Unlabeled data
hyjocean opened this issue · comments
hello, thanks for your excellent work.
wmm, and I have a problem, I find the response in "starting with "wide" data", you say the data can be unlabeled, it depends on my task "(You don't need labels necessarily, depending on your task.)"
and when I read your article or code readme, I notice that you mentioned the parameters in different data are same, right? (ok, I don't know if I understand right, and I can't find where is the latter information.)
So my question is, could I apply your work on my unlabeled data? if it's true, how can I set the "Y_traing" in examples codes?
thanks!
Hi @hyjocean, sorry for the slow reply.
In relation to labels, I didn't mean any 'special', only that you won't need labels for certain tasks (e.g., clustering, unsupervised training, etc.).
You don't need the labels to generate the features (i.e., X_training_transform = transform(X_training, parameters)), but you do need the labels when training the classifier (e.g., classifier.fit(X_training_transform, Y_training)). If you don't have labels then you can't train the classifier in this way.
I hope that helps.
Ahh, I get it.
Thanks for your patience reply~