Merge branch 'master' of github.com:dorianbrown/rank_bm25

dorianbrown · Feb 16, 2022 · 2550648 · 2550648
2 parents 70c7314 + 97a38cf
commit 2550648
Showing 1 changed file with 3 additions and 1 deletion.
diff --git a/rank_bm25.py b/rank_bm25.py
@@ -14,7 +14,7 @@
 
 class BM25:
     def __init__(self, corpus, tokenizer=None):
-        self.corpus_size = len(corpus)
+        self.corpus_size = 0
         self.avgdl = 0
         self.doc_freqs = []
         self.idf = {}
@@ -47,6 +47,8 @@ def _initialize(self, corpus):
                 except KeyError:
                     nd[word] = 1
 
+            self.corpus_size += 1
+
         self.avgdl = num_doc / self.corpus_size
         return nd