2011/11/6 Lars Buitinck <[email protected]>: > 2011/11/6 Sami Liedes <[email protected]>: >> clf = GridSearchCV(svm.sparse.SVC(C=1), TUNED_PARAMS, n_jobs=10) >> clf.fit(tf, tc, cv=StratifiedKFold(tc, 5, indices=True)) > > Reproduced with a much smaller set of TUNED_PARAMS. With n_jobs=1, the > problem does not occur. > > One solution is to clone(best_estimator) at grid_search.py, before > line 341 (in the if self.refit block). Currently, the code assumes > that a fit estimator can simply be re-fit on a new dataset, which is > not true of sparse SVMs due to the ndarray.resize calls (and probably > not of my NB estimators either, since I hadn't considered this > possibility).
The fit contract is that it can be called several times and that the results of previous calls are forgotten. Warm restart should be handled explicitly with a specific constructor parameter if required. Alternatively one should implement partial_fit for incremental learning. -- Olivier http://twitter.com/ogrisel - http://github.com/ogrisel ------------------------------------------------------------------------------ RSA(R) Conference 2012 Save $700 by Nov 18 Register now http://p.sf.net/sfu/rsa-sfdev2dev1 _______________________________________________ Scikit-learn-general mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
