Stratified 10 fold cross validation on imbalanced dataset
1 view (last 30 days)
Show older comments
Hello,
I have a variable named 'Xfeat' which is of size 3816401x2 "Table" , It has 2 classes(Lables) 'hypopnea' and 'Normal' . It contains 6 features namely 'feat_mat_1' to 'feat_mat_1'
It is a hugely imbalanced dataset with number of hypopnea being so low(1:100)
Using the normal 10-fold cross validation(from classification learner app) and using RUS-boosted trees as classifier gives an accuracy around 60 percent.
People have suggested to use stratified 10-fold cross validation but I am unable to implement this in classification learner app.

I request someone familar in implementing these classifiers through code to help me implement this as a code(I am a newbie to coding)
Here's the link to the file https://drive.google.com/file/d/1p3_hYuTyX2_5HNunX9NmrIKOFKsIiBfR/view?usp=sharing
And this would also help many newbies like me on the internet as well as there are very few discussions on this topic and I also thank matlab community for being so quick to respond to my previous questions
Thank you
1 Comment
Yaser Awadh
on 7 Dec 2022
Hi, Could you please share with me the code. I have tried to download frm GD, but I could'nt.
Thank you
Answers (0)
See Also
Categories
Find more on Statistics and Machine Learning Toolbox in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!