2013/9/26 Kyle Kastner <[email protected]>: > I had not thought about use inside a Pipeline - though now that you mention > it, that seems like the ideal use case for an algorithm like this. Is this > the PR you mentioned? > https://github.com/scikit-learn/scikit-learn/pull/1454
Yes but because of the limitations I mentioned about the current design of the Pipeline stuff this PR could not be written as a pipeline-able Transformer object, which makes it impossible to use as part of model evaluation and selection tools such as cross_val_score and GridSearchCV thus impeding usability. > As far as lagged features transformer - are we talking about rolling > statistics? Something similar to pandas rolling_mean, rolling_apply, etc.? Yes. -- Olivier http://twitter.com/ogrisel - http://github.com/ogrisel ------------------------------------------------------------------------------ October Webinars: Code for Performance Free Intel webinars can help you accelerate application performance. Explore tips for MPI, OpenMP, advanced profiling, and more. Get the most from the latest Intel processors and coprocessors. See abstracts and register > http://pubads.g.doubleclick.net/gampad/clk?id=60133471&iu=/4140/ostg.clktrk _______________________________________________ Scikit-learn-general mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
