Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix a case of advance indexing if the list of indices is not sorted. #96

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Fix a case of advance indexing if the list of indices is not sorted. #96

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 7 additions & 2 deletions bolt/spark/array.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
from bolt.spark.stack import StackedArray
from bolt.spark.utils import zip_with_index
from bolt.spark.statcounter import StatCounter
from bolt.utils import slicify, listify, tupleize, argpack, inshape, istransposeable, isreshapeable
from bolt.utils import slicify, listify, tupleize, argpack, inshape, istransposeable, isreshapeable, allclose


class BoltArraySpark(BoltArray):
Expand Down Expand Up @@ -536,8 +536,10 @@ def _getadvanced(self, index):
def key_check(key):
return key in key_tuples

sorted_index = argsort(index[0])

def key_func(key):
return unravel_index(key, shape)
return unravel_index(sorted_index[key], shape)

# filter records based on key targets
filtered = self._rdd.filter(lambda kv: key_check(kv[0]))
Expand Down Expand Up @@ -664,6 +666,9 @@ def __getitem__(self, index):
# if any key indices used negative steps, records are no longer ordered
if self._ordered is False or any([isinstance(s, slice) and s.step<0 for s in index[:self.split]]):
ordered = False
# if any keys are not in order the records are no longer ordered
elif any([isinstance(s, ndarray) and len(s.shape) == 1 and not allclose(array(sorted(s)), s) for s in index[:self.split]]):
ordered = False
else:
ordered = True

Expand Down
11 changes: 11 additions & 0 deletions test/spark/test_spark_getting.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,6 +77,10 @@ def test_getitem_list(sc):
assert allclose(b[[0, 1], [0, 2], [0, 3]].toarray(), x[[0, 1], [0, 2], [0, 3]])
assert allclose(b[[0, 1, 2], [0, 2, 1], [0, 3, 1]].toarray(), x[[0, 1, 2], [0, 2, 1], [0, 3, 1]])

assert allclose(b[[1, 0], [0, 1], [0, 2]].toarray(), x[[1, 0], [0, 1], [0, 2]])
assert allclose(b[[1, 0], [0, 2], [0, 3]].toarray(), x[[1, 0], [0, 2], [0, 3]])
assert allclose(b[[1, 0, 2], [0, 2, 1], [0, 3, 1]].toarray(), x[[1, 0, 2], [0, 2, 1], [0, 3, 1]])

b = array(x, sc, axis=(0,1))
assert allclose(b[[0, 1], [0, 1], [0, 2]].toarray(), x[[0, 1], [0, 1], [0, 2]])
assert allclose(b[[0, 1], [0, 2], [0, 3]].toarray(), x[[0, 1], [0, 2], [0, 3]])
Expand Down Expand Up @@ -108,6 +112,13 @@ def test_getitem_mixed(sc):
assert allclose(b[:, :, i, :].toarray(), x[:, :, i, :])
assert allclose(b[s, s, i, s].toarray(), x[s, s, i, s])

i = [1, 0]
s = slice(1, 3)
assert allclose(b[i, :, :, :].toarray(), x[i, :, :, :])
assert allclose(b[i, s, s, s].toarray(), x[i, s, s, s])
assert allclose(b[:, :, i, :].toarray(), x[:, :, i, :])
assert allclose(b[s, s, i, s].toarray(), x[s, s, i, s])

i = [1]
assert allclose(b[i, :, :, :].toarray(), x[i, :, :, :])
assert allclose(b[:, :, i, :].toarray(), x[:, :, i, :])
Expand Down