def test_group_add_bin():
# original group_add
obj = np.random.randn(10, 1)
lab = np.array([0, 0, 0, 1, 1, 1, 2, 2, 2, 2], dtype=np.int32)
cts = np.array([3, 3, 4], dtype=np.int32)
exp = np.zeros((3, 1), np.float64)
lib.group_add(exp, cts, obj, lab)
# bin-based group_add
bins = np.array([3, 6], dtype=np.int32)
out = np.zeros((3, 1), np.float64)
counts = np.zeros(len(out), dtype=np.int32)
lib.group_add_bin(out, counts, obj, bins)
assert_almost_equal(out, exp)
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 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 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)
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)
