On Sun, Mar 24, 2013 at 7:37 AM, ShNaYkHs ShNaYkHs <shnay...@gmail.com> wrote: > Well, I need a classifier in that can support partial_fit() and can give a > probability for prediction proba_predict() (in case of multi-class, not only > binary). PassiveAggressiveClassifier and Perceptron have no proba_predict() > method, and SGDClassifier have a proba_predict() method but supported only > for binary classification.
If you use a recent version of scikit-learn, you should be able to do this: ovr = OneVsRestClassifier(SGDClassifier(loss="log")) ovr.fit(X_train, y_train) prob = ovr.predict_proba(X_test) The shape of prob will be (n_samples, n_classes). Mathieu ------------------------------------------------------------------------------ Everyone hates slow websites. So do we. Make your web apps faster with AppDynamics Download AppDynamics Lite for free today: http://p.sf.net/sfu/appdyn_d2d_mar _______________________________________________ Scikit-learn-general mailing list Scikit-learn-general@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
