"How to deploy a model if I don't have RapidMiner Server?"

User143508User143508 Member Posts: 2 Contributor I
edited May 2019 in Help
Hi, I'm new to this and have been playing around with RapidMiner Studio. I've trained a model successfully and now the question is how can I use the model on other data, or how can I deploy the model. I've searched and found RapidMiner Server, but it seems that there is no free version any more. Is it possible to train a model in RapidMiner Studio and deploy it without RapidMiner Server? I'm OK with writing code or setting up web server, etc. Just want to know what are the options. Thank you.
Tagged:

Answers

  • sgenzersgenzer Administrator, Moderator, Employee, RapidMiner Certified Analyst, Community Manager, Member, University Professor, PM Moderator Posts: 2,959 Community Manager
    edited January 2019
    hi @User143508 so yes RapidMiner Server is how you deploy models in this ecosystem. RapidMiner Studio is only for building models. RM Server is not free but pretty darn cheap if you use the PAYG options on AWS or Azure if you're comfortable with setting up cloud infrastructures in these environments. You can build a pretty cheap system if you just set up some AWS Lambda workflows that fires up RM Server on demand / on a schedule and then shuts it down when you're done.

    Scott

  • User143508User143508 Member Posts: 2 Contributor I
    @sgenzer Thank you for the reply. So you can't take the model out? You'll be locked into RapidMiner? I've really liked RapidMiner Studio and was hoping one can somehow export the model and write some code to use it. What a pity.  :'(
  • sgenzersgenzer Administrator, Moderator, Employee, RapidMiner Certified Analyst, Community Manager, Member, University Professor, PM Moderator Posts: 2,959 Community Manager
    well if you like to play around you can certainly build your own simple scheduler and just run RM from command line. I've not done it myself but lots of people here on the community have puttered around in this way. 

Sign In or Register to comment.