Options
Rapid Miner Go vs Rapid Miner Studio
Contributor II
I have a dataset of 5,000 lines with 15 attributes. I've been trying to use this dataset in the tutorials, trying to understand the process of Rapid Miner Studio, trying to connect the appropriate boxes with lines. By chance I learned about Rapid Miner Go. After following the first step, downloading my training dataset, picking the appropriate attribute as dependent variable for a logistic regression model and following instructions from there. I ran the model and was simply amazed at the decent percentages I was getting for predictive value, including .77 for the AUC. I have not proceeded to model deployment. I just need to understand what it is I am missing by bypassing the Studio process?
Tagged:
0
Best Answers
-
Options
BalazsBarany
Administrator, Moderator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert Posts: 955 
Unicorn
Hi @tonyboy9,
you obviously have a dataset that is already good for applying machine learning on it. This is where RapidMiner Go shines.
You can do much more in RapidMiner Studio. If you have messy data in different data sources, you have everything in Studio to clean them and put them together. You have more modeling algorithms and more places to affect the result.
RapidMiner Go essentially does the modeling that a junior data scientist would do with the data. When you become more advanced, you can take the process created by Go and extend it to improve your results even more. Or you just build it from scratch in Studio, maybe using templates or the Projects extension.
In toy terms, Go is like Playmobil (you can play with it quickly) and Studio is like LEGO (you can build anything you need, it takes some time, but it can be a lot of fun).
Regards,
Balázs7 -
OptionsBalazsBarany
Administrator, Moderator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert Posts: 955 Unicorn
Hi Tony,
when you add an extension to RapidMiner Studio, you get some new operators. You find these in the operator list by searching for them, or browsing the operator tree.
Regards,
Balázs6
Answers
Oh, I nearly forgot. You mentioned extension, which I added the statistics extension. Where is that used in the Studio process?