counts2ppmi.py 文件源码

def calc_pmi(counts, cds):
    sum_w = np.array(counts.sum(axis=1))[:, 0]
    sum_c = np.array(counts.sum(axis=0))[0, :]
    if cds != 1:
        sum_c = sum_c ** cds
    sum_total = sum_c.sum()
    sum_w = np.reciprocal(sum_w)
    sum_c = np.reciprocal(sum_c)

    pmi = csr_matrix(counts)
    pmi = multiply_by_rows(pmi, sum_w)
    pmi = multiply_by_columns(pmi, sum_c)
    pmi = pmi * sum_total
    return pmi