ENH: add dayfirst/yearfirst to Timestamp for compat

TST: fix up python-dateutil compat for 2.5.3, xref pandas-dev#12944

Author: jreback

doc/source/whatsnew/v0.18.1.txt

@@ -170,7 +170,6 @@ Other Enhancements
 
 - ``pd.crosstab()`` has gained a ``normalize`` argument for normalizing frequency tables (:issue:`12569`). Examples in the updated docs :ref:`here <reshaping.crosstabulations>`.
 
-
 .. _whatsnew_0181.sparse:
 
 Sparse changes

pandas/src/inference.pyx

@@ -683,7 +683,7 @@ def maybe_convert_objects(ndarray[object] objects, bint try_float=0,
             seen_float = 1
         elif util.is_datetime64_object(val):
             if convert_datetime:
-                idatetimes[i] = convert_to_tsobject(val, None, None).value
+                idatetimes[i] = convert_to_tsobject(val, None, None, 0, 0).value
                 seen_datetime = 1
             else:
                 seen_object = 1
@@ -712,7 +712,7 @@ def maybe_convert_objects(ndarray[object] objects, bint try_float=0,
         elif PyDateTime_Check(val) or util.is_datetime64_object(val):
             if convert_datetime:
                 seen_datetime = 1
-                idatetimes[i] = convert_to_tsobject(val, None, None).value
+                idatetimes[i] = convert_to_tsobject(val, None, None, 0, 0).value
             else:
                 seen_object = 1
                 break

pandas/tseries/tests/test_tslib.py

@@ -592,78 +592,101 @@ def test_parsers_quarter_invalid(self):
             self.assertRaises(ValueError, tools.parse_time_string, case)
 
     def test_parsers_dayfirst_yearfirst(self):
+        tm._skip_if_no_dateutil()
+
+        # OK
+        # 2.5.1 10-11-12   [dayfirst=0, yearfirst=0] -> 2012-10-11 00:00:00
+        # 2.5.2 10-11-12   [dayfirst=0, yearfirst=1] -> 2012-10-11 00:00:00
+        # 2.5.3 10-11-12   [dayfirst=0, yearfirst=0] -> 2012-10-11 00:00:00
+
+        # OK
+        # 2.5.1 10-11-12   [dayfirst=0, yearfirst=1] -> 2010-11-12 00:00:00
+        # 2.5.2 10-11-12   [dayfirst=0, yearfirst=1] -> 2010-11-12 00:00:00
+        # 2.5.3 10-11-12   [dayfirst=0, yearfirst=1] -> 2010-11-12 00:00:00
+
+        # bug fix in 2.5.2
+        # 2.5.1 10-11-12   [dayfirst=1, yearfirst=1] -> 2010-11-12 00:00:00
+        # 2.5.2 10-11-12   [dayfirst=1, yearfirst=1] -> 2010-12-11 00:00:00
+        # 2.5.3 10-11-12   [dayfirst=1, yearfirst=1] -> 2010-12-11 00:00:00
+
+        # OK
+        # 2.5.1 10-11-12   [dayfirst=1, yearfirst=0] -> 2012-11-10 00:00:00
+        # 2.5.2 10-11-12   [dayfirst=1, yearfirst=0] -> 2012-11-10 00:00:00
+        # 2.5.3 10-11-12   [dayfirst=1, yearfirst=0] -> 2012-11-10 00:00:00
+
+        # OK
+        # 2.5.1 20/12/21   [dayfirst=0, yearfirst=0] -> 2021-12-20 00:00:00
+        # 2.5.2 20/12/21   [dayfirst=0, yearfirst=0] -> 2021-12-20 00:00:00
+        # 2.5.3 20/12/21   [dayfirst=0, yearfirst=0] -> 2021-12-20 00:00:00
+
+        # OK
+        # 2.5.1 20/12/21   [dayfirst=0, yearfirst=1] -> 2020-12-21 00:00:00
+        # 2.5.2 20/12/21   [dayfirst=0, yearfirst=1] -> 2020-12-21 00:00:00
+        # 2.5.3 20/12/21   [dayfirst=0, yearfirst=1] -> 2020-12-21 00:00:00
+
+        # revert of bug in 2.5.2
+        # 2.5.1 20/12/21   [dayfirst=1, yearfirst=1] -> 2020-12-21 00:00:00
+        # 2.5.2 20/12/21   [dayfirst=1, yearfirst=1] -> month must be in 1..12
+        # 2.5.3 20/12/21   [dayfirst=1, yearfirst=1] -> 2020-12-21 00:00:00
+
+        # OK
+        # 2.5.1 20/12/21   [dayfirst=1, yearfirst=0] -> 2021-12-20 00:00:00
+        # 2.5.2 20/12/21   [dayfirst=1, yearfirst=0] -> 2021-12-20 00:00:00
+        # 2.5.3 20/12/21   [dayfirst=1, yearfirst=0] -> 2021-12-20 00:00:00
 
