text/

>>> from tuiml.preprocessing.text import TfidfVectorizer, WordTokenizer
>>>
>>> # Tokenize text
>>> tokenizer = WordTokenizer()
>>> tokens = tokenizer.tokenize("Hello, World!")
>>> print(tokens)  # ['hello', 'world']
>>>
>>> # Convert to TF-IDF
>>> vectorizer = TfidfVectorizer(stop_words='english', max_features=1000)
>>> X = vectorizer.fit_transform(documents)