2013/5/16 Joel Nothman <[email protected]>: > I notice that there are some remnants of a former scikit-learn that allowed > parameters to fit(...) other than X and y, but these have been removed in > favour of object-level parameters.
That's right. The old convention was that fit would call _set_params, then do actual training. The problem with this was that the method could fail halfway through, without signaling to the caller what exactly had failed, so we made set_params public and deprecated passing estimator parameters to fit. > Should the same be the case with transform? In particular, Pipeline and > FeatureUnion only support 1-ary transform, and any parameter that can only > be set as an additional argument to transform can't be varied in a [grid] > search. That is, >1-ary transform seems misfit to the API. Yes, preferably the same should be the case for transform. > So what non-X arguments to transform methods take? > > copy=True in various, such as feature_extraction.text.TfidfTransformer > y=None in various > ridge_alpha=None in decomposition.sparse_pca.SparsePCA > threshold=None in feature_selection.selector_mixin.SelectorMixin > pooling_func=np.mean in > cluster._feature_agglomeration.AgglomerationTransform > Y=None in pls._PLS, pls.PLSSVD > > copy is not really a problem. It's not something you want to vary in > parameter search, and although perhaps the pipeline could take advantage of > it, it's no problem. [Aside: a consistent way of telling transformers that they own whatever is passed to them could benefit pipeline performance, though I never took the time to design an API for that. Putting fake copy= arguments on all constructors or transform methods is ugly, this should be handled in TransformerMixin.] -- Lars Buitinck Scientific programmer, ILPS University of Amsterdam ------------------------------------------------------------------------------ AlienVault Unified Security Management (USM) platform delivers complete security visibility with the essential security capabilities. Easily and efficiently configure, manage, and operate all of your security controls from a single console and one unified framework. Download a free trial. http://p.sf.net/sfu/alienvault_d2d _______________________________________________ Scikit-learn-general mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
