def get_word2rank()

in access/feature_extraction.py [0:0]

• 11 lines of code
• 4 McCabe index (conditional complexity)

def get_word2rank(vocab_size=np.inf):
    prepare_fasttext_embeddings()
    # TODO: Decrease vocab size or load from smaller file
    word2rank = {}
    line_generator = yield_lines(FASTTEXT_EMBEDDINGS_PATH)
    next(line_generator)  # Skip the first line (header)
    for i, line in enumerate(line_generator):
        if (i + 1) > vocab_size:
            break
        word = line.split(' ')[0]
        word2rank[word] = i
    return word2rank