How to get sentiment polarity rather than classification?

[mmz15]

Firstly, thanks to all contributors to this repo; it's a great contribution to the NLP community.

I just wanted to ask: is there a polarity/magnitude-based sentiment analysis? From the research paper implementations it all seems classification-based, but wanted to confirm. If not, is there an easy way to re-implement the existing code for such functionality? I'm trying to more closely mirror Google's natural language API, which adds scores and magnitude to their entity-based results.