How to generate correct data for SVM?

[JasmineCA]

Hi, I've discovered your extension through a grafana article, and it's quite interesting. I'm gonna test it for sure. But I have some questions about the SVM part. In a real test, how do you provide the train set for the SVM model? In your examples you put it inside the script directly, however I don't think it's suitable for a real test case.