-        # https://github.com/dateutil/dateutil/issues/217
-        # this issue was closed
         import dateutil
-        is_compat_version = dateutil.__version__ >= LooseVersion('2.5.2')
-        if is_compat_version:
-            dayfirst_yearfirst1 = datetime.datetime(2010, 12, 11)
-            dayfirst_yearfirst2 = datetime.datetime(2020, 12, 21)
-        else:
-            dayfirst_yearfirst1 = datetime.datetime(2010, 11, 12)
-            dayfirst_yearfirst2 = datetime.datetime(2020, 12, 21)
+        is_lt_253 = dateutil.__version__ < LooseVersion('2.5.3')
 
         # str : dayfirst, yearfirst, expected
-        cases = {'10-11-12': [(False, False, False,
+        cases = {'10-11-12': [(False, False,
                                datetime.datetime(2012, 10, 11)),
-                              (True, False, False,
+                              (True, False,
                                datetime.datetime(2012, 11, 10)),
-                              (False, True, False,
+                              (False, True,
                                datetime.datetime(2010, 11, 12)),
-                              (True, True, False, dayfirst_yearfirst1)],
-                 '20/12/21': [(False, False, False,
+                              (True, True,
+                               datetime.datetime(2010, 12, 11))],
+                 '20/12/21': [(False, False,
                                datetime.datetime(2021, 12, 20)),
-                              (True, False, False,
+                              (True, False,
                                datetime.datetime(2021, 12, 20)),
-                              (False, True, False,
+                              (False, True,
                                datetime.datetime(2020, 12, 21)),
-                              (True, True, True, dayfirst_yearfirst2)]}
+                              (True, True,
+                               datetime.datetime(2020, 12, 21))]}
 
-        tm._skip_if_no_dateutil()
         from dateutil.parser import parse
         for date_str, values in compat.iteritems(cases):
-            for dayfirst, yearfirst, is_compat, expected in values:
+            for dayfirst, yearfirst, expected in values:
 
-                f = lambda x: tools.parse_time_string(x,
-                                                      dayfirst=dayfirst,
-                                                      yearfirst=yearfirst)
-
-                # we now have an invalid parse
-                if is_compat and is_compat_version:
-                    self.assertRaises(tslib.DateParseError, f, date_str)
-
-                    def f(date_str):
-                        return to_datetime(date_str, dayfirst=dayfirst,
-                                           yearfirst=yearfirst)
-
-                    self.assertRaises(ValueError, f, date_str)
-
-                    def f(date_str):
-                        return DatetimeIndex([date_str], dayfirst=dayfirst,
-                                             yearfirst=yearfirst)[0]
+                # odd comparisons across version
+                # let's just skip
+                if dayfirst and yearfirst and is_lt_253:
+                    continue
 
-                    self.assertRaises(ValueError, f, date_str)
+                # compare with dateutil result
+                dateutil_result = parse(date_str, dayfirst=dayfirst,
+                                        yearfirst=yearfirst)
+                self.assertEqual(dateutil_result, expected)
 
