add dimension check to PointWiseDownscaler inputs #38
Description
currently if member_id is an additional dimension (which is easy to have happen if you grab multiple ensemble members from CMIP6 when searching the catalog), the PointwiseDownscaler fails with a ValueError, ValueError: dimensions {'member_id'} do not exist. Expected one or more of ('time', 'lat', 'lon'), coming from a dask backend issue. I believe this also occurs with any other extra dims present in the input data (e.g. height). We should probably add a check with a more informative error message for extra dims that should be removed. Including the traceback below for additional ref.
ValueError Traceback (most recent call last)
<ipython-input-81-1210dae294dd> in <module>
----> 1 predicted = model.predict(holdout_subset).load()
/opt/conda/lib/python3.7/site-packages/xarray/core/dataarray.py in load(self, **kwargs)
812 dask.array.compute
813 """
--> 814 ds = self._to_temp_dataset().load(**kwargs)
815 new = self._from_temp_dataset(ds)
816 self._variable = new._variable
/opt/conda/lib/python3.7/site-packages/xarray/core/dataset.py in load(self, **kwargs)
656
657 # evaluate all the dask arrays simultaneously
--> 658 evaluated_data = da.compute(*lazy_data.values(), **kwargs)
659
660 for k, data in zip(lazy_data, evaluated_data):
/opt/conda/lib/python3.7/site-packages/dask/base.py in compute(*args, **kwargs)
434 keys = [x.__dask_keys__() for x in collections]
435 postcomputes = [x.__dask_postcompute__() for x in collections]
--> 436 results = schedule(dsk, keys, **kwargs)
437 return repack([f(r, *a) for r, (f, a) in zip(results, postcomputes)])
438
/opt/conda/lib/python3.7/site-packages/distributed/client.py in get(self, dsk, keys, restrictions, loose_restrictions, resources, sync, asynchronous, direct, retries, priority, fifo_timeout, actors, **kwargs)
2570 should_rejoin = False
2571 try:
-> 2572 results = self.gather(packed, asynchronous=asynchronous, direct=direct)
2573 finally:
2574 for f in futures.values():
/opt/conda/lib/python3.7/site-packages/distributed/client.py in gather(self, futures, errors, direct, asynchronous)
1870 direct=direct,
1871 local_worker=local_worker,
-> 1872 asynchronous=asynchronous,
1873 )
1874
/opt/conda/lib/python3.7/site-packages/distributed/client.py in sync(self, func, asynchronous, callback_timeout, *args, **kwargs)
765 else:
766 return sync(
--> 767 self.loop, func, *args, callback_timeout=callback_timeout, **kwargs
768 )
769
/opt/conda/lib/python3.7/site-packages/distributed/utils.py in sync(loop, func, callback_timeout, *args, **kwargs)
332 if error[0]:
333 typ, exc, tb = error[0]
--> 334 raise exc.with_traceback(tb)
335 else:
336 return result[0]
/opt/conda/lib/python3.7/site-packages/distributed/utils.py in f()
316 if callback_timeout is not None:
317 future = gen.with_timeout(timedelta(seconds=callback_timeout), future)
--> 318 result[0] = yield future
319 except Exception as exc:
320 error[0] = sys.exc_info()
/opt/conda/lib/python3.7/site-packages/tornado/gen.py in run(self)
733
734 try:
--> 735 value = future.result()
736 except Exception:
737 exc_info = sys.exc_info()
/opt/conda/lib/python3.7/site-packages/distributed/client.py in _gather(self, futures, errors, direct, local_worker)
1726 exc = CancelledError(key)
1727 else:
-> 1728 raise exception.with_traceback(traceback)
1729 raise exc
1730 if errors == "skip":
/opt/conda/lib/python3.7/site-packages/xarray/core/parallel.py in _wrapper()
285 ]
286
--> 287 result = func(*converted_args, **kwargs)
288
289 # check all dims are present
/opt/conda/lib/python3.7/site-packages/skdownscale/pointwise_models/core.py in _fit_wrapper()
/opt/conda/lib/python3.7/site-packages/xarray/core/dataarray.py in __getitem__()
641 else:
642 # xarray-style array indexing
--> 643 return self.isel(indexers=self._item_key_to_dict(key))
644
645 def __setitem__(self, key: Any, value: Any) -> None:
/opt/conda/lib/python3.7/site-packages/xarray/core/dataarray.py in isel()
1051 # lists, or zero or one-dimensional np.ndarray's
1052
-> 1053 variable = self._variable.isel(indexers, missing_dims=missing_dims)
1054
1055 coords = {}
/opt/conda/lib/python3.7/site-packages/xarray/core/variable.py in isel()
1069 indexers = either_dict_or_kwargs(indexers, indexers_kwargs, "isel")
1070
-> 1071 indexers = drop_dims_from_indexers(indexers, self.dims, missing_dims)
1072
1073 key = tuple(indexers.get(dim, slice(None)) for dim in self.dims)
/opt/conda/lib/python3.7/site-packages/xarray/core/utils.py in drop_dims_from_indexers()
765 if invalid:
766 raise ValueError(
--> 767 f"dimensions {invalid} do not exist. Expected one or more of {dims}"
768 )
769
ValueError: dimensions {'member_id'} do not exist. Expected one or more of ('time', 'lat', 'lon')