Skip to content

flox.xarray.xarray_reduce() computes lazily but cannot be pulled down #405

Closed
@charlie-becker

Description

@charlie-becker

I'm attempting to run a similar example shown in the xarray flox demo.

Everything appears to compute lazily, but fails when I try to pull the entire array down. Certain subsets can be pulled down, but over certain chunks, it seems to fail.

xr.set_options(use_flox=True, use_numbagg=True)
county_mean = fxarray.xarray_reduce(
    ds_subset,
    aligned_counties,
    func="mean",
    expected_groups=(county_ids,),
    method="cohorts")
county_mean

Screenshot 2024-11-13 at 5 34 39 PM

# some slices work
county_mean.isel(time=slice(0, 2), GEOID=slice(300, 310)).values

array([[1.02196488, 1.44516348, 0.75965351, 1.08162497, 1.42856831,
        0.57487382, 1.25551675, 1.10393899, 0.64814745, 0.87742339],
       [1.02451059, 1.44312821, 0.75893909, 1.08319094, 1.4299601 ,
        0.57509014, 1.25875236, 1.11137815, 0.64105671, 0.87635005]])
# others don't (including the entire array at once)
county_mean.values

IndexError                                Traceback (most recent call last)
File /glade/work/cbecker/conda-envs/cat/lib/python3.11/site-packages/dask/array/chunk.py:421, in getitem(obj, index)
    420 try:
--> 421     result = obj[index]
    422 except IndexError as e:

IndexError: index 1 is out of bounds for axis 1 with size 1

The above exception was the direct cause of the following exception:

ValueError                                Traceback (most recent call last)
Cell In[63], line 2
      1 # others don't (including the entire array at once)
----> 2 county_mean.values

File /glade/work/cbecker/conda-envs/cat/lib/python3.11/site-packages/xarray/core/dataarray.py:811, in DataArray.values(self)
    798 @property
    799 def values(self) -> np.ndarray:
    800     """
    801     The array's data converted to numpy.ndarray.
    802 
   (...)
    809     to this array may be reflected in the DataArray as well.
    810     """
--> 811     return self.variable.values

File /glade/work/cbecker/conda-envs/cat/lib/python3.11/site-packages/xarray/core/variable.py:554, in Variable.values(self)
    551 @property
    552 def values(self) -> np.ndarray:
    553     """The variable's data as a numpy.ndarray"""
--> 554     return _as_array_or_item(self._data)

File /glade/work/cbecker/conda-envs/cat/lib/python3.11/site-packages/xarray/core/variable.py:352, in _as_array_or_item(data)
    338 def _as_array_or_item(data):
    339     """Return the given values as a numpy array, or as an individual item if
    340     it's a 0d datetime64 or timedelta64 array.
    341 
   (...)
    350     TODO: remove this (replace with np.asarray) once these issues are fixed
    351     """
--> 352     data = np.asarray(data)
    353     if data.ndim == 0:
    354         if data.dtype.kind == "M":

File /glade/work/cbecker/conda-envs/cat/lib/python3.11/site-packages/dask/array/core.py:1746, in Array.__array__(self, dtype, **kwargs)
   1745 def __array__(self, dtype=None, **kwargs):
-> 1746     x = self.compute()
   1747     if dtype and x.dtype != dtype:
   1748         x = x.astype(dtype)

File /glade/work/cbecker/conda-envs/cat/lib/python3.11/site-packages/dask/base.py:372, in DaskMethodsMixin.compute(self, **kwargs)
    348 def compute(self, **kwargs):
    349     """Compute this dask collection
    350 
    351     This turns a lazy Dask collection into its in-memory equivalent.
   (...)
    370     dask.compute
    371     """
--> 372     (result,) = compute(self, traverse=False, **kwargs)
    373     return result

File /glade/work/cbecker/conda-envs/cat/lib/python3.11/site-packages/dask/base.py:660, in compute(traverse, optimize_graph, scheduler, get, *args, **kwargs)
    657     postcomputes.append(x.__dask_postcompute__())
    659 with shorten_traceback():
--> 660     results = schedule(dsk, keys, **kwargs)
    662 return repack([f(r, *a) for r, (f, a) in zip(results, postcomputes)])

File /glade/work/cbecker/conda-envs/cat/lib/python3.11/site-packages/dask/array/_shuffle.py:305, in _getitem(obj, index)
    304 def _getitem(obj, index):
--> 305     return getitem(obj, index[1])

File /glade/work/cbecker/conda-envs/cat/lib/python3.11/site-packages/dask/array/chunk.py:423, in getitem(obj, index)
    421     result = obj[index]
    422 except IndexError as e:
--> 423     raise ValueError(
    424         "Array chunk size or shape is unknown. "
    425         "Possible solution with x.compute_chunk_sizes()"
    426     ) from e
    428 try:
    429     if not result.flags.owndata and obj.size >= 2 * result.size:

ValueError: Array chunk size or shape is unknown. Possible solution with x.compute_chunk_sizes()

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions