ENH: Add isocalendar accessor to DatetimeIndex and Series.dt

doc/source/whatsnew/v1.1.0.rst

@@ -88,6 +88,7 @@ Other enhancements
 - :class:`Series.str` now has a `fullmatch` method that matches a regular expression against the entire string in each row of the series, similar to `re.fullmatch` (:issue:`32806`).
 - :meth:`DataFrame.sample` will now also allow array-like and BitGenerator objects to be passed to ``random_state`` as seeds (:issue:`32503`)
 - :meth:`MultiIndex.union` will now raise `RuntimeWarning` if the object inside are unsortable, pass `sort=False` to suppress this warning (:issue:`33015`)
+- :class:`Series.dt` and :class:`DatatimeIndex` now have an `isocalendar` accessor that returns a :class:`DataFrame` with year, week, and day calculated according to the ISO 8601 calendar (:issue:`33206`).
 -
 
 .. ---------------------------------------------------------------------------

pandas/_libs/tslibs/ccalendar.pxd

@@ -2,9 +2,11 @@ from cython cimport Py_ssize_t
 
 from numpy cimport int64_t, int32_t
 
+ctypedef (int32_t, int32_t, int32_t) iso_calendar_t
 
 cdef int dayofweek(int y, int m, int d) nogil
 cdef bint is_leapyear(int64_t year) nogil
 cpdef int32_t get_days_in_month(int year, Py_ssize_t month) nogil
 cpdef int32_t get_week_of_year(int year, int month, int day) nogil
+cpdef iso_calendar_t get_iso_calendar(int year, int month, int day) nogil
 cpdef int32_t get_day_of_year(int year, int month, int day) nogil

pandas/_libs/tslibs/ccalendar.pyx

@@ -150,33 +150,65 @@ cpdef int32_t get_week_of_year(int year, int month, int day) nogil:
     -------
     week_of_year : int32_t
 
+    Notes
+    -----
+    Assumes the inputs describe a valid date.
+    """
+    return get_iso_calendar(year, month, day)[1]
+
+
+@cython.wraparound(False)
+@cython.boundscheck(False)
+cpdef iso_calendar_t get_iso_calendar(int year, int month, int day) nogil:
+    """
+    Return the year, week, and day of year corresponding to ISO 8601
+
+    Parameters
+    ----------
+    year : int
+    month : int
+    day : int
+
+    Returns
+    -------
+    year : int32_t
+    week : int32_t
+    day : int32_t
+
     Notes
     -----
     Assumes the inputs describe a valid date.
     """
     cdef:
         int32_t doy, dow
-        int woy
+        int32_t iso_year, iso_week
 
     doy = get_day_of_year(year, month, day)
     dow = dayofweek(year, month, day)
 
     # estimate
-    woy = (doy - 1) - dow + 3
-    if woy >= 0:
-        woy = woy // 7 + 1
+    iso_week = (doy - 1) - dow + 3
+    if iso_week >= 0:
+        iso_week = iso_week // 7 + 1
 
     # verify
-    if woy < 0:
-        if (woy > -2) or (woy == -2 and is_leapyear(year - 1)):
-            woy = 53
+    if iso_week < 0:
+        if (iso_week > -2) or (iso_week == -2 and is_leapyear(year - 1)):
+            iso_week = 53
         else:
-            woy = 52
-    elif woy == 53:
+            iso_week = 52
+    elif iso_week == 53:
         if 31 - day + dow < 3:
-            woy = 1
+            iso_week = 1
+
+    iso_year = year
+    if iso_week == 1 and doy > 7:
+        iso_year += 1
+
+    elif iso_week >= 52 and doy < 7:
+        iso_year -= 1
 
