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

# Vectorizer to convert text into a matrix of token counts vectorizer = CountVectorizer() count_features = vectorizer.fit_transform(data)

# Let's create a dummy dataset data = [' '.join(tokens)] in3x,net,watch,14zwhrd6,dildo,18

from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer # Vectorizer to convert text into a matrix

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