diff options
| author | Martin Czygan <martin.czygan@gmail.com> | 2020-11-28 17:22:06 +0100 |
|---|---|---|
| committer | Martin Czygan <martin.czygan@gmail.com> | 2020-11-28 17:22:06 +0100 |
| commit | dbe51fe929712f142c91ce3f4ffad600a2c2c8f6 (patch) | |
| tree | e5036589b3a592dcfbd8861f304f1cd1b178a1ba /fuzzycat | |
| parent | 834a23edfa931b12648dbff31d53ea98d272c125 (diff) | |
| download | fuzzycat-dbe51fe929712f142c91ce3f4ffad600a2c2c8f6.tar.gz fuzzycat-dbe51fe929712f142c91ce3f4ffad600a2c2c8f6.zip | |
limit to 5 authors
Diffstat (limited to 'fuzzycat')
| -rw-r--r-- | fuzzycat/verify.py | 7 |
1 files changed, 5 insertions, 2 deletions
diff --git a/fuzzycat/verify.py b/fuzzycat/verify.py index a40c0d9..2eff873 100644 --- a/fuzzycat/verify.py +++ b/fuzzycat/verify.py @@ -325,8 +325,11 @@ def compare(a, b): # in this block. Score = collections.namedtuple("Score", "a b value") scores = [] - # account for the possible arbitrary ordering of authors - for a, b in itertools.product(a_slug_authors, b_slug_authors): + # account for the possible arbitrary ordering of authors, XXX: this + # explodes. + a_trimmed = sorted(a_slug_authors)[:5] + b_trimmed = sorted(b_slug_authors)[:5] + for a, b in itertools.product(a_trimmed, b_trimmed): scores.append(Score(a, b, author_similarity_score(a, b))) # TODO: less arbitrary metric and threshold top_scores = [] |