-    return woy
+    return iso_year, iso_week, dow + 1
 
 
 @cython.wraparound(False)

pandas/_libs/tslibs/fields.pyx

@@ -15,7 +15,7 @@ from pandas._libs.tslibs.ccalendar import (
     get_locale_names, MONTHS_FULL, DAYS_FULL, DAY_SECONDS)
 from pandas._libs.tslibs.ccalendar cimport (
     get_days_in_month, is_leapyear, dayofweek, get_week_of_year,
-    get_day_of_year)
+    get_day_of_year, get_iso_calendar, iso_calendar_t)
 from pandas._libs.tslibs.np_datetime cimport (
     npy_datetimestruct, pandas_timedeltastruct, dt64_to_dtstruct,
     td64_to_tdstruct)
@@ -670,3 +670,42 @@ cpdef isleapyear_arr(ndarray years):
                       np.logical_and(years % 4 == 0,
                                      years % 100 > 0))] = 1
     return out.view(bool)
+
+
+@cython.wraparound(False)
+@cython.boundscheck(False)
+def build_isocalendar_sarray(const int64_t[:] dtindex):
+    """
+    Given a int64-based datetime array, return the ISO 8601 year, week, and day
+    as a structured array.
+    """
+    cdef:
+        Py_ssize_t i, count = len(dtindex)
+        npy_datetimestruct dts
+        ndarray[int32_t] iso_years, iso_weeks, days
+        iso_calendar_t ret_val
+
+    sa_dtype = [
+        ("year", "i4"),
+        ("week", "i4"),
+        ("day", "i4"),
+    ]
+
+    out = np.empty(count, dtype=sa_dtype)
+
+    iso_years = out["year"]
+    iso_weeks = out["week"]
+    days = out["day"]
+
+    with nogil:
+        for i in range(count):
+            if dtindex[i] == NPY_NAT:
+                ret_val = -1, -1, -1
+            else:
+                dt64_to_dtstruct(dtindex[i], &dts)
+                ret_val = get_iso_calendar(dts.year, dts.month, dts.day)
+
+            iso_years[i] = ret_val[0]
+            iso_weeks[i] = ret_val[1]
+            days[i] = ret_val[2]
+    return out

pandas/core/arrays/datetimes.py

@@ -182,7 +182,7 @@ class DatetimeArray(dtl.DatetimeLikeArrayMixin, dtl.TimelikeOps, dtl.DatelikeOps
         "microsecond",
         "nanosecond",
     ]
-    _other_ops = ["date", "time", "timetz"]
+    _other_ops = ["date", "time", "timetz", "isocalendar"]
     _datetimelike_ops = _field_ops + _object_ops + _bool_ops + _other_ops
     _datetimelike_methods = [
         "to_period",
@@ -1234,6 +1234,50 @@ def date(self):
 
         return tslib.ints_to_pydatetime(timestamps, box="date")
 
+    @property
+    def isocalendar(self):
+        """
+        Returns a DataFrame with the year, week, and day calculated according to
+        the ISO 8601 standard.
+
+        .. versionadded:: 1.1.0
+
+        Returns
+        -------
+        DataFrame
+            with columns year, week and day
+
+        See Also
+        --------
+        Timestamp.isocalendar
+        datetime.date.isocalendar
+
+        Examples
+        --------
+        >>> idx = pd.date_range(start='2019-12-29', freq='D', periods=4)
+        >>> idx.isocalendar
+           year  week  day
+        0  2019    52    7
+        1  2020     1    1
+        2  2020     1    2
+        3  2020     1    3
+        >>> idx.isocalendar.week
+        0    52
+        1     1
+        2     1
+        3     1
+        Name: week, dtype: Int64
+        """
+        from pandas import DataFrame
+
+        sarray = fields.build_isocalendar_sarray(self.asi8)
+        iso_calendar_df = DataFrame(
+            sarray, columns=["year", "week", "day"], dtype="Int64"
+        )
+        if self._hasnans:
+            iso_calendar_df.iloc[self._isnan] = None
+        return iso_calendar_df
+
     year = _field_accessor(
         "year",
         "Y",

pandas/core/indexes/accessors.py

@@ -219,6 +219,38 @@ def to_pydatetime(self) -> np.ndarray:
     def freq(self):
         return self._get_values().inferred_freq
 
