def test_cython_right_outer_join(self):
left = a_([0, 1, 2, 1, 2, 0, 0, 1, 2, 3, 3], dtype=np.int64)
right = a_([1, 1, 0, 4, 2, 2, 1], dtype=np.int64)
max_group = 5
rs, ls = algos.left_outer_join(right, left, max_group)
exp_ls = left.argsort(kind='mergesort')
exp_rs = right.argsort(kind='mergesort')
# 0 1 1 1
exp_li = a_([0, 1, 2, 3, 4, 5, 3, 4, 5, 3, 4, 5,
# 2 2 4
6, 7, 8, 6, 7, 8, -1])
exp_ri = a_([0, 0, 0, 1, 1, 1, 2, 2, 2, 3, 3, 3,
4, 4, 4, 5, 5, 5, 6])
exp_ls = exp_ls.take(exp_li)
exp_ls[exp_li == -1] = -1
exp_rs = exp_rs.take(exp_ri)
exp_rs[exp_ri == -1] = -1
self.assert_numpy_array_equal(ls, exp_ls, check_dtype=False)
self.assert_numpy_array_equal(rs, exp_rs, check_dtype=False)
def _get_multiindex_indexer(join_keys, index, sort):
from functools import partial
# bind `sort` argument
fkeys = partial(_factorize_keys, sort=sort)
# left & right join labels and num. of levels at each location
rlab, llab, shape = map(list, zip(* map(fkeys, index.levels, join_keys)))
if sort:
rlab = list(map(np.take, rlab, index.labels))
else:
i8copy = lambda a: a.astype('i8', subok=False, copy=True)
rlab = list(map(i8copy, index.labels))
# fix right labels if there were any nulls
for i in range(len(join_keys)):
mask = index.labels[i] == -1
if mask.any():
# check if there already was any nulls at this location
# if there was, it is factorized to `shape[i] - 1`
a = join_keys[i][llab[i] == shape[i] - 1]
if a.size == 0 or not a[0] != a[0]:
shape[i] += 1
rlab[i][mask] = shape[i] - 1
# get flat i8 join keys
lkey, rkey = _get_join_keys(llab, rlab, shape, sort)
# factorize keys to a dense i8 space
lkey, rkey, count = fkeys(lkey, rkey)
return _algos.left_outer_join(lkey, rkey, count, sort=sort)
def _get_single_indexer(join_key, index, sort=False):
left_key, right_key, count = _factorize_keys(join_key, index, sort=sort)
left_indexer, right_indexer = algos.left_outer_join(
com._ensure_int64(left_key), com._ensure_int64(right_key), count, sort=sort
)
return left_indexer, right_indexer
def _get_single_indexer(join_key, index, sort=False):
left_key, right_key, count = _factorize_keys(join_key, index, sort=sort)
left_indexer, right_indexer = \
algos.left_outer_join(com._ensure_int64(left_key),
com._ensure_int64(right_key),
count, sort=sort)
return left_indexer, right_indexer
def _get_multiindex_indexer(join_keys, index, sort=False):
shape = []
labels = []
for level, key in zip(index.levels, join_keys):
llab, rlab, count = _factorize_keys(level, key, sort=False)
labels.append(rlab)
shape.append(count)
left_group_key = get_group_index(labels, shape)
right_group_key = get_group_index(index.labels, shape)
left_group_key, right_group_key, max_groups = _factorize_keys(left_group_key, right_group_key, sort=False)
left_indexer, right_indexer = algos.left_outer_join(
com._ensure_int64(left_group_key), com._ensure_int64(right_group_key), max_groups, sort=False
)
