Forum Jar
Forum Jar : RapidMiner Forum : Text analysis
See other topics in RapidMiner Forum

RapidMiner Forum
Important rules for using RapidMiner Forum
• No offensive words are allowed in this forum.
• To prevent spams, you must not use the words "http" ".com" or "/"(slashes) in this forum.

Alert! Please do not buy anything or pay anyone on this forum. Scammers have been reported on our forum. Please also do not go to any links posted on here. We have been reported about links to websites that contain viruses. Thank you.

Topic: Text analysis
Hey guys,

We want to do a binary classification on a text data set with the distribution 80% negative class, 20% positive class. In order to reach maximum statistical meaningfulness, we want to do so by using 10-fold cross validation.

If we model this within Rapidminer, we are unsuccessful since it doesn’t output any statistical metrics (like precision, recall, etc).

We found a workaround that works, but it doesn’t make any sense out of a ML perspective: If we first divide into training or test and then use 10-fold-crossvalidation it works — But the training or test split should be part of the crossvaligdation (9 training folds, 1 test fold, 10 iterations). So right now the only way to get this working is by FIRST dividing into test and training and THEN use X-Validation. Did we model it the right way or did we miss anything?

If you need any more information for helping us, just comment.

Best regards!

by Thiemo Thu Dec 01 11:22:50 UTC 2016
Post a new comment

Name (optional):

By posting a comment, you indicate that you have agreed to our terms of use.

Feel adventurous? Check out random forums on Forum Jar!
Related Forums
Machine learning Forum
Data mining Forum
XML Forum
Graphical user interface Forum
Dortmund University of Technology Forum
GNU Forum
SourceForge Forum
Java (programming language) Forum
Weka (machine learning) Forum
Knowledge discovery Forum
Command line Forum
Batch file Forum
Java API Forum
Plugin Forum
Extension (computing) Forum
Plotting Forum
Text mining Forum

sponsored links: free polls | free chat rooms (weirdtown chat) | widgets for myspace | make chat room | free chat room list | review websites | toy dj | chat vocab

terms of use | privacy policy
©2018 All rights reserved.