In3x,net,watch,14zwhrd6,dildo,18 -

# Your data text = "in3x,net,watch,14zwhrd6,dildo,18"

# Vectorizer to convert text into a matrix of token counts vectorizer = CountVectorizer() count_features = vectorizer.fit_transform(data) in3x,net,watch,14zwhrd6,dildo,18

# Let's create a dummy dataset data = [' '.join(tokens)] # Your data text = "in3x

# TF-IDF transformer tfidf = TfidfTransformer() tfidf_features = tfidf.fit_transform(count_features) in3x,net,watch,14zwhrd6,dildo,18

# Tokenize (simple split) tokens = text.split(',')