diff --git a/data-computer/v1/lda.py b/data-computer/v1/lda.py index e8aedc2..b393c50 100755 --- a/data-computer/v1/lda.py +++ b/data-computer/v1/lda.py @@ -42,6 +42,8 @@ #tokenize def tokenize(text): tokens = [word for word in text.replace("'"," ").split() if word not in stopwords and len(word)>2] + if len(tokens)==0: + return ["none"] return tokens