def get_compressed_ids(labels, sizes):
# no overflow
if com._long_prod(sizes) < 2**63:
group_index = get_group_index(labels, sizes)
comp_index, obs_ids = _compress_group_index(group_index)
else:
n = len(labels[0])
mask = np.zeros(n, dtype=bool)
for v in labels:
mask |= v < 0
while com._long_prod(sizes) >= 2**63:
i = len(sizes)
while com._long_prod(sizes[:i]) >= 2**63:
i -= 1
rem_index, rem_ids = get_compressed_ids(labels[:i], sizes[:i])
sizes = [len(rem_ids)] + sizes[i:]
labels = [rem_index] + labels[i:]
return get_compressed_ids(labels, sizes)
return comp_index, obs_ids
def get_compressed_ids(labels, sizes):
# no overflow
if com._long_prod(sizes) < 2 ** 63:
group_index = get_group_index(labels, sizes)
comp_index, obs_ids = _compress_group_index(group_index)
else:
n = len(labels[0])
mask = np.zeros(n, dtype=bool)
for v in labels:
mask |= v < 0
while com._long_prod(sizes) >= 2 ** 63:
i = len(sizes)
while com._long_prod(sizes[:i]) >= 2 ** 63:
i -= 1
rem_index, rem_ids = get_compressed_ids(labels[:i], sizes[:i])
sizes = [len(rem_ids)] + sizes[i:]
labels = [rem_index] + labels[i:]
return get_compressed_ids(labels, sizes)
return comp_index, obs_ids