return left_indexer, right_indexer
def test_cython_right_outer_join(self):
left = a_([0, 1, 2, 1, 2, 0, 0, 1, 2, 3, 3], dtype=np.int64)
right = a_([1, 1, 0, 4, 2, 2, 1], dtype=np.int64)
max_group = 5
rs, ls = algos.left_outer_join(right, left, max_group)
exp_ls = left.argsort(kind='mergesort')
exp_rs = right.argsort(kind='mergesort')
# 0 1 1 1
exp_li = a_([
0,
1,
2,
3,
4,
5,
3,
4,
5,
3,
4,
5,
# 2 2 4
6,
7,
8,
6,
7,
8,
-1
])
exp_ri = a_([0, 0, 0, 1, 1, 1, 2, 2, 2, 3, 3, 3, 4, 4, 4, 5, 5, 5, 6])
exp_ls = exp_ls.take(exp_li)
exp_ls[exp_li == -1] = -1
exp_rs = exp_rs.take(exp_ri)
exp_rs[exp_ri == -1] = -1
self.assert_numpy_array_equal(ls, exp_ls, check_dtype=False)
self.assert_numpy_array_equal(rs, exp_rs, check_dtype=False)
def test_left_outer_join_bug():
left = np.array([0, 1, 0, 1, 1, 2, 3, 1, 0, 2, 1, 2, 0, 1, 1, 2, 3, 2, 3,
2, 1, 1, 3, 0, 3, 2, 3, 0, 0, 2, 3, 2, 0, 3, 1, 3, 0, 1,
3, 0, 0, 1, 0, 3, 1, 0, 1, 0, 1, 1, 0, 2, 2, 2, 2, 2, 0,
3, 1, 2, 0, 0, 3, 1, 3, 2, 2, 0, 1, 3, 0, 2, 3, 2, 3, 3,
2, 3, 3, 1, 3, 2, 0, 0, 3, 1, 1, 1, 0, 2, 3, 3, 1, 2, 0,
3, 1, 2, 0, 2], dtype=np.int64)
right = np.array([3, 1], dtype=np.int64)
max_groups = 4
lidx, ridx = algos.left_outer_join(left, right, max_groups, sort=False)
exp_lidx = np.arange(len(left))
exp_ridx = -np.ones(len(left))
exp_ridx[left == 1] = 1
exp_ridx[left == 3] = 0
assert(np.array_equal(lidx, exp_lidx))
assert(np.array_equal(ridx, exp_ridx))
def test_left_outer_join_bug():
left = np.array([0, 1, 0, 1, 1, 2, 3, 1, 0, 2, 1, 2, 0, 1, 1, 2, 3, 2, 3,
2, 1, 1, 3, 0, 3, 2, 3, 0, 0, 2, 3, 2, 0, 3, 1, 3, 0, 1,
3, 0, 0, 1, 0, 3, 1, 0, 1, 0, 1, 1, 0, 2, 2, 2, 2, 2, 0,
3, 1, 2, 0, 0, 3, 1, 3, 2, 2, 0, 1, 3, 0, 2, 3, 2, 3, 3,
2, 3, 3, 1, 3, 2, 0, 0, 3, 1, 1, 1, 0, 2, 3, 3, 1, 2, 0,
3, 1, 2, 0, 2], dtype=np.int64)
right = np.array([3, 1], dtype=np.int64)
max_groups = 4
lidx, ridx = _algos.left_outer_join(left, right, max_groups, sort=False)
exp_lidx = np.arange(len(left))
exp_ridx = -np.ones(len(left))
exp_ridx[left == 1] = 1
exp_ridx[left == 3] = 0
assert (np.array_equal(lidx, exp_lidx))
assert (np.array_equal(ridx, exp_ridx))
def _get_multiindex_indexer(join_keys, index, sort=False):
shape = []
labels = []
for level, key in zip(index.levels, join_keys):
llab, rlab, count = _factorize_keys(level, key, sort=False)
labels.append(rlab)
shape.append(count)
left_group_key = get_group_index(labels, shape)
right_group_key = get_group_index(index.labels, shape)
left_group_key, right_group_key, max_groups = \
_factorize_keys(left_group_key, right_group_key,
sort=False)
left_indexer, right_indexer = \
algos.left_outer_join(com._ensure_int64(left_group_key),
com._ensure_int64(right_group_key),
max_groups, sort=False)
return left_indexer, right_indexer
def _right_outer_join(x, y, max_groups):
right_indexer, left_indexer = _algos.left_outer_join(y, x, max_groups)
return left_indexer, right_indexer