Binning problem

[alexanderchang1]

There's a problem in the spatial binning function in that creates the wrong matrix type that then triggers an error downstream.

from popari._dataset_utils import _spatial_binning

binned_datasets = []
for dataset in transformed_datasets:
    binned_dataset = _spatial_binning(dataset, chunks=8, downsample_rate=0.2)
    print(f"Dataset downsampled from {len(dataset)} spots to {len(binned_dataset)} spots.")
    binned_datasets.append(binned_dataset)

/bgfs/alee/LO_LAB/Personal/Alexander_Chang/alc376/envs/popari_env/lib/python3.12/site-packages/scipy/sparse/_index.py:151: SparseEfficiencyWarning: Changing the sparsity structure of a csr_array is expensive. lil and dok are more efficient.
  self._set_arrayXarray(i, j, x)

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Cell In[23], line 8
      5 if isinstance(dataset.X, csr_array):
      6     # Convert dataset.X to csr_matrix
      7     dataset.X = dataset.X.tocsr()
----> 8 binned_dataset = _spatial_binning(dataset, chunks=8, downsample_rate=0.2)
      9 print(f"Dataset downsampled from {len(dataset)} spots to {len(binned_dataset)} spots.")
     10 binned_datasets.append(binned_dataset)

File /bgfs/alee/LO_LAB/Personal/Alexander_Chang/alc376/envs/popari_env/lib/python3.12/site-packages/popari/_dataset_utils.py:797, in _spatial_binning(dataset, level, chunks, downsample_rate, chunk_size, chunk_1d_density, num_jobs)
    795 binned_dataset.obsm["spatial"] = filtered_bin_coordinates
    796 binned_dataset.obs["total_transformed_counts"] = binned_dataset.X.sum(axis=1)
--> 797 binned_dataset.obsm[f"bin_assignments_{binned_dataset_name}"] = bin_assignments
    799 binned_dataset.uns["chunk_size"] = chunk_size
    800 binned_dataset.uns["chunk_1d_density"] = chunk_1d_density

File /bgfs/alee/LO_LAB/Personal/Alexander_Chang/alc376/envs/popari_env/lib/python3.12/site-packages/anndata/_core/aligned_mapping.py:216, in AlignedActual.__setitem__(self, key, value)
    215 def __setitem__(self, key: str, value: Value):
--> 216     value = self._validate_value(value, key)
    217     self._data[key] = value

File /bgfs/alee/LO_LAB/Personal/Alexander_Chang/alc376/envs/popari_env/lib/python3.12/site-packages/anndata/_core/aligned_mapping.py:279, in AxisArraysBase._validate_value(self, val, key)
    277             msg = "Index.equals and pd.testing.assert_index_equal disagree"
    278             raise AssertionError(msg)
--> 279 return super()._validate_value(val, key)

File /bgfs/alee/LO_LAB/Personal/Alexander_Chang/alc376/envs/popari_env/lib/python3.12/site-packages/anndata/_core/aligned_mapping.py:100, in AlignedMappingBase._validate_value(self, val, key)
     97     raise ValueError(msg)
     99 name = f"{self.attrname.title().rstrip('s')} {key!r}"
--> 100 return coerce_array(val, name=name, allow_df=self._allow_df)

File /bgfs/alee/LO_LAB/Personal/Alexander_Chang/alc376/envs/popari_env/lib/python3.12/site-packages/anndata/_core/storage.py:104, in coerce_array(value, name, allow_df, allow_array_like)
    102 if e is not None:
    103     msg += " (Failed to convert it to an array, see above for details.)"
--> 104 raise ValueError(msg) from e

ValueError: Obsm 'bin_assignments_MWS22-14789_level_0' needs to be of one of np.ndarray, numpy.ma.core.MaskedArray, scipy.sparse.spmatrix, awkward.Array, h5py.Dataset, zarr.Array, zappy.base.ZappyArray, anndata.experimental.[CSC,CSR]Dataset, dask.array.Array, cupy.ndarray, or cupyx.scipy.sparse.spmatrix, not <class 'scipy.sparse._csr.csr_array'>.

[alexanderchang1]

See #21 which fixes this problem

[alam-shahul]

Closing this, as the dependencies have been updated so that this is no longer an issue.