def retrieval_cosine(self, query):
scores = dict()
tokens = Tokens()
query_terms = tokens.edit_query(query)
query_weights = dict(collections.Counter(query_terms).items())
for query in query_weights:
query_weights[query] = tf(query_weights[query])
for query in query_weights:
term = query
doc_ids = self.L(term)
for doc in doc_ids:
if doc[0] not in scores:
scores[doc[0]] = tf(doc[1]) * tf(query_weights[term])
else:
new_value = scores[doc[0]] + tf(doc[1]) * tf(
query_weights[term])
scores[doc[0]] = new_value
for id in scores:
norm_value = self.inverted_index.get_norms(str(id))
scores[id] = round(
scores[id] /
(norm_value * self.get_query_norms(query_weights)), 2)
scores = sorted(scores.items(), key=lambda kv: kv[1], reverse=True)
return scores
