Scikit-learn expects that every observation we also call it a sample or a data point is basically described by a vector, a convector of values. It's probably not the best way to get a predictive system. You want to do some feature transformation, change the input to get something that brings feature that are more powerful for scikit-learning and the learning system. So they're probably a bit of a pre-processing to do on this row signals then once you have your vector, you can use the scikit learn machinery to build your predictive system.