Replace division in log() with subtraction of two log()s (#23)

dorianbrown · May 28, 2024 · b447cc9 · b447cc9
1 parent 990470e
commit b447cc9
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/rank_bm25.py b/rank_bm25.py
@@ -182,7 +182,7 @@ def __init__(self, corpus, tokenizer=None, k1=1.5, b=0.75, delta=1):
 
     def _calc_idf(self, nd):
         for word, freq in nd.items():
-            idf = math.log((self.corpus_size + 1) / freq)
+            idf = math.log(self.corpus_size + 1) - math.log(freq)
             self.idf[word] = idf
 
     def get_scores(self, query):