def get_document(self, doc_id):
dbManager = DbManager()
return dbManager.get_document(doc_id)
def add_snippets(self, ranked_docs, query):
dbManager = DbManager()
builder = StructureBuilder()
docs_with_snippets = []
tf_idf_q_terms = {}
q_terms = builder.get_stemmed_tems(query)
for q_term in q_terms:
# number of documents in DC in which q_term appears at least once.
n_docs_q_term = len(self.q_terms_freqs[q_term]
) if q_term in self.q_terms_freqs else 0
if n_docs_q_term != 0:
freq_d = len([q for q in q_terms if q == q_term])
max_q_freq = self.get_local_max_freq(q_terms)
tf_idf_q_terms[q_term] = self.calc_tf_idf(
freq_d, max_q_freq, self.docs_count, n_docs_q_term)
else:
tf_idf_q_terms[q_term] = 0
for ranked_doc in ranked_docs:
doc_id = ranked_doc[0]
docs_relevant_scores = {}
doc = dbManager.get_document(doc_id)
if doc == None: continue
sentences = self.get_doc_sentences(doc)
title = sentences.pop(0)['content']
for sentence in sentences:
senetence_content = sentence['content']
# if the sentence has less than 2 character then it is probabily not an actual sentence.
if len(senetence_content) <= 2: continue
sentence_id = sentence['id']
tf_idf_sum = 0
denom_di_sum = 0
denom_qi_sum = 0
index_sentence = builder.get_stemmed_terms_frequencies_from_doc(
sentence)
for q_term in q_terms:
# check the not stemmed words
if q_term in index_sentence.Terms:
q_sentence_freq = index_sentence.get_term_freq(q_term)
max_freq = index_sentence.get_max_freq()
# if the query term doesn't have frequency on the sentence and there is no max freq. then disregard this q_term
if (q_sentence_freq == 0 and max_freq == 0):
continue
tf_idf_doc = self.calc_tf_idf(
q_sentence_freq, max_freq, self.docs_count,
len(self.q_terms_freqs[q_term]))
tf_idf_q = tf_idf_q_terms[q_term]
# The two sentences in d that have the highest cosine similarity with respect to q; with TF-IDF as the term weighting scheme.
tf_idf_sum += tf_idf_doc * tf_idf_q
denom_di_sum += tf_idf_doc**2
denom_qi_sum += tf_idf_q**2
denom = math.sqrt(denom_di_sum) * math.sqrt(denom_qi_sum)
score = tf_idf_sum / denom if denom != 0 else 0
docs_relevant_scores[sentence_id] = round(score, 3)
sorted_docs_total_freqs = sorted(docs_relevant_scores.items(),
key=operator.itemgetter(1),
reverse=True)
top_sentences = sorted_docs_total_freqs[0:2]
top_snippets = [
s['content'] for s in sentences
if s['id'] == top_sentences[0][0]
or s['id'] == top_sentences[1][0]
]
docs_with_snippets.append({
"docId": doc_id,
"score": ranked_doc[1],
"title": title,
"snippets": top_snippets
})
return docs_with_snippets
