Fixes piskvorky#1828

sj29-innovate · Jan 8, 2018 · 80dc13d · 80dc13d
1 parent 37bc8d4
commit 80dc13d
Showing 1 changed file with 2 additions and 1 deletion.
diff --git a/gensim/summarization/bm25.py b/gensim/summarization/bm25.py
@@ -121,8 +121,9 @@ def get_score(self, document, index, average_idf):
             if word not in self.f[index]:
                 continue
             idf = self.idf[word] if self.idf[word] >= 0 else EPSILON * average_idf
+            doc_length = len(self.corpus[index])
             score += (idf * self.f[index][word] * (PARAM_K1 + 1)
-                      / (self.f[index][word] + PARAM_K1 * (1 - PARAM_B + PARAM_B * len(document) / self.avgdl)))
+                      / (self.f[index][word] + PARAM_K1 * (1 - PARAM_B + PARAM_B * doc_length / self.avgdl)))
         return score
 
     def get_scores(self, document, average_idf):