def extend_vocab()

in torchmoji/create_vocab.py [0:0]

• 16 lines of code
• 5 McCabe index (conditional complexity)

def extend_vocab(current_vocab, new_vocab, max_tokens=10000):
    """ Extends current vocabulary with words from vocab that are not
        present in the current vocabulary. Adds up to max_tokens words.

    # Arguments:
        current_vocab: Current dictionary of tokens.
        new_vocab: Vocabulary to be added. MUST have word_counts populated, i.e.
            must have run count_all_words() previously.
        max_tokens: Maximum number of words to be added.

    # Returns:
        How many new tokens have been added.
    """
    if max_tokens < 0:
        max_tokens = 10000

    words = OrderedDict()

    # sort words by frequency
    desc_order = OrderedDict(sorted(new_vocab.word_counts.items(),
                                key=lambda kv: kv[1], reverse=True))
    words.update(desc_order)

    base_index = len(current_vocab.keys())
    added = 0
    for word in words:
        if added >= max_tokens:
            break
        if word not in current_vocab.keys():
            current_vocab[word] = base_index + added
            added += 1

    return added