You'll be redirected shortly, we've moved to our new idea portal: https://ibm-watson.ideas.aha.io
It will be good to have a capability in the tooling to do a train/test evaluation on a WDS collection and have the nDCG & recall metrics visible in the dashboard
I have been using a python script for testing WDS:
It's pretty basic, but might help you.
You won't be notified about changes to this idea.