# Tokenize (simple split) tokens = text.split(',')
# Vectorizer to convert text into a matrix of token counts vectorizer = CountVectorizer() count_features = vectorizer.fit_transform(data) in3x,net,watch,14zwhrd6,dildo,18
# TF-IDF transformer tfidf = TfidfTransformer() tfidf_features = tfidf.fit_transform(count_features) # Tokenize (simple split) tokens = text