def compute_scores(self, list_of_docs, query: Query):
""" Scores each document, depending of the tokens it contains."""
print("Search Engine is computing search scores ...")
query_tf_idf = {}
vocab_query = query.get_vocabulary()
# get the tf_idf for words in the query
for word in vocab_query:
tf_idf = query.get_term_frequency(word) * self.collection.compute_idf(word)
query_tf_idf[word] = tf_idf
# score the documents which contain the words
doc_scores = {}
for doc_id in list_of_docs:
score = 0
for word in vocab_query:
normalized_tf = self.collection.log_normalization(
term=word, id_document=doc_id
)
if normalized_tf == 0: # the word is not in the document
doc_tf_idf = 0
else:
doc_tf_idf = normalized_tf * self.collection.compute_idf(word) #tf-idf for the word in the document
score += query_tf_idf[word] * doc_tf_idf
doc_scores[doc_id] = score
return doc_scores
