Re: [Scikit-learn-general] Crossvalidation with feature selection

Or better: http://scikit-learn.org/stable/auto_examples/svm/plot_svm_anova.html 2012/11/9 Alexandre Gramfort : >> The solution is to use a Pipeline that is passed to the cross_val_score >> instead of the estimator > > yes and here is an example > > http://scikit-learn.org/0.11/auto_examples/svm/p

Re: [Scikit-learn-general] Crossvalidation with feature selection

> The solution is to use a Pipeline that is passed to the cross_val_score > instead of the estimator yes and here is an example http://scikit-learn.org/0.11/auto_examples/svm/plot_svm_anova.html Alex -- Everyone hates s

Re: [Scikit-learn-general] Crossvalidation with feature selection

I've answered my own question. The solution is to use a Pipeline that is passed to the cross_val_score instead of the estimator Matti Lyra DPhil Student Text Analytics Group Chichester 1, R203 School of Engineering and Informatics University of Sussex Brighton,

[Scikit-learn-general] Crossvalidation with feature selection

I was looking at the cross validation code for scikits (sklearn.crossvalidation.cross_val_score) and noticed that there doesn't seem to a way of doing feature selection within a cross validation loop. Is this indeed the case, or am I missing something? Matti Lyr