def test_intersect1d_a(self) -> None:
a1 = np.array([3, 2, 1])
a2 = np.array(['3', '2', '1'])
self.assertEqual(len(intersect1d(a1, a2)), 0)
self.assertEqual(
len(intersect1d(np.array([1, 2, 3]), np.array([None, False]))), 0)
self.assertEqual(
set(intersect1d(np.array(['a', 'b', 'c']), np.array(['aa', 'bbb', 'c']))),
{'c'}
)
def test_intersect1d(self, arrays: tp.Sequence[np.ndarray]) -> None:
post = util.intersect1d(arrays[0], arrays[1], assume_unique=False)
self.assertTrue(post.ndim == 1)
# nan values in complex numbers make direct comparison tricky
self.assertTrue(len(post) == len(set(arrays[0]) & set(arrays[1])))
if (post.dtype.kind not in ('O', 'M', 'm', 'c', 'f')
and not np.isnan(post).any()):
self.assertTrue(set(post) == (set(arrays[0]) & set(arrays[1])))
def test_intersect1d_b(self):
# long way of
a1 = np.empty(4, dtype=object)
a1[:] = [(0, 0), (0, 1), (0, 2), (0, 3)]
a2 = np.empty(3, dtype=object)
a2[:] = [(0, 1), (0, 3), (4, 5)]
# must get an array of tuples back
post = intersect1d(a1, a2)
self.assertEqual(post.tolist(), [(0, 1), (0, 3)])
def from_correspondence(cls, src_index: 'Index',
dst_index: 'Index') -> 'IndexCorrespondence':
'''
Return an IndexCorrespondence instance from the correspondence of two Index or IndexHierarchy objects.
'''
mixed_depth = False
if src_index.depth == dst_index.depth:
depth = src_index.depth
else:
# if dimensions are mixed, the only way there can be a match is if the 1D index is of object type (so it can hold a tuple); otherwise, there can be no matches;
if src_index.depth == 1 and src_index.values.dtype.kind == 'O':
depth = dst_index.depth
mixed_depth = True
elif dst_index.depth == 1 and dst_index.values.dtype.kind == 'O':
depth = src_index.depth
mixed_depth = True
else:
depth = 0
# need to use lower level array methods go get intersection, rather than Index methods, as need arrays, not Index objects
if depth == 1:
# NOTE: this can fail in some cases: comparing two object arrays with NaNs and strings.
common_labels = intersect1d(src_index.values,
dst_index.values,
assume_unique=True)
has_common = len(common_labels) > 0
assert not mixed_depth
elif depth > 1:
# if either values arrays are object, we have to covert all values to tuples
common_labels = intersect2d(src_index.values,
dst_index.values,
assume_unique=True)
if mixed_depth:
# when mixed, on the 1D index we have to use loc_to_iloc with tuples
common_labels = list(array2d_to_tuples(common_labels))
has_common = len(common_labels) > 0
else:
has_common = False
size = len(dst_index.values)
# either a reordering or a subset
if has_common:
if len(common_labels) == len(dst_index):
# use new index to retain order
values_dst = dst_index.values
if values_dst.dtype == DTYPE_BOOL:
# if the index values are a Boolean array, loc_to_iloc will try to do a Boolean selection, which is incorrect. Using a list avoids this problem.
iloc_src = src_index.loc_to_iloc(values_dst.tolist())
else:
iloc_src = src_index.loc_to_iloc(values_dst)
iloc_dst = np.arange(size)
return cls(has_common=has_common,
is_subset=True,
iloc_src=iloc_src,
iloc_dst=iloc_dst,
size=size)
# these will be equal sized
iloc_src = src_index.loc_to_iloc(common_labels)
iloc_dst = dst_index.loc_to_iloc(common_labels)
# if iloc_src.dtype != int:
# import ipdb; ipdb.set_trace()
return cls(has_common=has_common,
is_subset=False,
iloc_src=iloc_src,
iloc_dst=iloc_dst,
size=size)
return cls(has_common=has_common,
is_subset=False,
iloc_src=None,
iloc_dst=None,
size=size)