diff --git a/test_combine.py b/test_combine.py index 8aea1c2ab670f8a4e23086a2301c4527ba4ec4c2..233702ca00dcb76829c9510a4240817f8bbfeb1c 100644 --- a/test_combine.py +++ b/test_combine.py @@ -65,7 +65,7 @@ def jaccard_similarity(str1, str2): tokens_str1 = set(word_tokenize(str1.lower())) tokens_str2 = set(word_tokenize(str2.lower())) - stop_words = set(stopwords.words('english')) + stop_words = set(stopwords.words('french')) tokens_str1 = tokens_str1 - stop_words tokens_str2 = tokens_str2 - stop_words