issue_comments: 953344052

Oh, hmm... I'm noticing now that IndexVariable (currently) eagerly loads data into memory, so that check will always be false for the problematic IndexVariable variable.

So perhaps a slight adjustment to is_duck_dask_array to handle xarray.Variable ?

```diff diff --git a/xarray/core/dataset.py b/xarray/core/dataset.py index 550c3587..16637574 100644 --- a/xarray/core/dataset.py +++ b/xarray/core/dataset.py @@ -4159,14 +4159,14 @@ class Dataset(DataWithCoords, DatasetArithmetic, Mapping): # Dask arrays don't support assignment by index, which the fast unstack # function requires. # https://github.com/pydata/xarray/pull/4746#issuecomment-753282125 - any(is_duck_dask_array(v.data) for v in self.variables.values()) + any(is_duck_dask_array(v) for v in self.variables.values()) # Sparse doesn't currently support (though we could special-case # it) # https://github.com/pydata/sparse/issues/422 - or any( - isinstance(v.data, sparse_array_type) - for v in self.variables.values() - ) + # or any( + # isinstance(v.data, sparse_array_type) + # for v in self.variables.values() + # ) or sparse # Until https://github.com/pydata/xarray/pull/4751 is resolved, # we check explicitly whether it's a numpy array. Once that is @@ -4177,9 +4177,9 @@ class Dataset(DataWithCoords, DatasetArithmetic, Mapping): # # or any( # # isinstance(v.data, pint_array_type) for v in self.variables.values() # # ) - or any( - not isinstance(v.data, np.ndarray) for v in self.variables.values() - ) + # or any( + # not isinstance(v.data, np.ndarray) for v in self.variables.values() + # ) ): result = result._unstack_full_reindex(dim, fill_value, sparse) else: diff --git a/xarray/core/pycompat.py b/xarray/core/pycompat.py index d1649235..e9669105 100644 --- a/xarray/core/pycompat.py +++ b/xarray/core/pycompat.py @@ -44,6 +44,12 @@ class DuckArrayModule:

def is_duck_dask_array(x): + from xarray.core.variable import IndexVariable, Variable + if isinstance(x, IndexVariable): + return False + elif isinstance(x, Variable): + x = x.data + if DuckArrayModule("dask").available: from dask.base import is_dask_collection ```

That's completely ignoring the accesses to v.data for the sparse and pint checks, which don't look quite as easy to solve.