Skip to content

fix: fix match score #32

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

Merged
hanxiao merged 1 commit into from
Jan 11, 2022
Merged

fix: fix match score #32

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
fix: fix match score
  • Loading branch information
Joan Fontanals Martinez committed Jan 11, 2022
commit 8dcd33eea8b506cfb0f47b6bf64df79a3814ee8b
2 changes: 1 addition & 1 deletion docarray/array/mixins/match.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -121,7 +121,7 @@ def match(
if only_id:
d = Document(id=rhv[_id].id)
else:
d = rhv[int(_id)] # type: Document
d = Document(rhv[int(_id)], copy=True) # type: Document

if d.id in lhv:
d = Document(
Expand Down
31 changes: 31 additions & 0 deletions tests/unit/array/mixins/test_match.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -515,3 +515,34 @@ def test_diff_framework_match(ndarray_val):
da = DocumentArray.empty(10)
da.embeddings = ndarray_val
da.match(da)


def test_match_ensure_scores_unique():
import numpy as np
from docarray import DocumentArray

da1 = DocumentArray.empty(4)
da1.embeddings = np.array(
[[0, 0, 0, 0, 1], [1, 0, 0, 0, 0], [1, 1, 1, 1, 0], [1, 2, 2, 1, 0]]
)

da2 = DocumentArray.empty(5)
da2.embeddings = np.array(
[
[0.0, 0.1, 0.0, 0.0, 0.0],
[1.0, 0.1, 0.0, 0.0, 0.0],
[1.0, 1.2, 1.0, 1.0, 0.0],
[1.0, 2.2, 2.0, 1.0, 0.0],
[4.0, 5.2, 2.0, 1.0, 0.0],
]
)

da1.match(da2, metric='euclidean', only_id=False, limit=5)

assert len(da1) == 4
for query in da1:
previous_score = -10000
assert len(query.matches) == 5
for m in query.matches:
assert m.scores['euclidean'].value >= previous_score
previous_score = m.scores['euclidean'].value