-                    continue
+                result1, _, _ = tools.parse_time_string(date_str,
+                                                        dayfirst=dayfirst,
+                                                        yearfirst=yearfirst)
 
-                result1, _, _ = f(date_str)
+                # we don't support dayfirst/yearfirst here:
+                if not dayfirst and not yearfirst:
+                    result2 = Timestamp(date_str)
+                    self.assertEqual(result2, expected)
 
-                result2 = to_datetime(date_str, dayfirst=dayfirst,
+                result3 = to_datetime(date_str, dayfirst=dayfirst,
                                       yearfirst=yearfirst)
 
-                result3 = DatetimeIndex([date_str], dayfirst=dayfirst,
+                result4 = DatetimeIndex([date_str], dayfirst=dayfirst,
                                         yearfirst=yearfirst)[0]
 
-                # Timestamp doesn't support dayfirst and yearfirst
                 self.assertEqual(result1, expected)
-                self.assertEqual(result2, expected)
                 self.assertEqual(result3, expected)
-
-                # compare with dateutil result
-                dateutil_result = parse(date_str, dayfirst=dayfirst,
-                                        yearfirst=yearfirst)
-                self.assertEqual(dateutil_result, expected)
+                self.assertEqual(result4, expected)
 
     def test_parsers_timestring(self):
         tm._skip_if_no_dateutil()

pandas/tslib.pxd

@@ -1,6 +1,6 @@
 from numpy cimport ndarray, int64_t
 
-cdef convert_to_tsobject(object, object, object)
+cdef convert_to_tsobject(object, object, object, bint, bint)
 cdef convert_to_timedelta64(object, object, object)
 cpdef object maybe_get_tz(object)
 cdef bint _is_utc(object)

pandas/tslib.pyx

@@ -237,9 +237,6 @@ class Timestamp(_Timestamp):
         numpy unit used for conversion, if ts_input is int or float
     """
 
-    # Do not add ``dayfirst`` and ``yearfist`` to Timestamp based on the discussion
-    # https://github.com/pydata/pandas/pull/7599
-
     @classmethod
     def fromordinal(cls, ordinal, offset=None, tz=None):
         """ passed an ordinal, translate and convert to a ts
@@ -295,7 +292,7 @@ class Timestamp(_Timestamp):
         cdef _TSObject ts
         cdef _Timestamp ts_base
 
-        ts = convert_to_tsobject(ts_input, tz, unit)
+        ts = convert_to_tsobject(ts_input, tz, unit, 0, 0)
 
         if ts.value == NPY_NAT:
             return NaT
@@ -544,7 +541,7 @@ class Timestamp(_Timestamp):
 
         if self.nanosecond != 0 and warn:
             print 'Warning: discarding nonzero nanoseconds'
-        ts = convert_to_tsobject(self, self.tzinfo, None)
+        ts = convert_to_tsobject(self, self.tzinfo, None, 0, 0)
 
         return datetime(ts.dts.year, ts.dts.month, ts.dts.day,
                         ts.dts.hour, ts.dts.min, ts.dts.sec,
@@ -997,7 +994,7 @@ cdef class _Timestamp(datetime):
         cdef:
             pandas_datetimestruct dts
             _TSObject ts
-        ts = convert_to_tsobject(self, self.tzinfo, None)
+        ts = convert_to_tsobject(self, self.tzinfo, None, 0, 0)
         dts = ts.dts
         return datetime(dts.year, dts.month, dts.day,
                         dts.hour, dts.min, dts.sec,
@@ -1237,7 +1234,8 @@ cpdef _get_utcoffset(tzinfo, obj):
         return tzinfo.utcoffset(obj)
 
