Re: [Scikit-learn-general] Nesting of stratified crossvalidation

2015-10-30 Thread Andreas Mueller
Depends. If you give "fit_params" to cross_val_score it will be passed to GridSearchCV in the correct way, I believe. On 10/30/2015 06:36 AM, Christoph Sawade wrote: Thanks for the response. I am actually interested in the new DisjointLabelKFold (https://github.com/scikit-learn/scikit-learn/

Re: [Scikit-learn-general] Nesting of stratified crossvalidation

2015-10-30 Thread Christoph Sawade
Thanks for the response. I am actually interested in the new DisjointLabelKFold (https://github.com/scikit-learn/scikit-learn/pull/) which depends on an additional label. This use case seems to be not yet covered in the new sklearn.model_selection, is it? > Changes to support this case have re

Re: [Scikit-learn-general] Nesting of stratified crossvalidation

2015-10-28 Thread Joel Nothman
Changes to support this case have recently been merged into master, and an example is on its way: https://github.com/scikit-learn/scikit-learn/issues/5589 I think you should be able to run your code by importing GridSearchCV, cross_val_score and StratifiedShuffleSplit from the new sklearn.model_se

[Scikit-learn-general] Nesting of stratified crossvalidation

2015-10-28 Thread Christoph Sawade
Hey there! A general purpose in machine learning when training a model is to estimate also the performance. This is often done via cross validation. In order to tune also hyperparameters one might want to nest the crossvalidation loops into another. The sklearn framework makes that very easy. Howe