Merge branch 'main' into chunk-by-frequency

* main: Delete ``base`` and ``loffset`` parameters to resample (pydata#9233) Update dropna docstring (pydata#9257)
dcherian · Jul 19, 2024 · 5e61d14 · 5e61d14
2 parents 5c39645 + 39d5b39
commit 5e61d14
Show file tree

Hide file tree

Showing 9 changed files with 43 additions and 402 deletions.
diff --git a/doc/whats-new.rst b/doc/whats-new.rst
@@ -45,6 +45,11 @@ New Features
 
 Breaking changes
 ~~~~~~~~~~~~~~~~
+- The ``base`` and ``loffset`` parameters to :py:meth:`Dataset.resample` and :py:meth:`DataArray.resample`
+  is now removed. These parameters has been deprecated since v2023.03.0. Using the
+  ``origin`` or ``offset`` parameters is recommended as a replacement for using
+  the ``base`` parameter and using time offset arithmetic is recommended as a
+  replacement for using the ``loffset`` parameter.
 
 
 Deprecations

diff --git a/xarray/core/common.py b/xarray/core/common.py
@@ -881,10 +881,8 @@ def _resample(
         skipna: bool | None,
         closed: SideOptions | None,
         label: SideOptions | None,
-        base: int | None,
         offset: pd.Timedelta | datetime.timedelta | str | None,
         origin: str | DatetimeLike,
-        loffset: datetime.timedelta | str | None,
         restore_coord_dims: bool | None,
         **indexer_kwargs: str | Resampler,
     ) -> T_Resample:
@@ -906,16 +904,6 @@ def _resample(
             Side of each interval to treat as closed.
         label : {"left", "right"}, optional
             Side of each interval to use for labeling.
-        base : int, optional
-            For frequencies that evenly subdivide 1 day, the "origin" of the
-            aggregated intervals. For example, for "24H" frequency, base could
-            range from 0 through 23.
-
-            .. deprecated:: 2023.03.0
-                Following pandas, the ``base`` parameter is deprecated in favor
-                of the ``origin`` and ``offset`` parameters, and will be removed
-                in a future version of xarray.
-
         origin : {'epoch', 'start', 'start_day', 'end', 'end_day'}, pd.Timestamp, datetime.datetime, np.datetime64, or cftime.datetime, default 'start_day'
             The datetime on which to adjust the grouping. The timezone of origin
             must match the timezone of the index.
@@ -928,15 +916,6 @@ def _resample(
             - 'end_day': `origin` is the ceiling midnight of the last day
         offset : pd.Timedelta, datetime.timedelta, or str, default is None
             An offset timedelta added to the origin.
-        loffset : timedelta or str, optional
-            Offset used to adjust the resampled time labels. Some pandas date
-            offset strings are supported.
-
-            .. deprecated:: 2023.03.0
-                Following pandas, the ``loffset`` parameter is deprecated in favor
-                of using time offset arithmetic, and will be removed in a future
-                version of xarray.
-
         restore_coord_dims : bool, optional
             If True, also restore the dimension order of multi-dimensional
             coordinates.
@@ -1072,18 +1051,6 @@ def _resample(
         from xarray.core.groupers import Resampler, TimeResampler
         from xarray.core.resample import RESAMPLE_DIM
 
-        # note: the second argument (now 'skipna') use to be 'dim'
-        if (
-            (skipna is not None and not isinstance(skipna, bool))
-            or ("how" in indexer_kwargs and "how" not in self.dims)
-            or ("dim" in indexer_kwargs and "dim" not in self.dims)
-        ):
-            raise TypeError(
-                "resample() no longer supports the `how` or "
-                "`dim` arguments. Instead call methods on resample "
-                "objects, e.g., data.resample(time='1D').mean()"
-            )
-
         indexer = either_dict_or_kwargs(indexer, indexer_kwargs, "resample")
         if len(indexer) != 1:
             raise ValueError("Resampling only supported along single dimensions.")
@@ -1093,22 +1060,13 @@ def _resample(
         dim_coord = self[dim]
 
         group = DataArray(
-            dim_coord,
-            coords=dim_coord.coords,
-            dims=dim_coord.dims,
-            name=RESAMPLE_DIM,
+            dim_coord, coords=dim_coord.coords, dims=dim_coord.dims, name=RESAMPLE_DIM
         )
 
         grouper: Resampler
         if isinstance(freq, str):
             grouper = TimeResampler(
-                freq=freq,
-                closed=closed,
-                label=label,
-                origin=origin,
-                offset=offset,
-                loffset=loffset,
-                base=base,
+                freq=freq, closed=closed, label=label, origin=origin, offset=offset
             )
         elif isinstance(freq, Resampler):
             grouper = freq

diff --git a/xarray/core/dataarray.py b/xarray/core/dataarray.py
@@ -7249,10 +7249,8 @@ def resample(
         skipna: bool | None = None,
         closed: SideOptions | None = None,
         label: SideOptions | None = None,
-        base: int | None = None,
         offset: pd.Timedelta | datetime.timedelta | str | None = None,
         origin: str | DatetimeLike = "start_day",
-        loffset: datetime.timedelta | str | None = None,
         restore_coord_dims: bool | None = None,
         **indexer_kwargs: str | Resampler,
     ) -> DataArrayResample:
@@ -7274,10 +7272,6 @@ def resample(
             Side of each interval to treat as closed.
         label : {"left", "right"}, optional
             Side of each interval to use for labeling.
-        base : int, optional
