def __get_doc_scores(self, posting_list, query: Query):
click.secho("[Search Engine] Computing search scores ...",
fg="bright_blue")
query_tf_idf = {}
norm_query_vector = 0
query_vocabulary = query.get_vocabulary()
for token in query_vocabulary:
tf_idf = query.get_tf(token) * self.collection.get_idf(token)
query_tf_idf[token] = tf_idf
norm_query_vector += tf_idf**2
norm_query_vector = sqrt(norm_query_vector)
doc_scores = {}
for doc_id in posting_list:
score = 0
for token in query_vocabulary:
if self.weighting_model == "tw-idf":
weight = self.collection.get_tw_idf(target_term=token,
target_doc_id=doc_id,
b=0.003)
elif self.weighting_model == "tf-idf":
weight = self.collection.get_piv_plus(target_term=token,
target_doc_id=doc_id,
b=0.2)
else:
weight = self.collection.get_bm25_plus(
target_term=token,
target_doc_id=doc_id,
b=0.75,
k1=1.2)
score += query_tf_idf[token] * weight
score /= self.collection.documents_norms[doc_id] * norm_query_vector
doc_scores[doc_id] = score
return doc_scores
