I have used sklearn's sklearn.decomposition.LatentDirichletAllocation module to model 10 topics in a set of documents.
I have also used the same on a reference text (1 document) and obtained a 1 topic LDA for it.
I want to compare the 10 topics from the documents to the 1 reference topic and determine which one is most closely related to the referece.
I have been trying to figure out an implementation of KL divergence for this purpose but cannot seem to understand how to tie it in with the LDA outputs. Any help is appreciated.