_MIN
+    int pdays_in_month(int64_t ordinal, int freq) except INT32_MIN
     char *c_strftime(date_info *dinfo, char *fmt)
     int get_yq(int64_t ordinal, int freq, int *quarter, int *year)
 
@@ -427,6 +428,8 @@ cdef accessor _get_accessor_func(int code):
         return &pday_of_year
     elif code == 10:
         return &pweekday
+    elif code == 11:
+        return &pdays_in_month
     return NULL
 
 
@@ -925,6 +928,12 @@ cdef class Period(object):
     property qyear:
         def __get__(self):
             return self._field(1)
+    property days_in_month:
+        def __get__(self):
+            return self._field(11)
+    property daysinmonth:
+        def __get__(self):
+            return self.days_in_month
 
     @classmethod
     def now(cls, freq=None):

pandas/src/period_helper.c

@@ -1439,3 +1439,13 @@ int psecond(npy_int64 ordinal, int freq) {
         return INT_ERR_CODE;
     return (int)dinfo.second;
 }
+
+int pdays_in_month(npy_int64 ordinal, int freq) {
+    int days;
+    struct date_info dinfo;
+    if(get_date_info(ordinal, freq, &dinfo) == INT_ERR_CODE)
+        return INT_ERR_CODE;
+    
+    days = days_in_month[dInfoCalc_Leapyear(dinfo.year, dinfo.calendar)][dinfo.month-1];
+    return days;
+}

pandas/src/period_helper.h

@@ -160,6 +160,7 @@ int pweek(npy_int64 ordinal, int freq);
 int phour(npy_int64 ordinal, int freq);
 int pminute(npy_int64 ordinal, int freq);
 int psecond(npy_int64 ordinal, int freq);
+int pdays_in_month(npy_int64 ordinal, int freq);
 
 double getAbsTime(int freq, npy_int64 dailyDate, npy_int64 originalDate);
 char *c_strftime(struct date_info *dinfo, char *fmt);

pandas/tests/test_series.py

@@ -79,7 +79,7 @@ def test_dt_namespace_accessor(self):
         # GH 7207
         # test .dt namespace accessor
 
-        ok_for_base = ['year','month','day','hour','minute','second','weekofyear','week','dayofweek','weekday','dayofyear','quarter','freq']
+        ok_for_base = ['year','month','day','hour','minute','second','weekofyear','week','dayofweek','weekday','dayofyear','quarter','freq','days_in_month','daysinmonth']
         ok_for_period = ok_for_base + ['qyear']
         ok_for_dt = ok_for_base + ['date','time','microsecond','nanosecond', 'is_month_start', 'is_month_end', 'is_quarter_start',
                                    'is_quarter_end', 'is_year_start', 'is_year_end', 'tz']

pandas/tseries/index.py

@@ -187,7 +187,7 @@ def _join_i8_wrapper(joinf, **kwargs):
     _comparables = ['name','freqstr','tz']
     _attributes = ['name','freq','tz']
     _datetimelike_ops = ['year','month','day','hour','minute','second',
-                         'weekofyear','week','dayofweek','weekday','dayofyear','quarter',
+                         'weekofyear','week','dayofweek','weekday','dayofyear','quarter', 'days_in_month', 'daysinmonth',
                          'date','time','microsecond','nanosecond','is_month_start','is_month_end',
                          'is_quarter_start','is_quarter_end','is_year_start','is_year_end','tz','freq']
     _is_numeric_dtype = False
@@ -1401,6 +1401,8 @@ def _set_freq(self, value):
     weekday = dayofweek
     dayofyear = _field_accessor('dayofyear', 'doy', "The ordinal day of the year")
     quarter = _field_accessor('quarter', 'q', "The quarter of the date")
+    days_in_month = _field_accessor('days_in_month', 'dim', "The number of days in the month")
+    daysinmonth = days_in_month
     is_month_start = _field_accessor('is_month_start', 'is_month_start', "Logical indicating if first day of month (defined by frequency)")
     is_month_end = _field_accessor('is_month_end', 'is_month_end', "Logical indicating if last day of month (defined by frequency)")
     is_quarter_start = _field_accessor('is_quarter_start', 'is_quarter_start', "Logical indicating if first day of quarter (defined by frequency)")

pandas/tseries/period.py

@@ -150,7 +150,7 @@ class PeriodIndex(DatetimeIndexOpsMixin, Int64Index):
     _typ = 'periodindex'
     _attributes = ['name','freq']
     _datetimelike_ops = ['year','month','day','hour','minute','second',
-                         'weekofyear','week','dayofweek','weekday','dayofyear','quarter', 'qyear', 'freq']
+                         'weekofyear','week','dayofweek','weekday','dayofyear','quarter', 'qyear', 'freq', 'days_in_month', 'daysinmonth']
     _is_numeric_dtype = False
     freq = None
 
