retrieving GMM classification of each cell

[dsb66]

I would like to retrieve the GMM classification of each cell in my dataset to further explore subpopulations. I didn't see that these values are stored in the pop object, but by inspecting the code I think they can be calculated as follows:

C = PA.get_coeff(pop,key)
prediction = pop['samples'][key]['gmm'].predict(C)

Is it correct? If not, could you point me to the right way to calculate the GMM classification of each cell?
Also, is there a way to retrieve the weight of each NMF feature for each gaussian in the GMM?

Thank you very much,
Dario