 # helper to extract datetime and int64 from several different possibilities
-cdef convert_to_tsobject(object ts, object tz, object unit):
+cdef convert_to_tsobject(object ts, object tz, object unit,
+                         bint dayfirst, bint yearfirst):
     """
     Extract datetime and int64 from any of:
         - np.int64 (with unit providing a possible modifier)
@@ -1259,7 +1257,7 @@ cdef convert_to_tsobject(object ts, object tz, object unit):
     obj = _TSObject()
 
     if util.is_string_object(ts):
-        return convert_str_to_tsobject(ts, tz, unit)
+        return convert_str_to_tsobject(ts, tz, unit, dayfirst, yearfirst)
 
     if ts is None or ts is NaT:
         obj.value = NPY_NAT
@@ -1329,7 +1327,7 @@ cdef convert_to_tsobject(object ts, object tz, object unit):
     elif PyDate_Check(ts):
         # Keep the converter same as PyDateTime's
         ts = datetime.combine(ts, datetime_time())
-        return convert_to_tsobject(ts, tz, None)
+        return convert_to_tsobject(ts, tz, None, 0, 0)
     elif getattr(ts, '_typ', None) == 'period':
         raise ValueError("Cannot convert Period to Timestamp unambiguously. Use to_timestamp")
     else:
@@ -1390,7 +1388,7 @@ cpdef convert_str_to_tsobject(object ts, object tz, object unit,
             except Exception:
                 raise ValueError
 
-    return convert_to_tsobject(ts, tz, unit)
+    return convert_to_tsobject(ts, tz, unit, dayfirst, yearfirst)
 
 def _test_parse_iso8601(object ts):
     """
@@ -1581,7 +1579,7 @@ def datetime_to_datetime64(ndarray[object] values):
                 else:
                     inferred_tz = _get_zone(val.tzinfo)
 
-                _ts = convert_to_tsobject(val, None, None)
+                _ts = convert_to_tsobject(val, None, None, 0, 0)
                 iresult[i] = _ts.value
                 _check_dts_bounds(&_ts.dts)
             else:
@@ -1993,7 +1991,7 @@ cpdef array_to_datetime(ndarray[object] values, errors='raise',
                 seen_datetime=1
                 if val.tzinfo is not None:
                     if utc_convert:
-                        _ts = convert_to_tsobject(val, None, unit)
+                        _ts = convert_to_tsobject(val, None, unit, 0, 0)
                         iresult[i] = _ts.value
                         try:
                             _check_dts_bounds(&_ts.dts)
@@ -2091,7 +2089,7 @@ cpdef array_to_datetime(ndarray[object] values, errors='raise',
                         raise TypeError("invalid string coercion to datetime")
 
                     try:
-                        _ts = convert_to_tsobject(py_dt, None, None)
+                        _ts = convert_to_tsobject(py_dt, None, None, 0, 0)
                         iresult[i] = _ts.value
                     except ValueError:
                         if is_coerce:
@@ -2180,7 +2178,7 @@ def parse_str_array_to_datetime(ndarray values, dayfirst=False,
                                           yearfirst=yearfirst, freq=freq)
         except Exception:
             raise ValueError
-        _ts = convert_to_tsobject(py_dt, None, None)
+        _ts = convert_to_tsobject(py_dt, None, None, 0, 0)
         iresult[i] = _ts.value
 
     return iresult
@@ -3466,7 +3464,7 @@ def pydt_to_i8(object pydt):
     cdef:
         _TSObject ts
 
-    ts = convert_to_tsobject(pydt, None, None)
+    ts = convert_to_tsobject(pydt, None, None, 0, 0)
 
     return ts.value
 
@@ -4230,7 +4228,7 @@ def get_start_end_field(ndarray[int64_t] dtindex, object field, object freqstr=N
                 if dtindex[i] == NPY_NAT: out[i] = -1; continue
 
                 pandas_datetime_to_datetimestruct(dtindex[i], PANDAS_FR_ns, &dts)
-                ts = convert_to_tsobject(dtindex[i], None, None)
+                ts = convert_to_tsobject(dtindex[i], None, None, 0, 0)
                 dom = dts.day
                 dow = ts_dayofweek(ts)
 