@@ -385,7 +385,9 @@ def to_datetime(self, dayfirst=False):
     dayofyear = day_of_year = _field_accessor('dayofyear', 9, "The ordinal day of the year")
     quarter = _field_accessor('quarter', 2, "The quarter of the date")
     qyear = _field_accessor('qyear', 1)
-
+    days_in_month = _field_accessor('days_in_month', 11, "The number of days in the month")
+    daysinmonth = days_in_month
+    
     def _get_object_array(self):
         freq = self.freq
         return np.array([ Period._from_ordinal(ordinal=x, freq=freq) for x in self.values], copy=False)

pandas/tseries/tests/test_period.py

@@ -432,7 +432,9 @@ def test_properties_weekly(self):
         assert_equal(w_date.month, 1)
         assert_equal(w_date.week, 1)
         assert_equal((w_date - 1).week, 52)
-
+        assert_equal(w_date.days_in_month, 31)
+        assert_equal(Period(freq='WK', year=2012, month=2, day=1).days_in_month, 29)
+        
     def test_properties_daily(self):
         # Test properties on Periods with daily frequency.
         b_date = Period(freq='B', year=2007, month=1, day=1)
@@ -443,6 +445,8 @@ def test_properties_daily(self):
         assert_equal(b_date.day, 1)
         assert_equal(b_date.weekday, 0)
         assert_equal(b_date.dayofyear, 1)
+        assert_equal(b_date.days_in_month, 31)
+        assert_equal(Period(freq='B', year=2012, month=2, day=1).days_in_month, 29)
         #
         d_date = Period(freq='D', year=2007, month=1, day=1)
         #
@@ -452,6 +456,9 @@ def test_properties_daily(self):
         assert_equal(d_date.day, 1)
         assert_equal(d_date.weekday, 0)
         assert_equal(d_date.dayofyear, 1)
+        assert_equal(d_date.days_in_month, 31)
+        assert_equal(Period(freq='D', year=2012, month=2,
+                            day=1).days_in_month, 29)
 
     def test_properties_hourly(self):
         # Test properties on Periods with hourly frequency.
@@ -464,6 +471,9 @@ def test_properties_hourly(self):
         assert_equal(h_date.weekday, 0)
         assert_equal(h_date.dayofyear, 1)
         assert_equal(h_date.hour, 0)
+        assert_equal(h_date.days_in_month, 31)
+        assert_equal(Period(freq='H', year=2012, month=2, day=1,
+                            hour=0).days_in_month, 29)
         #
 
     def test_properties_minutely(self):
@@ -478,6 +488,9 @@ def test_properties_minutely(self):
         assert_equal(t_date.dayofyear, 1)
         assert_equal(t_date.hour, 0)
         assert_equal(t_date.minute, 0)
+        assert_equal(t_date.days_in_month, 31)
+        assert_equal(Period(freq='D', year=2012, month=2, day=1, hour=0,
+                            minute=0).days_in_month, 29)
 
     def test_properties_secondly(self):
         # Test properties on Periods with secondly frequency.
@@ -493,13 +506,16 @@ def test_properties_secondly(self):
         assert_equal(s_date.hour, 0)
         assert_equal(s_date.minute, 0)
         assert_equal(s_date.second, 0)
+        assert_equal(s_date.days_in_month, 31)
+        assert_equal(Period(freq='Min', year=2012, month=2, day=1, hour=0,
+                            minute=0, second=0).days_in_month, 29)
 
     def test_properties_nat(self):
         p_nat = Period('NaT', freq='M')
         t_nat = pd.Timestamp('NaT')
         # confirm Period('NaT') work identical with Timestamp('NaT')
         for f in ['year', 'month', 'day', 'hour', 'minute', 'second',
-                  'week', 'dayofyear', 'quarter']:
+                  'week', 'dayofyear', 'quarter', 'days_in_month']:
             self.assertTrue(np.isnan(getattr(p_nat, f)))
             self.assertTrue(np.isnan(getattr(t_nat, f)))
 
