def test_create_dataset_from_dataset(tmp_path):
from_h5_path = tmp_path / 'from.h5'
to_h5_path = tmp_path / 'to.h5'
sparse_matrix = ss.csr_matrix([[0, 1, 0], [0, 0, 1], [0, 0, 0], [1, 1, 0]],
dtype=np.float64)
with h5py.File(from_h5_path) as from_h5f:
from_dset = from_h5f.create_dataset('sparse/matrix',
data=sparse_matrix)
with h5py.File(to_h5_path) as to_h5f:
to_h5f.create_dataset('sparse/matrix', data=from_dset)
assert (to_h5f['sparse/matrix'].value != sparse_matrix).size == 0
def test_create_and_read_dataset(tmp_path):
h5_path = tmp_path / 'test.h5'
sparse_matrix = ss.csr_matrix([[0, 1, 0], [0, 0, 1], [0, 0, 0], [1, 1, 0]],
dtype=np.float64)
with h5py.File(h5_path) as h5f:
h5f.create_dataset('sparse/matrix', data=sparse_matrix)
with h5py.File(h5_path) as h5f:
assert (h5f['sparse']['matrix'][1:3] != sparse_matrix[1:3]).size == 0
assert (h5f['sparse']['matrix'][2:] != sparse_matrix[2:]).size == 0
assert (h5f['sparse']['matrix'][:2] != sparse_matrix[:2]).size == 0
assert (h5f['sparse']['matrix'][-2:] != sparse_matrix[-2:]).size == 0
assert (h5f['sparse']['matrix'][:-2] != sparse_matrix[:-2]).size == 0
assert (h5f['sparse']['matrix'].value != sparse_matrix).size == 0
def test_create_dataset_from_dataset():
from_h5_path = mkstemp(suffix=".h5")[1]
to_h5_path = mkstemp(suffix=".h5")[1]
sparse_matrix = ss.csr_matrix([[0, 1, 0], [0, 0, 1], [0, 0, 0], [1, 1, 0]],
dtype=np.float64)
with h5py.File(from_h5_path) as from_h5f:
from_dset = from_h5f.create_dataset('sparse/matrix',
data=sparse_matrix)
with h5py.File(to_h5_path) as to_h5f:
to_h5f.create_dataset('sparse/matrix', data=from_dset)
assert (to_h5f['sparse/matrix'].value != sparse_matrix).size == 0
os.remove(from_h5_path)
os.remove(to_h5_path)
def test_create_and_read_dataset():
h5_path = mkstemp(suffix=".h5")[1]
sparse_matrix = ss.csr_matrix([[0, 1, 0], [0, 0, 1], [0, 0, 0], [1, 1, 0]],
dtype=np.float64)
with h5py.File(h5_path) as h5f:
h5f.create_dataset('sparse/matrix', data=sparse_matrix)
with h5py.File(h5_path) as h5f:
assert (h5f['sparse']['matrix'][1:3] != sparse_matrix[1:3]).size == 0
assert (h5f['sparse']['matrix'][2:] != sparse_matrix[2:]).size == 0
assert (h5f['sparse']['matrix'][:2] != sparse_matrix[:2]).size == 0
assert (h5f['sparse']['matrix'][-2:] != sparse_matrix[-2:]).size == 0
assert (h5f['sparse']['matrix'][:-2] != sparse_matrix[:-2]).size == 0
assert (h5f['sparse']['matrix'].value != sparse_matrix).size == 0
os.remove(h5_path)
def test_dataset_append(tmp_path):
h5_path = tmp_path / 'test.h5'
sparse_matrix = ss.csr_matrix([[0, 1, 0], [0, 0, 1], [0, 0, 0], [1, 1, 0]],
dtype=np.float64)
to_append = ss.csr_matrix([[0, 1, 1], [1, 0, 0]], dtype=np.float64)
appended_matrix = ss.vstack((sparse_matrix, to_append))
with h5py.File(h5_path) as h5f:
h5f.create_dataset('matrix', data=sparse_matrix, chunks=(100000, ))
h5f['matrix'].append(to_append)
assert (h5f['matrix'].value != appended_matrix).size == 0
def read_h5(self, input_file):
h5 = h5py.File(input_file, 'r')
self.data = h5['/GRCh38/data']
self.indices = h5['/GRCh38/indices']
self.indptr = h5['/GRCh38/indptr']
self.genes = h5['/GRCh38/genes']
self.barcodes = h5['/GRCh38/barcodes']
self.shape = h5['/GRCh38/shape']
self.gene_names = h5['/GRCh38/gene_names']
csr_m = csr_matrix((self.data, self.indices, self.indptr),
shape=(self.shape[1], self.shape[0]))
self.trans_m = np.transpose(csr_m)
def getAnnData(input_file):
h5 = h5py.File(input_file,'r')
data = h5['/GRCh38/data']
indices = h5['/GRCh38/indices']
barcodes = h5['/GRCh38/barcodes']
indptr = h5['/GRCh38/indptr']
genes = h5['/GRCh38/genes']
gene_names = h5['/GRCh38/gene_names']
shape = h5['/GRCh38/shape']
X = csr_matrix((data,indices,indptr),shape=(shape.value[1],shape.value[0]),dtype='float32')
adata = AnnData(X,
obs=pd.DataFrame(index=barcodes.value),
var=pd.DataFrame(index=genes.value),
dtype=X.dtype.name,
filemode=True)
return adata
def getNormAnnData(input_file, normalize_type):
h5 = h5py.File(input_file, 'r')
data = h5['/GRCh38/data']
indices = h5['/GRCh38/indices']
barcodes = h5['/GRCh38/barcodes']
indptr = h5['/GRCh38/indptr']
genes = h5['/GRCh38/genes']
gene_names = h5['/GRCh38/gene_names']
shape = h5['/GRCh38/shape']
if normalize_type == "rank":
zero_value = h5['/GRCh38/zero_value']
else:
size_factor = h5['/GRCh38/size_factor'][:]
X = csr_matrix((data, indices, indptr),
shape=(shape.value[1], shape.value[0]),
dtype='float32')
if normalize_type == "rank":
X = X.toarray()
for i in range(shape.value[1]):
for j in range(shape.value[0]):
if abs(X[i][j] - 0) < 1e-5:
X[i][j] = zero_value[i]
adata = AnnData(X,
obs=pd.DataFrame(index=barcodes.value),
var=pd.DataFrame(index=genes.value),
dtype=X.dtype.name,
filemode=True)
if normalize_type == "rank":
return adata
else:
return adata, size_factor
