def one_hot()

in lambdachecker/sms_spam_classifier_utilities.py [0:0]

• 9 lines of code
• 1 McCabe index (conditional complexity)

def one_hot(text, n,
            filters='!"#$%&()*+,-./:;<=>?@[\\]^_`{|}~\t\n',
            lower=True,
            split=' '):
    """One-hot encodes a text into a list of word indexes of size n.
    This is a wrapper to the `hashing_trick` function using `hash` as the
    hashing function; unicity of word to index mapping non-guaranteed.
    # Arguments
        text: Input text (string).
        n: int. Size of vocabulary.
        filters: list (or concatenation) of characters to filter out, such as
            punctuation. Default: `!"#$%&()*+,-./:;<=>?@[\\]^_`{|}~\t\n`,
            includes basic punctuation, tabs, and newlines.
        lower: boolean. Whether to set the text to lowercase.
        split: str. Separator for word splitting.
    # Returns
        List of integers in [1, n]. Each integer encodes a word
        (unicity non-guaranteed).
    """
    return hashing_trick(text, n,
                         hash_function='md5',
                         filters=filters,
                         lower=lower,
                         split=split)