Evaluate classifikator with new data set

Hey everybody,

I am trying to train a simple classificator . Because of the structure of my data (there are far more samples of one group and less of another) I decided to make a training sample in which the data is more balanced. I would really like to train my classificator with the training data and the evaluate it with other data. Is there a way to get all the graphs like to confusion matrix when the model is already trained ?

Thanks in advance!