Merge remote-tracking branch 'upstream/master' into fix/whats-new

* upstream/master:
  Added fill_value for unstack (pydata#3541)

Author: dcherian

doc/whats-new.rst

@@ -40,6 +40,11 @@ New Features
 
 - Added the ``max_gap`` kwarg to :py:meth:`DataArray.interpolate_na` and
   :py:meth:`Dataset.interpolate_na`. This controls the maximum size of the data
+- Added the ``fill_value`` option to :py:meth:`~xarray.DataArray.unstack` and
+  :py:meth:`~xarray.Dataset.unstack` (:issue:`3518`).
+  By `Keisuke Fujii <https://github.com/fujiisoup>`_.
+- Added the ``max_gap`` kwarg to :py:meth:`~xarray.DataArray.interpolate_na` and
+  :py:meth:`~xarray.Dataset.interpolate_na`. This controls the maximum size of the data
   gap that will be filled by interpolation. By `Deepak Cherian <https://github.com/dcherian>`_.
 - :py:meth:`Dataset.drop_sel` & :py:meth:`DataArray.drop_sel` have been added for dropping labels.
   :py:meth:`Dataset.drop_vars` & :py:meth:`DataArray.drop_vars` have been added for 

xarray/core/dataarray.py

@@ -1726,7 +1726,9 @@ def stack(
         return self._from_temp_dataset(ds)
 
     def unstack(
-        self, dim: Union[Hashable, Sequence[Hashable], None] = None
+        self,
+        dim: Union[Hashable, Sequence[Hashable], None] = None,
+        fill_value: Any = dtypes.NA,
     ) -> "DataArray":
         """
         Unstack existing dimensions corresponding to MultiIndexes into
@@ -1739,6 +1741,7 @@ def unstack(
         dim : hashable or sequence of hashable, optional
             Dimension(s) over which to unstack. By default unstacks all
             MultiIndexes.
+        fill_value: value to be filled. By default, np.nan
 
         Returns
         -------
@@ -1770,7 +1773,7 @@ def unstack(
         --------
         DataArray.stack
         """
-        ds = self._to_temp_dataset().unstack(dim)
+        ds = self._to_temp_dataset().unstack(dim, fill_value)
         return self._from_temp_dataset(ds)
 
     def to_unstacked_dataset(self, dim, level=0):

xarray/core/dataset.py

@@ -3333,7 +3333,7 @@ def ensure_stackable(val):
 
         return data_array
 
-    def _unstack_once(self, dim: Hashable) -> "Dataset":
+    def _unstack_once(self, dim: Hashable, fill_value) -> "Dataset":
         index = self.get_index(dim)
         index = index.remove_unused_levels()
         full_idx = pd.MultiIndex.from_product(index.levels, names=index.names)
@@ -3342,7 +3342,7 @@ def _unstack_once(self, dim: Hashable) -> "Dataset":
         if index.equals(full_idx):
             obj = self
         else:
-            obj = self.reindex({dim: full_idx}, copy=False)
+            obj = self.reindex({dim: full_idx}, copy=False, fill_value=fill_value)
 
         new_dim_names = index.names
         new_dim_sizes = [lev.size for lev in index.levels]
@@ -3368,7 +3368,11 @@ def _unstack_once(self, dim: Hashable) -> "Dataset":
             variables, coord_names=coord_names, indexes=indexes
         )
 
-    def unstack(self, dim: Union[Hashable, Iterable[Hashable]] = None) -> "Dataset":
+    def unstack(
+        self,
+        dim: Union[Hashable, Iterable[Hashable]] = None,
+        fill_value: Any = dtypes.NA,
+    ) -> "Dataset":
         """
         Unstack existing dimensions corresponding to MultiIndexes into
         multiple new dimensions.
@@ -3380,6 +3384,7 @@ def unstack(self, dim: Union[Hashable, Iterable[Hashable]] = None) -> "Dataset":
         dim : Hashable or iterable of Hashable, optional
             Dimension(s) over which to unstack. By default unstacks all
             MultiIndexes.
+        fill_value: value to be filled. By default, np.nan
 
         Returns
         -------
@@ -3417,7 +3422,7 @@ def unstack(self, dim: Union[Hashable, Iterable[Hashable]] = None) -> "Dataset":
 
         result = self.copy(deep=False)
         for dim in dims:
-            result = result._unstack_once(dim)
+            result = result._unstack_once(dim, fill_value)
         return result
 
     def update(self, other: "CoercibleMapping", inplace: bool = None) -> "Dataset":

xarray/tests/test_dataset.py

@@ -2794,6 +2794,23 @@ def test_unstack_errors(self):
         with raises_regex(ValueError, "do not have a MultiIndex"):
             ds.unstack("x")
 
+    def test_unstack_fill_value(self):
+        ds = xr.Dataset(
+            {"var": (("x",), np.arange(6))},
+            coords={"x": [0, 1, 2] * 2, "y": (("x",), ["a"] * 3 + ["b"] * 3)},
+        )
+        # make ds incomplete
+        ds = ds.isel(x=[0, 2, 3, 4]).set_index(index=["x", "y"])
+        # test fill_value
+        actual = ds.unstack("index", fill_value=-1)
+        expected = ds.unstack("index").fillna(-1).astype(np.int)
+        assert actual["var"].dtype == np.int
+        assert_equal(actual, expected)
+
+        actual = ds["var"].unstack("index", fill_value=-1)
+        expected = ds["var"].unstack("index").fillna(-1).astype(np.int)
+        assert actual.equals(expected)
+
     def test_stack_unstack_fast(self):
         ds = Dataset(
             {