Should look something like this:
from revscoring.features import wikitext from revscoring.datasources.meta import vectorizers from revscoring.features.meta import aggregators google_news_kvs = vectorizer.word2vec.load_kv("google_news.bin") revision_text_vectors = vectorizer.word2vec( wikitext.revision.datasources.words, google_news_kvs, name="revision.text.google_news_vectors") mean_revision_text_vector = aggregators.mean( revision_text_vectors, vector=True, # We'll need to add this. I think all of our aggregators could work on vectors. Maybe it could auto detect that there's a vector involved. name="revision.text.google_news_vector")