def find(self):
print("Finding similarity")
simi = Similarity()
embeddings_index, knn = simi.similarity()
print("***************")
from similarity import Similarity
a = Similarity(update=False)
print(a.similarity('A caza de papil é linda', 'A Casa de papel é linda '))
print(a.similarity('A caza de papel é linda', 'A Casa de papel é linda '))
print(a.similarity('A casa de papel eh linda', 'A Casa de papel é linda '))
print(
f"*** Loaded {sim.num_words} word vectors with dimensionality {sim.num_features}"
)
print("** Computing matches")
n = 0
n_unknown = 0
for reviewer in Author.objects.filter(
Q(volunteer=True) | Q(first_author=True)):
if Bid.objects.filter(author=reviewer).exists():
continue
email = reviewer.email
try:
reftexts = reference[email]
except KeyError:
print(
f"##### No reference text found for {reviewer.email} ({reviewer.first_name} {reviewer.last_name})"
)
n_unknown += 1
continue
for paper in Paper.objects.all():
text = "\n\n".join([paper.title, paper.abstract])
s = sim.similarity(text, "\n\n".join(reftexts))
Bid.objects.create(paper=paper, author=reviewer, score=0, weight=s)
n += 1
print(
f"*** Assigned similarity scores for {n} reviewers (skipped {n_unknown} reviewers)"
)
#print(reviewer, reviewer.email in reference)
