diff --git a/src/machinevisiontoolbox/BagOfWords.py b/src/machinevisiontoolbox/BagOfWords.py
index 65b85885..33231f3e 100644
--- a/src/machinevisiontoolbox/BagOfWords.py
+++ b/src/machinevisiontoolbox/BagOfWords.py
@@ -58,6 +58,13 @@ def __init__(
         of image features is assigned labels from the ``.centroids`` any with a
         label greater that ``.nstopwords`` is a stop word and can be discarded.
 
+        .. note:: Removing stop words can leave a remaining word that never
+            occurs in any image, giving it an inverse document frequency (idf)
+            of ``inf`` (``log(N / 0)``). This is harmless -- every place idf is
+            used to compute a word-frequency vector, the corresponding word
+            count is also always zero there, so the ``0 * inf`` result is
+            ``nan`` and gets replaced with 0 before the vector is returned.
+
         :reference:
             - Video Google: a text retrieval approach to object matching in videos
               J.Sivic and A.Zisserman,
@@ -139,7 +146,12 @@ def __init__(
         # total number of occurrences of word i
         # multiple occurrences in the one image count only as one
         ni = (W > 0).sum(axis=1)
-        idf = np.log(N / ni)
+        # a word that never occurs in any image (ni=0, possible after
+        # stopword removal) gives idf=inf here; harmless since nid is
+        # always 0 at that same position below, so 0*inf->nan, already
+        # suppressed by the invalid="ignore" there.
+        with np.errstate(divide="ignore"):
+            idf = np.log(N / ni)
 
         M = []
 
diff --git a/tests/test_bag_of_words.py b/tests/test_bag_of_words.py
index e8ab1f13..bd34e619 100644
--- a/tests/test_bag_of_words.py
+++ b/tests/test_bag_of_words.py
@@ -4,6 +4,7 @@
 """
 
 import unittest
+import warnings
 
 from machinevisiontoolbox import FileCollection, BagOfWords
 import numpy as np
@@ -26,7 +27,15 @@ def test_retrieve(self):
         bag = BagOfWords(features, 2_000, seed=0)
         # self.assertEqual(len(bag), 42_213)
 
-        bag = BagOfWords(features, 2_000, nstopwords=50, seed=0)
+        # Regression test: nstopwords>0 can leave a word with zero
+        # occurrences across every remaining image (ni=0), which used to
+        # raise "RuntimeWarning: divide by zero" from idf = np.log(N/ni)
+        # -- harmless (the inf it produces is always multiplied by 0
+        # downstream) but not suppressed, unlike the equivalent case
+        # right below it in the same function.
+        with warnings.catch_warnings():
+            warnings.simplefilter("error", RuntimeWarning)
+            bag = BagOfWords(features, 2_000, nstopwords=50, seed=0)
         # self.assertEqual(len(bag), 34_997)
 
         query = FileCollection("campus/holdout/*.png", mono=True)