diff options
Diffstat (limited to 'source/utils.py')
-rwxr-xr-x | source/utils.py | 4 |
1 files changed, 3 insertions, 1 deletions
diff --git a/source/utils.py b/source/utils.py index 9b52ce4b..09056bbe 100755 --- a/source/utils.py +++ b/source/utils.py @@ -119,7 +119,9 @@ def top_words(articles, n=10, size=5): words = Counter() wordre = re.compile(r'\b\w{%s,}\b' % size, re.I) for article in articles: - for word in [elem.lower() for elem in wordre.findall(clear_string(article["article_content"])) if elem.lower() not in stop_words]: + for word in [elem.lower() for elem in + wordre.findall(clear_string(article["article_content"])) \ + if elem.lower() not in stop_words]: words[word] += 1 return words.most_common(n) |