How to access _dlabel after training the raw data?

[xuezhaokun]

I have a 129 x 4862 data. And I trained it via som = sompy.SOMFactory.build(data, mapsize, mask=None, mapshape='planar', lattice='rect', normalization='var', initialization='pca', neighborhood='gaussian', training='batch', name='sompy') som.train(n_job=1, verbose='info')

I thought after training my data, I should get a label for each of my raw data record. I noticed there is _dlabel field in SOM. but when I tried to accessed it always gave me NONE. I am wondering how could I get labels for my raw data after training it.

Thanks

[sevamoo]

Label comes from the data and initially they are none. I am not sure from your question, what are you looking for. If you want to find the bmu of each data point, just use project function or fin_k_nodes.

[yasohasakii]

Hi！ Still ambigious about label attr. I want to figure out how to get data label after I did cluster operate because my project is to classify raw data by SOM, thanks!

Label comes from the data and initially they are none. I am not sure from your question, what are you looking for. If you want to find the bmu of each data point, just use project function or fin_k_nodes.

[Aaron-LHR]

Hi！ Still ambigious about label attr. I want to figure out how to get data label after I did cluster operate because my project is to classify raw data by SOM, thanks!

Label comes from the data and initially they are none. I am not sure from your question, what are you looking for. If you want to find the bmu of each data point, just use project function or fin_k_nodes.

Hello! Have you solved this problem? Thanks!