def test_de_backed(sparse, file_format, tmp_path):
fs = fsspec.filesystem('file')
adata = get_example_data(sparse)
output_dir = str(tmp_path)
prepare_data = PrepareData(datasets=[adata],
output=output_dir,
output_format=file_format)
prepare_data.execute()
if file_format == 'parquet':
reader = ParquetDataset()
elif file_format == 'zarr':
reader = ZarrDataset()
batch_size = 30
obs_field = 'sc_groups'
nfeatures = adata.shape[1]
def get_batch_fn(i):
end = min(nfeatures, i + batch_size)
return reader.read_dataset(filesystem=fs,
path=output_dir,
dataset=dict(id=''),
keys=dict(X=[slice(i, end)]))
results = DE(series=adata.obs[obs_field],
nfeatures=nfeatures,
batch_size=batch_size,
get_batch_fn=get_batch_fn,
base=get_base(adata),
one_vs_rest=True)
diff_results(adata, obs_field, results.pair2results[0])
def test_de_2_groups(sparse):
adata = get_example_data(sparse)
batch_size = 3
obs_field = 'sc_groups'
nfeatures = adata.shape[1]
get_batch_fn = lambda i: adata[:, i:min(nfeatures, i + batch_size)]
results = DE(series=adata.obs[obs_field],
nfeatures=nfeatures,
batch_size=batch_size,
get_batch_fn=get_batch_fn,
base=get_base(adata),
one_vs_rest=True)
diff_results(adata, obs_field, results.pair2results[0])
def test_de_4_groups(sparse):
adata1 = get_example_data(sparse)
adata2 = get_example_data(sparse)
adata2.obs['sc_groups'] = adata2.obs['sc_groups'].replace({0: 2, 1: 3})
adata = anndata.concat((adata1, adata2))
adata.obs_names_make_unique()
batch_size = 3
obs_field = 'sc_groups'
adata.obs[obs_field] = adata.obs[obs_field].astype('category')
nfeatures = adata.shape[1]
get_batch_fn = lambda i: adata[:, i:min(nfeatures, i + batch_size)]
de = DE(series=adata.obs[obs_field],
nfeatures=nfeatures,
batch_size=batch_size,
get_batch_fn=get_batch_fn,
base=get_base(adata))
for i in range(4):
diff_results(adata, obs_field, de.pair2results[i], str(i))