Predict new documents

[madegomez]

HI.
I am interested in using your library, but so far this library only seems to be able to assign topics to sentences in its training set. Is there a way to predict another subset different from training set?

Thank you.

[federicoscabbia]

from stack overflow this seems to be the way:
mgp.score(["my", "beautiful", "text", "is", "here"])

Use tokenized text or it won-t work