+    @property
+    def isocalendar(self):
+        """
+        Returns a DataFrame with the year, week, and day calculated according to
+        the ISO 8601 standard.
+
+        .. versionadded:: 1.1.0
+
+        Returns
+        -------
+        DataFrame
+            with columns year, week and day
+
+        See Also
+        --------
+        Timestamp.isocalendar
+        datetime.date.isocalendar
+
+        Examples
+        --------
+        >>> ser = pd.to_datetime(pd.Series(["2010-01-01", pd.NaT]))
+        >>> ser.dt.isocalendar
+           year  week  day
+        0  2009    53     5
+        1  <NA>  <NA>  <NA>
+        >>> ser.dt.isocalendar.week
+        0      53
+        1    <NA>
+        Name: week, dtype: Int64
+        """
+        return self._get_values().isocalendar.set_index(self._parent.index)
+
 
 @delegate_names(
     delegate=TimedeltaArray, accessors=TimedeltaArray._datetimelike_ops, typ="property"

pandas/core/indexes/datetimes.py

@@ -89,6 +89,7 @@ def _new_DatetimeIndex(cls, d):
         "date",
         "time",
         "timetz",
+        "isocalendar",
     ]
     + DatetimeArray._bool_ops,
     DatetimeArray,

pandas/tests/series/test_datetime_values.py

@@ -65,7 +65,7 @@ def get_expected(s, name):
             if isinstance(result, np.ndarray):
                 if is_integer_dtype(result):
                     result = result.astype("int64")
-            elif not is_list_like(result):
+            elif not is_list_like(result) or isinstance(result, pd.DataFrame):
                 return result
             return Series(result, index=s.index, name=s.name)
 
@@ -74,6 +74,8 @@ def compare(s, name):
             b = get_expected(s, prop)
             if not (is_list_like(a) and is_list_like(b)):
                 assert a == b
+            elif isinstance(a, pd.DataFrame):
+                tm.assert_frame_equal(a, b)
             else:
                 tm.assert_series_equal(a, b)
 
@@ -665,3 +667,19 @@ def test_setitem_with_different_tz(self):
             dtype=object,
         )
         tm.assert_series_equal(ser, expected)
+
+    @pytest.mark.parametrize(
+        "input_series, expected_output",
+        [
+            [["2020-01-01"], [[2020, 1, 3]]],
+            [[pd.NaT], [[np.NaN, np.NaN, np.NaN]]],
+            [["2019-12-31", "2019-12-29"], [[2020, 1, 2], [2019, 52, 7]]],
+            [["2010-01-01", pd.NaT], [[2009, 53, 5], [np.NaN, np.NaN, np.NaN]]],
+        ],
+    )
+    def test_isocalendar(self, input_series, expected_output):
+        result = pd.to_datetime(pd.Series(input_series)).dt.isocalendar
+        expected_frame = pd.DataFrame(
+            expected_output, columns=["year", "week", "day"], dtype="Int64"
+        )
+        tm.assert_frame_equal(result, expected_frame)

pandas/tests/tslibs/test_ccalendar.py

@@ -1,4 +1,4 @@
-from datetime import datetime
+from datetime import date, datetime
 
 import numpy as np
 import pytest
@@ -25,3 +25,26 @@ def test_get_day_of_year_dt():
 
     expected = (dt - dt.replace(month=1, day=1)).days + 1
     assert result == expected
+
+
+@pytest.mark.parametrize(
+    "input_date_tuple, expected_iso_tuple",
+    [
+        [(2020, 1, 1), (2020, 1, 3)],
+        [(2019, 12, 31), (2020, 1, 2)],
+        [(2019, 12, 30), (2020, 1, 1)],
+        [(2009, 12, 31), (2009, 53, 4)],
+        [(2010, 1, 1), (2009, 53, 5)],
+        [(2010, 1, 3), (2009, 53, 7)],
+        [(2010, 1, 4), (2010, 1, 1)],
+        [(2006, 1, 1), (2005, 52, 7)],
+        [(2005, 12, 31), (2005, 52, 6)],
+        [(2008, 12, 28), (2008, 52, 7)],
+        [(2008, 12, 29), (2009, 1, 1)],
+    ],
+)
+def test_dt_correct_iso_8601_year_week_and_day(input_date_tuple, expected_iso_tuple):
+    result = ccalendar.get_iso_calendar(*input_date_tuple)
+    expected_from_date_isocalendar = date(*input_date_tuple).isocalendar()
+    assert result == expected_from_date_isocalendar
+    assert result == expected_iso_tuple