Skip to main content
11 events
when toggle format what by license comment
Oct 2, 2018 at 7:48 comment added Ignacio Alorre @NeilSlater Perfect. It is clear now, didnt that the itnernal cross-validation splits where named itself training set and cross validation set.
Oct 2, 2018 at 7:46 comment added Neil Slater @IgnacioAlorre: Yes, I already reference k-fold cross-validation in the answer. Whether you view that as having "2 data sets" or "repeatedly splitting into train/cv sets" is just semantics - probably driven by whether you are implementing it yourself, or feeding the whole training set into a method which does it for you.
Oct 2, 2018 at 7:43 comment added Ignacio Alorre @NeilSlater Thanks for the quick reply. But there the debate is cross-validation vs test set. What I mean is use the training set for a 10-fold cross validation, and later use the test set to get some metrics over the prediction obtained. So instead of trainin set and cross validation set, as you pointed out, apply the 10 fold cross validation over the training set.
Oct 2, 2018 at 7:41 comment added Neil Slater @IgnacioAlorre: datascience.stackexchange.com/questions/18339/… - but yes you can use k-fold cross validation, which is effective but more time-consuming. I already mention that in the answer.
Oct 2, 2018 at 7:39 comment added Ignacio Alorre @NeilSlater Why three: training set, cross-validation set and test set? I though cross-validation is a technique to use over the training set. For example using a 10-fold crossvalidation, you train/test grouoing the training set into 10 different groups.
Aug 8, 2016 at 13:49 history edited Neil Slater CC BY-SA 3.0
added 496 characters in body
Aug 8, 2016 at 7:38 history edited Neil Slater CC BY-SA 3.0
added 449 characters in body
Aug 8, 2016 at 7:37 vote accept girl101
Aug 8, 2016 at 7:29 comment added girl101 @Dawny33 I have updated the question
Aug 8, 2016 at 7:23 comment added Dawny33 I'm a simple data guy. If I see a cross validation advice, I give a +1 :D
Aug 8, 2016 at 7:19 history answered Neil Slater CC BY-SA 3.0