From 3c4ac0abc1e23fe15ef1bc55c523707456683a38 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?V=C3=ADt=20Novotn=C3=BD?= <witiko@mail.muni.cz>
Date: Tue, 26 Nov 2019 20:42:53 +0100
Subject: [PATCH] Warn when BM25.average_idf < 0 Closes #2684

---
 gensim/summarization/bm25.py | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/gensim/summarization/bm25.py b/gensim/summarization/bm25.py
index b9621aeb1e..0477ca7430 100644
--- a/gensim/summarization/bm25.py
+++ b/gensim/summarization/bm25.py
@@ -37,6 +37,7 @@
 """
 
 
+import logging
 import math
 from six import iteritems
 from six.moves import range
@@ -48,6 +49,8 @@
 PARAM_B = 0.75
 EPSILON = 0.25
 
+logger = logging.getLogger(__name__)
+
 
 class BM25(object):
     """Implementation of Best Matching 25 ranking function.
@@ -116,6 +119,13 @@ def _initialize(self, corpus):
                 negative_idfs.append(word)
         self.average_idf = float(idf_sum) / len(self.idf)
 
+        if self.average_idf < 0:
+            logger.warning(
+                'Average inverse document frequency is less than zero. Your corpus of {} documents'
+                ' is either too small or it does not originate from actual text documents. BM25'
+                ' will likely produce "wrong" results.'.format(self.corpus_size)
+            )
+
         eps = EPSILON * self.average_idf
         for word in negative_idfs:
             self.idf[word] = eps