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)
def dict_unique(values, expected_K, sort=False, memory=False):
if memory:
gc.collect()
before_mem = proc.get_memory_info().rss
rizer = lib.DictFactorizer()
result = rizer.unique_int64(values)
if memory:
result = proc.get_memory_info().rss - before_mem
return result
if sort:
result.sort()
assert (len(result) == expected_K)
return result
def f2():
rizer = lib.DictFactorizer()
labs, counts = rizer.factorize(xarr, sort=False)
k = len(rizer.uniques)
out = np.empty(k)
lib.group_add(out, counts, data, labs)
def algo3_sort():
rizer = lib.DictFactorizer()
labs, counts = rizer.factorize(labels, sort=True)
k = len(rizer.uniques)
out = np.empty(k)
lib.group_add(out, counts, data, labs)