@@ -2327,7 +2343,7 @@ def test_fields(self):
     def _check_all_fields(self, periodindex):
         fields = ['year', 'month', 'day', 'hour', 'minute',
                   'second', 'weekofyear', 'week', 'dayofweek',
-                  'weekday', 'dayofyear', 'quarter', 'qyear']
+                  'weekday', 'dayofyear', 'quarter', 'qyear', 'days_in_month']
 
         periods = list(periodindex)
 

pandas/tseries/tests/test_timeseries.py

@@ -937,7 +937,7 @@ def test_nat_vector_field_access(self):
 
         fields = ['year', 'quarter', 'month', 'day', 'hour',
                   'minute', 'second', 'microsecond', 'nanosecond',
-                  'week', 'dayofyear']
+                  'week', 'dayofyear', 'days_in_month']
         for field in fields:
             result = getattr(idx, field)
             expected = [getattr(x, field) if x is not NaT else np.nan
@@ -947,7 +947,7 @@ def test_nat_vector_field_access(self):
     def test_nat_scalar_field_access(self):
         fields = ['year', 'quarter', 'month', 'day', 'hour',
                   'minute', 'second', 'microsecond', 'nanosecond',
-                  'week', 'dayofyear']
+                  'week', 'dayofyear', 'days_in_month']
         for field in fields:
             result = getattr(NaT, field)
             self.assertTrue(np.isnan(result))
@@ -1625,7 +1625,7 @@ def test_timestamp_fields(self):
         # extra fields from DatetimeIndex like quarter and week
         idx = tm.makeDateIndex(100)
 
-        fields = ['dayofweek', 'dayofyear', 'week', 'weekofyear', 'quarter', 'is_month_start', 'is_month_end', 'is_quarter_start', 'is_quarter_end', 'is_year_start', 'is_year_end']
+        fields = ['dayofweek', 'dayofyear', 'week', 'weekofyear', 'quarter', 'days_in_month', 'is_month_start', 'is_month_end', 'is_quarter_start', 'is_quarter_end', 'is_year_start', 'is_year_end']
         for f in fields:
             expected = getattr(idx, f)[-1]
             result = getattr(Timestamp(idx[-1]), f)
@@ -2865,6 +2865,9 @@ def test_datetimeindex_accessors(self):
         self.assertEqual(dti.quarter[0], 1)
         self.assertEqual(dti.quarter[120], 2)
 
+        self.assertEqual(dti.days_in_month[0], 31)
+        self.assertEqual(dti.days_in_month[90], 30)
+
         self.assertEqual(dti.is_month_start[0], True)
         self.assertEqual(dti.is_month_start[1], False)
         self.assertEqual(dti.is_month_start[31], True)
@@ -2948,7 +2951,9 @@ def test_datetimeindex_accessors(self):
             (Timestamp('2013-06-28', offset='BQS-APR').is_quarter_end, 1),
             (Timestamp('2013-03-29', offset='BQS-APR').is_year_end, 1),
             (Timestamp('2013-11-01', offset='AS-NOV').is_year_start, 1),
-            (Timestamp('2013-10-31', offset='AS-NOV').is_year_end, 1)]
+            (Timestamp('2013-10-31', offset='AS-NOV').is_year_end, 1),
+            (Timestamp('2012-02-01').days_in_month, 29),
+            (Timestamp('2013-02-01').days_in_month, 28)]
 
         for ts, value in tests:
             self.assertEqual(ts, value)

pandas/tslib.pyx

@@ -390,6 +390,12 @@ class Timestamp(_Timestamp):
     def quarter(self):
         return self._get_field('q')
 
+    @property
+    def days_in_month(self):
+        return self._get_field('dim')
+
+    daysinmonth = days_in_month
+
     @property
     def freqstr(self):
         return getattr(self.offset, 'freqstr', self.offset)
@@ -603,7 +609,7 @@ class NaTType(_NaT):
 
 fields = ['year', 'quarter', 'month', 'day', 'hour',
           'minute', 'second', 'millisecond', 'microsecond', 'nanosecond',
-          'week', 'dayofyear']
+          'week', 'dayofyear', 'days_in_month']
 for field in fields:
     prop = property(fget=lambda self: np.nan)
     setattr(NaTType, field, prop)
@@ -3188,6 +3194,14 @@ def get_date_field(ndarray[int64_t] dtindex, object field):
             out[i] = ((out[i] - 1) / 3) + 1
         return out
 
+    elif field == 'dim':
+        for i in range(count):
+            if dtindex[i] == NPY_NAT: out[i] = -1; continue
+
+            pandas_datetime_to_datetimestruct(dtindex[i], PANDAS_FR_ns, &dts)
+            out[i] = monthrange(dts.year, dts.month)[1]
+        return out
+
     raise ValueError("Field %s not supported" % field)