Preserve base and loffset arguments in resample

xarray/core/common.py

@@ -10,10 +10,16 @@
 import numpy as np
 import pandas as pd
 
+from xarray.coding import cftime_offsets
 from xarray.core import dtypes, duck_array_ops, formatting, formatting_html, ops
 from xarray.core.options import OPTIONS, _get_keep_attrs
 from xarray.core.pycompat import is_duck_dask_array
-from xarray.core.utils import Frozen, either_dict_or_kwargs, is_scalar
+from xarray.core.utils import (
+    Frozen,
+    either_dict_or_kwargs,
+    emit_user_level_warning,
+    is_scalar,
+)
 
 try:
     import cftime
@@ -928,8 +934,8 @@ def _resample(
         """
         # TODO support non-string indexer after removing the old API.
 
-        from xarray.coding.cftimeindex import CFTimeIndex
         from xarray.core.dataarray import DataArray
+        from xarray.core.groupby import TimeResampleGrouper
         from xarray.core.resample import RESAMPLE_DIM
 
         if keep_attrs is not None:
@@ -959,28 +965,36 @@ def _resample(
         dim_name: Hashable = dim
         dim_coord = self[dim]
 
-        if isinstance(self._indexes[dim_name].to_pandas_index(), CFTimeIndex):
-            from xarray.core.resample_cftime import CFTimeGrouper
-
-            grouper = CFTimeGrouper(
-                freq=freq,
-                closed=closed,
-                label=label,
-                base=base,
-                loffset=loffset,
-                origin=origin,
-                offset=offset,
+        if loffset is not None:
+            emit_user_level_warning(
+                "Following pandas, the `loffset` argument to resample will be deprecated in a "
+                "future version of xarray.  Switch to using time offset arithmetic.",
+                FutureWarning,
             )
-        else:
-            grouper = pd.Grouper(
-                freq=freq,
-                closed=closed,
-                label=label,
-                base=base,
-                offset=offset,
-                origin=origin,
-                loffset=loffset,
+
+        if base is None:
+            emit_user_level_warning(
+                "Following pandas, the `base` argument to resample will be deprecated in a "
+                "future version of xarray.  Switch to using `origin` or `offset` instead.",
+                FutureWarning,
             )
+
+        if base is not None and offset is not None:
+            raise ValueError("base and offset cannot be present at the same time")
+
+        if base is not None:
+            index = self._indexes[dim_name].to_pandas_index()
+            offset = _convert_base_to_offset(base, freq, index)
+
+        grouper = TimeResampleGrouper(
+            freq=freq,
+            closed=closed,
+            label=label,
+            origin=origin,
+            offset=offset,
+            loffset=loffset,
+        )
+
         group = DataArray(
             dim_coord, coords=dim_coord.coords, dims=dim_coord.dims, name=RESAMPLE_DIM
         )
@@ -1799,3 +1813,22 @@ def _contains_datetime_like_objects(var) -> bool:
     np.datetime64, np.timedelta64, or cftime.datetime)
     """
     return is_np_datetime_like(var.dtype) or contains_cftime_datetimes(var)
+
+
+def _convert_base_to_offset(base, freq, index):
+    """Required until we officially deprecate the base argument to resample.  This
+    translates a provided `base` argument to an `offset` argument, following logic
+    from pandas.
+    """
+    from xarray.coding.cftimeindex import CFTimeIndex
+
+    if isinstance(index, pd.DatetimeIndex):
+        freq = pd.tseries.frequencies.to_offset(freq)
+        if isinstance(freq, pd.offsets.Tick):
+            return pd.Timedelta(base * freq.nanos // freq.n)
+    elif isinstance(index, CFTimeIndex):
+        freq = cftime_offsets.to_offset(freq)
+        if isinstance(freq, cftime_offsets.Tick):
+            return base * freq.as_timedelta() // freq.n
+    else:
+        raise ValueError("Can only resample using a DatetimeIndex or CFTimeIndex.")

xarray/core/groupby.py

@@ -245,7 +245,7 @@ def _unique_and_monotonic(group: T_Group) -> bool:
     return index.is_unique and index.is_monotonic_increasing
 
