def convert(
input,
output,
chunk_size=16 * 1024 * 1024,
genome=None,
overwrite=False
):
input_path, input_ext = splitext(input)
output_path, output_ext = splitext(output)
print('converting: %s to %s' % (input, output))
if input_ext == '.h5' or input_ext == '.loom':
if output_ext == '.zarr':
# Convert 10x (HDF5) to Zarr
source = h5py.File(input)
zarr.tree(source)
store = zarr.DirectoryStore(output)
dest = zarr.group(store=store, overwrite=overwrite)
# following fails if without_attrs=False (the default), possibly related to https://github.com/h5py/h5py/issues/973
zarr.copy_all(source, dest, log=sys.stdout, without_attrs=True)
zarr.tree(dest)
elif output_ext == '.h5ad':
if not genome:
keys = list(h5py.File(input).keys())
if len(keys) == 1:
genome = keys[0]
else:
raise Exception(
'Set --genome flag when converting from 10x HDF5 (.h5) to Anndata HDF5 (.h5ad); top-level groups in file %s: %s'
% (input, ','.join(keys))
)
adata = read_10x_h5(input, genome=genome)
# TODO: respect overwrite flag
adata.write(output)
elif input_ext == '.h5ad':
adata = read_h5ad(input, backed='r')
(r, c) = adata.shape
chunks = (getsize(input) - 1) / chunk_size + 1
chunk_size = (r - 1) / chunks + 1
if output_ext == '.zarr':
print('converting %s (%dx%d) to %s in %d chunks (%d rows each)' % (input, r, c, output, chunks, chunk_size))
# TODO: respect overwrite flag
adata.write_zarr(
make_store(output),
chunks=(chunk_size, c)
)
else:
raise Exception('Unrecognized output extension: %s' % output_ext)
else:
raise Exception('Unrecognized input extension: %s' % input_ext)
def test_tree(zarr_version):
kwargs = _init_creation_kwargs(zarr_version)
g1 = zarr.group(**kwargs)
g1.create_group('foo')
g3 = g1.create_group('bar')
g3.create_group('baz')
g5 = g3.create_group('qux')
g5.create_dataset('baz', shape=100, chunks=10)
assert repr(zarr.tree(g1)) == repr(g1.tree())
assert str(zarr.tree(g1)) == str(g1.tree())
def _open_session(self, mode="r"):
try:
z = zarr.open(self.root_dir, mode=mode) # don't create it
except ValueError:
# nothing to open here, unlikely a zarr dataset
return
else:
self._handle = z[self.path]
# preview the internal structure
if logger.getEffectiveLevel() <= logging.DEBUG:
zarr.tree(self._handle)
def show_meta(input):
input_path, input_ext = splitext(input)
if input_ext == ".h5" or input_ext == ".h5ad" or input_ext == ".loom":
file = h5py.File(input, "r")
return zarr.tree(file)
elif input_ext == ".zarr":
store = make_store(input)
file = zarr.open(store)
return tree(file)
import h5py
import sys
import zarr
# Convert 10x (HDF5) to Zarr
source = h5py.File("/Downloads/1M_neurons_filtered_gene_bc_matrices_h5.h5")
zarr.tree(source)
store = zarr.DirectoryStore('data/10x.zarr')
dest = zarr.group(store=store, overwrite=True)
# following fails if without_attrs=False (the default), possibly related to https://github.com/h5py/h5py/issues/973
zarr.copy_all(source, dest, log=sys.stdout, without_attrs=True)
import zarr from constants import ZARR_DB root = zarr.open(ZARR_DB) # compare with size of plink file root.info root['/chromosome-1/calls'].info zarr.tree(root)