2011/9/21 Mathieu Blondel <[email protected]>: > On Wed, Sep 21, 2011 at 6:15 PM, Olivier Grisel > <[email protected]> wrote: > >> The narrative doc of the cross validation module was not following a >> very logical order. I fixed that by introducing the motivation and >> basic usage example first and then introducing the list of all >> available cross validation strategies: > > I think that we should mention the following 2 use cases of cross-validation: > - performance evaluation when an explicit test set is not available > - hyper-parameter tuning > > It seems to me that only the 1st one is currently mentioned.
The second is mentioned at the end of the page by pointing to the next chapter on grid search. But I agree the two main use cases should be stated explicitly in the intro. -- Olivier http://twitter.com/ogrisel - http://github.com/ogrisel ------------------------------------------------------------------------------ All the data continuously generated in your IT infrastructure contains a definitive record of customers, application performance, security threats, fraudulent activity and more. Splunk takes this data and makes sense of it. Business sense. IT sense. Common sense. http://p.sf.net/sfu/splunk-d2dcopy1 _______________________________________________ Scikit-learn-general mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