 
-def _apply_loffset(grouper, result):
+def _apply_loffset(loffset, result):
     """
     (copied from pandas)
     if loffset is set, offset the result index
@@ -258,17 +258,19 @@ def _apply_loffset(grouper, result):
     result : Series or DataFrame
         the result of resample
     """
+    # TODO: include some validation of the type of the loffset
+    # argument.
+    if isinstance(loffset, str):
+        loffset = pd.tseries.frequencies.to_offset(loffset)
 
     needs_offset = (
-        isinstance(grouper.loffset, (pd.DateOffset, datetime.timedelta))
+        isinstance(loffset, (pd.DateOffset, datetime.timedelta))
         and isinstance(result.index, pd.DatetimeIndex)
         and len(result.index) > 0
     )
 
     if needs_offset:
-        result.index = result.index + grouper.loffset
-
-    grouper.loffset = None
+        result.index = result.index + loffset
 
 
 class GroupBy(Generic[T_Xarray]):
@@ -530,14 +532,7 @@ def __repr__(self) -> str:
         )
 
     def _get_index_and_items(self, index, grouper):
-        from xarray.core.resample_cftime import CFTimeGrouper
-
-        s = pd.Series(np.arange(index.size), index)
-        if isinstance(grouper, CFTimeGrouper):
-            first_items = grouper.first_items(index)
-        else:
-            first_items = s.groupby(grouper).first()
-            _apply_loffset(grouper, first_items)
+        first_items = grouper.first_items(index)
         full_index = first_items.index
         if first_items.isnull().any():
             first_items = first_items.dropna()
@@ -1365,3 +1360,41 @@ class DatasetGroupBy(  # type: ignore[misc]
     ImplementsDatasetReduce,
 ):
     __slots__ = ()
+
+
+class TimeResampleGrouper:
+    def __init__(self, freq, closed, label, origin, offset, loffset):
+        self.freq = freq
+        self.closed = closed
+        self.label = label
+        self.origin = origin
+        self.offset = offset
+        self.loffset = loffset
+
+    def first_items(self, index):
+        from xarray import CFTimeIndex
+        from xarray.core.resample_cftime import CFTimeGrouper
+
+        if isinstance(index, CFTimeIndex):
+            grouper = CFTimeGrouper(
+                freq=self.freq,
+                closed=self.closed,
+                label=self.label,
+                origin=self.origin,
+                offset=self.offset,
+                loffset=self.loffset,
+            )
+            return grouper.first_items(index)
+        else:
+            s = pd.Series(np.arange(index.size), index)
+            grouper = pd.Grouper(
+                freq=self.freq,
+                closed=self.closed,
+                label=self.label,
+                origin=self.origin,
+                offset=self.offset,
+            )
+
+            first_items = s.groupby(grouper).first()
+            _apply_loffset(self.loffset, first_items)
+        return first_items

xarray/core/resample_cftime.py

@@ -71,18 +71,13 @@ def __init__(
         freq: str | BaseCFTimeOffset,
         closed: SideOptions | None = None,
         label: SideOptions | None = None,
-        base: int | None = None,
         loffset: str | datetime.timedelta | BaseCFTimeOffset | None = None,
         origin: str | CFTimeDatetime = "start_day",
         offset: str | datetime.timedelta | None = None,
     ):
         self.offset: datetime.timedelta | None
         self.closed: SideOptions
         self.label: SideOptions
-
-        if base is not None and offset is not None:
-            raise ValueError("base and offset cannot be provided at the same time")
-
         self.freq = to_offset(freq)
         self.loffset = loffset
         self.origin = origin
@@ -122,9 +117,6 @@ def __init__(
                 else:
                     self.label = label
 
-        if base is not None and isinstance(self.freq, Tick):
-            offset = type(self.freq)(n=base % self.freq.n).as_timedelta()
-
         if offset is not None:
             try:
                 self.offset = _convert_offset_to_timedelta(offset)

xarray/tests/test_groupby.py

@@ -16,6 +16,7 @@
     assert_equal,
     assert_identical,
     create_test_data,
+    has_pandas_version_two,
     requires_dask,
     requires_flox,
     requires_scipy,
@@ -1802,6 +1803,7 @@ def test_upsample_interpolate_dask(self, chunked_time):
             # done here due to floating point arithmetic
             assert_allclose(expected, actual, rtol=1e-16)
 
+    @pytest.mark.skipif(has_pandas_version_two, reason="requires pandas < 2.0.0")
     def test_resample_base(self) -> None:
         times = pd.date_range("2000-01-01T02:03:01", freq="6H", periods=10)
         array = DataArray(np.arange(10), [("time", times)])