Analyzing Categorical Data or Polynomial Data in Rapid Miner
Newbie
Hi! I need help. I am currently task to analyze and cluster the data that I've got in our Learning Management System. But, I have a problem. I am really new to R and I do not know how to perform analysis on the Polynomial data. It doesn't allow me to normalize the data or put K means clustering to it. Please help the deadline of this is tomorrow.
I just need to find a way to analyze it, to get its mean, average, sum, such as Aggregate etc., to apply k means clustering to it, j48, decision tree etc. Please help. Thank you
样本数据:
I just need to find a way to analyze it, to get its mean, average, sum, such as Aggregate etc., to apply k means clustering to it, j48, decision tree etc. Please help. Thank you
样本数据:
Tagged:
0
Answers
The Academy has a lot of introductory videos for the tasks you're describing:
Aggregating:https://academy.www.turtlecreekpls.com/learn/video/aggregations-pivot-intro
Clustering:https://academy.www.turtlecreekpls.com/learn/video/clustering-demo
These are just a few examples. Just enter the keyword into the search box and you will get a short tutorial that shows you how to realize the operation in RapidMiner.
How would you normalize nominal data? That's not defined.
For J.48 and other decision tree methods you need a label (or target attribute). You can use Set Role to designate an attribute as the label. All the modeling algorithms will then work.
Regards,
Balázs