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 = lib.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 = \
lib.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 = lib.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_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 = lib.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 = \
lib.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_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 = lib.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 _right_outer_join(x, y, max_groups):
right_indexer, left_indexer = lib.left_outer_join(y, x, max_groups)
return left_indexer, right_indexer
def _right_outer_join(x, y, max_groups):
right_indexer, left_indexer = lib.left_outer_join(y, x, max_groups)
return left_indexer, right_indexer
