counts2pmi.py 文件源码

def main():
    args = docopt("""
    Usage:
        counts2pmi.py [options] <counts> <output_path>

    Options:
        --cds NUM    Context distribution smoothing [default: 1.0]
    """)

    counts_path = args['<counts>']
    vectors_path = args['<output_path>']
    cds = float(args['--cds'])

    counts, iw, ic = read_counts_matrix(counts_path)

    pmi = calc_pmi(counts, cds)

    save_matrix(vectors_path, pmi)
    save_vocabulary(vectors_path + '.words.vocab', iw)
    save_vocabulary(vectors_path + '.contexts.vocab', ic)