How to handle unlabelled data

[neural-nerd-raj]

I noticed, after load_sessions is called, it has train/test data in form of:
{'templates': ['BLOCK NameSystem.allocateBlock:<>',...], 'label': 0}.**
For unsupervised data there is no label key available.
How to handle this? Do I need to assume '0' as label for unsupervised?

[CattusX]

Unsupervised learning should be achieved by setting the "--label_type" parameter to "nextlog", meaning that the ID of the next log in the window is used as a label for unsupervised learning. For supervised learning, the parameter should be set to "anomaly".

[alexjamesmx]

they do it that way so you can mesure metrics at the end. but int real world applications you wont have label(0 or 1). Regarding the @new-cat , thats right, labels will be next key given a sequence