diff options
| author | Martin Czygan <martin.czygan@gmail.com> | 2020-11-17 02:36:40 +0100 |
|---|---|---|
| committer | Martin Czygan <martin.czygan@gmail.com> | 2020-11-17 02:36:40 +0100 |
| commit | e503c86cddd1591cccf1354b7c8ecd1a00d600e3 (patch) | |
| tree | 1ba3bfcd689a581a337913b406d67a9e7d1ba0ba | |
| parent | 8d708f337c8abbec61229f023637ddebcee827b5 (diff) | |
| download | fuzzycat-e503c86cddd1591cccf1354b7c8ecd1a00d600e3.tar.gz fuzzycat-e503c86cddd1591cccf1354b7c8ecd1a00d600e3.zip | |
update docs and blacklist
| -rw-r--r-- | fuzzycat/verify.py | 28 |
1 files changed, 28 insertions, 0 deletions
diff --git a/fuzzycat/verify.py b/fuzzycat/verify.py index 9af70e4..241ce7f 100644 --- a/fuzzycat/verify.py +++ b/fuzzycat/verify.py @@ -23,6 +23,30 @@ Examples from clustering stage (from a sample of 100k records): ["Editorial Board & Publication Information",2] ... +WIP: + + { + "miss.blacklisted": 620, + "miss.contrib_intersection_empty": 3256, + "miss.dataset_doi": 8725, + "miss.num_diff": 14914, + "miss.release_type": 14352, + "miss.short_title": 3321, + "miss.vhs": 45, + "miss.year": 12385, + "ok.arxiv_version": 13, + "ok.dummy": 8874, + "ok.preprint_published": 7, + "ok.slug_title_author_match": 526, + "ok.title_author_match": 6187, + "skip.container_name_blacklist": 71, + "skip.publisher_blacklist": 22, + "skip.too_large": 1077, + "skip.unique": 830449, + "total": 904844 + } + + """ import collections @@ -41,6 +65,10 @@ get_key_values = operator.itemgetter("k", "v") TITLE_BLACKLIST = set([ "annual meeting", "an invitation to membership", + "appendix d.", + "appendix d", + "abstracts of papers from other journals", + "an epitome of current medical literature", "", ":{unav)", "[others]", |