-            For frequencies that evenly subdivide 1 day, the "origin" of the
-            aggregated intervals. For example, for "24H" frequency, base could
-            range from 0 through 23.
         origin : {'epoch', 'start', 'start_day', 'end', 'end_day'}, pd.Timestamp, datetime.datetime, np.datetime64, or cftime.datetime, default 'start_day'
             The datetime on which to adjust the grouping. The timezone of origin
             must match the timezone of the index.
@@ -7290,15 +7284,6 @@ def resample(
             - 'end_day': `origin` is the ceiling midnight of the last day
         offset : pd.Timedelta, datetime.timedelta, or str, default is None
             An offset timedelta added to the origin.
-        loffset : timedelta or str, optional
-            Offset used to adjust the resampled time labels. Some pandas date
-            offset strings are supported.
-
-            .. deprecated:: 2023.03.0
-                Following pandas, the ``loffset`` parameter is deprecated in favor
-                of using time offset arithmetic, and will be removed in a future
-                version of xarray.
-
         restore_coord_dims : bool, optional
             If True, also restore the dimension order of multi-dimensional
             coordinates.
@@ -7403,10 +7388,8 @@ def resample(
             skipna=skipna,
             closed=closed,
             label=label,
-            base=base,
             offset=offset,
             origin=origin,
-            loffset=loffset,
             restore_coord_dims=restore_coord_dims,
             **indexer_kwargs,
         )

diff --git a/xarray/core/dataset.py b/xarray/core/dataset.py
@@ -6412,7 +6412,7 @@ def dropna(
         Data variables:
             temperature  (time, location) float64 64B 23.4 24.1 nan ... 24.2 20.5 25.3
 
-        # Drop NaN values from the dataset
+        Drop NaN values from the dataset
 
         >>> dataset.dropna(dim="time")
         <xarray.Dataset> Size: 80B
@@ -6423,7 +6423,7 @@ def dropna(
         Data variables:
             temperature  (time, location) float64 48B 23.4 24.1 21.8 24.2 20.5 25.3
 
-        # Drop labels with any NAN values
+        Drop labels with any NaN values
 
         >>> dataset.dropna(dim="time", how="any")
         <xarray.Dataset> Size: 80B
@@ -6434,7 +6434,7 @@ def dropna(
         Data variables:
             temperature  (time, location) float64 48B 23.4 24.1 21.8 24.2 20.5 25.3
 
-        # Drop labels with all NAN values
+        Drop labels with all NAN values
 
         >>> dataset.dropna(dim="time", how="all")
         <xarray.Dataset> Size: 104B
@@ -6445,7 +6445,7 @@ def dropna(
         Data variables:
             temperature  (time, location) float64 64B 23.4 24.1 nan ... 24.2 20.5 25.3
 
-        # Drop labels with less than 2 non-NA values
+        Drop labels with less than 2 non-NA values
 
         >>> dataset.dropna(dim="time", thresh=2)
         <xarray.Dataset> Size: 80B
@@ -6459,6 +6459,11 @@ def dropna(
         Returns
         -------
         Dataset
+
+        See Also
+        --------
+        DataArray.dropna
+        pandas.DataFrame.dropna
         """
         # TODO: consider supporting multiple dimensions? Or not, given that
         # there are some ugly edge cases, e.g., pandas's dropna differs
@@ -10667,10 +10672,8 @@ def resample(
         skipna: bool | None = None,
         closed: SideOptions | None = None,
         label: SideOptions | None = None,
-        base: int | None = None,
         offset: pd.Timedelta | datetime.timedelta | str | None = None,
         origin: str | DatetimeLike = "start_day",
-        loffset: datetime.timedelta | str | None = None,
         restore_coord_dims: bool | None = None,
         **indexer_kwargs: str | Resampler,
     ) -> DatasetResample:
@@ -10692,10 +10695,6 @@ def resample(
             Side of each interval to treat as closed.
         label : {"left", "right"}, optional
             Side of each interval to use for labeling.
-        base : int, optional
-            For frequencies that evenly subdivide 1 day, the "origin" of the
-            aggregated intervals. For example, for "24H" frequency, base could
-            range from 0 through 23.
         origin : {'epoch', 'start', 'start_day', 'end', 'end_day'}, pd.Timestamp, datetime.datetime, np.datetime64, or cftime.datetime, default 'start_day'
             The datetime on which to adjust the grouping. The timezone of origin
             must match the timezone of the index.
@@ -10708,15 +10707,6 @@ def resample(
             - 'end_day': `origin` is the ceiling midnight of the last day
         offset : pd.Timedelta, datetime.timedelta, or str, default is None
             An offset timedelta added to the origin.
-        loffset : timedelta or str, optional
-            Offset used to adjust the resampled time labels. Some pandas date
-            offset strings are supported.
-
-            .. deprecated:: 2023.03.0
-                Following pandas, the ``loffset`` parameter is deprecated in favor
-                of using time offset arithmetic, and will be removed in a future
-                version of xarray.
-
         restore_coord_dims : bool, optional
             If True, also restore the dimension order of multi-dimensional
             coordinates.
@@ -10749,10 +10739,8 @@ def resample(
             skipna=skipna,
             closed=closed,
             label=label,
-            base=base,
             offset=offset,
             origin=origin,
-            loffset=loffset,
             restore_coord_dims=restore_coord_dims,
             **indexer_kwargs,
         )