@@ -4254,7 +4252,7 @@ def get_start_end_field(ndarray[int64_t] dtindex, object field, object freqstr=N
                 if dtindex[i] == NPY_NAT: out[i] = -1; continue
 
                 pandas_datetime_to_datetimestruct(dtindex[i], PANDAS_FR_ns, &dts)
-                ts = convert_to_tsobject(dtindex[i], None, None)
+                ts = convert_to_tsobject(dtindex[i], None, None, 0, 0)
                 isleap = is_leapyear(dts.year)
                 mo_off = _month_offset[isleap, dts.month - 1]
                 dom = dts.day
@@ -4286,7 +4284,7 @@ def get_start_end_field(ndarray[int64_t] dtindex, object field, object freqstr=N
                 if dtindex[i] == NPY_NAT: out[i] = -1; continue
 
                 pandas_datetime_to_datetimestruct(dtindex[i], PANDAS_FR_ns, &dts)
-                ts = convert_to_tsobject(dtindex[i], None, None)
+                ts = convert_to_tsobject(dtindex[i], None, None, 0, 0)
                 dom = dts.day
                 dow = ts_dayofweek(ts)
 
@@ -4310,7 +4308,7 @@ def get_start_end_field(ndarray[int64_t] dtindex, object field, object freqstr=N
                 if dtindex[i] == NPY_NAT: out[i] = -1; continue
 
                 pandas_datetime_to_datetimestruct(dtindex[i], PANDAS_FR_ns, &dts)
-                ts = convert_to_tsobject(dtindex[i], None, None)
+                ts = convert_to_tsobject(dtindex[i], None, None, 0, 0)
                 isleap = is_leapyear(dts.year)
                 mo_off = _month_offset[isleap, dts.month - 1]
                 dom = dts.day
@@ -4342,7 +4340,7 @@ def get_start_end_field(ndarray[int64_t] dtindex, object field, object freqstr=N
                 if dtindex[i] == NPY_NAT: out[i] = -1; continue
 
                 pandas_datetime_to_datetimestruct(dtindex[i], PANDAS_FR_ns, &dts)
-                ts = convert_to_tsobject(dtindex[i], None, None)
+                ts = convert_to_tsobject(dtindex[i], None, None, 0, 0)
                 dom = dts.day
                 dow = ts_dayofweek(ts)
 
@@ -4366,7 +4364,7 @@ def get_start_end_field(ndarray[int64_t] dtindex, object field, object freqstr=N
                 if dtindex[i] == NPY_NAT: out[i] = -1; continue
 
                 pandas_datetime_to_datetimestruct(dtindex[i], PANDAS_FR_ns, &dts)
-                ts = convert_to_tsobject(dtindex[i], None, None)
+                ts = convert_to_tsobject(dtindex[i], None, None, 0, 0)
                 isleap = is_leapyear(dts.year)
                 dom = dts.day
                 mo_off = _month_offset[isleap, dts.month - 1]
@@ -4382,7 +4380,7 @@ def get_start_end_field(ndarray[int64_t] dtindex, object field, object freqstr=N
                 if dtindex[i] == NPY_NAT: out[i] = -1; continue
 
                 pandas_datetime_to_datetimestruct(dtindex[i], PANDAS_FR_ns, &dts)
-                ts = convert_to_tsobject(dtindex[i], None, None)
+                ts = convert_to_tsobject(dtindex[i], None, None, 0, 0)
                 isleap = is_leapyear(dts.year)
                 mo_off = _month_offset[isleap, dts.month - 1]
                 dom = dts.day
@@ -4429,7 +4427,7 @@ def get_date_name_field(ndarray[int64_t] dtindex, object field):
 
 
 cdef inline int m8_weekday(int64_t val):
-    ts = convert_to_tsobject(val, None, None)
+    ts = convert_to_tsobject(val, None, None, 0, 0)
     return ts_dayofweek(ts)
 
 cdef int64_t DAY_NS = 86400000000000LL