utils.py 文件源码

def predict_ana( model, a, a2, b, realb2 ):
    questWordIndices = [ model.word2id[x] for x in (a,a2,b) ]
    # b2 is effectively iterating through the vocab. The row is all the cosine values
    b2a2 = model.sim_row(a2)
    b2a  = model.sim_row(a)
    b2b  = model.sim_row(b)
    addsims = b2a2 - b2a + b2b

    addsims[questWordIndices] = -10000

    iadd = np.nanargmax(addsims)
    b2add  = model.vocab[iadd]

    # For debugging purposes
    ia = model.word2id[a]
    ia2 = model.word2id[a2]
    ib = model.word2id[b]
    ib2 = model.word2id[realb2]
    realaddsim = addsims[ib2]

    mulsims = ( b2a2 + 1 ) * ( b2b + 1 ) / ( b2a + 1.001 )
    mulsims[questWordIndices] = -10000
    imul = np.nanargmax(mulsims)
    b2mul  = model.vocab[imul]

    return b2add, b2mul