fixed bug

marixko · Oct 20, 2022 · d75f911 · d75f911
1 parent 6508568
commit d75f911
Showing 1 changed file with 3 additions and 0 deletions.
diff --git a/utils.py b/utils.py
@@ -10,6 +10,8 @@
 from wordcloud import WordCloud
 import matplotlib.pyplot as plt
 
+nltk.download("stopwords")
+
 def get_top_ngram(corpus, n=None):
     vec = CountVectorizer(ngram_range=(n, n)).fit(corpus)
     bag_of_words = vec.transform(corpus)
@@ -26,6 +28,7 @@ def tokenize(s):
     return word_tokenize(s, language="english")
 
 def remove_stopwords(s):
+    stpwrds = set(stopwords.words("english"))
     return [w for w in s if not w in stpwrds]
 
 def stem(s):