def _factorize_int64(left_index, right_index, sort=True):
rizer = lib.Int64Factorizer(max(len(left_index), len(right_index)))
llab, _ = rizer.factorize(left_index)
rlab, _ = rizer.factorize(right_index)
if sort:
llab, rlab = _sort_labels(np.array(rizer.uniques), llab, rlab)
return llab, rlab, rizer.get_count()
def _factorize_int64(left_index, right_index, sort=True):
rizer = lib.Int64Factorizer(max(len(left_index), len(right_index)))
# 32-bit compatibility
if left_index.dtype != np.int64: # pragma: no cover
left_index = left_index.astype('i8')
if right_index.dtype != np.int64: # pragma: no cover
right_index = right_index.astype('i8')
llab, _ = rizer.factorize(left_index)
rlab, _ = rizer.factorize(right_index)
if sort:
llab, rlab = _sort_labels(np.array(rizer.uniques), llab, rlab)
return llab, rlab, rizer.get_count()
def algo4():
rizer = lib.DictFactorizer()
labs1, _ = rizer.factorize(labels, sort=False)
k1 = len(rizer.uniques)
rizer = lib.DictFactorizer()
labs2, _ = rizer.factorize(labels2, sort=False)
k2 = len(rizer.uniques)
group_id = labs1 * k2 + labs2
max_group = k1 * k2
if max_group > 1e6:
rizer = lib.Int64Factorizer(len(group_id))
group_id, _ = rizer.factorize(group_id.astype('i8'), sort=True)
max_group = len(rizer.uniques)
out = np.empty(max_group)
counts = np.zeros(max_group, dtype='i4')
lib.group_add(out, counts, data, group_id)