train.py 文件源码

def vector_quantize(data_dict, vs, bins):
    codebooks = {}
    vq_data = {}
    for size in vs.keys():
        all_size_data = []
        for disease in vs[size]:
            all_size_data.extend(data_dict[disease])
        #whitened = sp.whiten(all_size_data)
        #codebooks[size] = sp.kmeans(whitened, bins)[0]
        codebooks[size] = sp.kmeans(np.asarray(all_size_data), bins)[0]
    pickle.dump(codebooks,open("all_codebooks.pkl","wb"))
    for dis in data_dict.keys():
        n = len(data_dict[dis])
        m = len(data_dict[dis][0])
        vq_data[dis] = map(str,sp.vq(np.reshape(data_dict[dis],(n,m)), codebooks[len(data_dict[dis][0])])[0])
    return vq_data