On 10/05/2015 11:30 AM, Kyle Kastner wrote: > preprocessing was done with straight numpy, and I am 90% sure there is > a more "sklearn approved" way to do it using FeatureUnion, etc. Nope, not really currently. Not nicely. ColumnTransformer is not merged yet. Also OneHotEncoder is currently not in a great shape.
Both of these can be fixed soon, though. ------------------------------------------------------------------------------ _______________________________________________ Scikit-learn-general mailing list Scikit-learn-general@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
