Hello guys, some basic issue here with multi dimensional scaling: mds = manifold.MDS(n_components=3, max_iter=10000, eps=0.0001, n_jobs=4,dissimilarity='precomputed') similarities1 = euclidean_distances(sub_corpus) similarities2 = scipy.spatial.distance_matrix(sub_corpus,sub_corpus)
print numpy.setdiff1d(similarities1,similarities2) # WOW BIG DIFF HERE [ 1.19603996e-03 5.81854256e-03 1.54755116e-02 ..., 2.01659846e+00 2.02083683e+00 2.03397322e+00] pos_3D = mds.fit(similarities).embedding_ The euclidean distance always give me a: ValueError: similarities must be symmetric whereas the scipy distance works fine. Is it due to some sort of compile issue? I can see differences in the decimal places even for say 2 samples! ------------------------------------------------------------------------------ DreamFactory - Open Source REST & JSON Services for HTML5 & Native Apps OAuth, Users, Roles, SQL, NoSQL, BLOB Storage and External API Access Free app hosting. Or install the open source package on any LAMP server. Sign up and see examples for AngularJS, jQuery, Sencha Touch and Native! http://pubads.g.doubleclick.net/gampad/clk?id=63469471&iu=/4140/ostg.clktrk _______________________________________________ Scikit-learn-general mailing list Scikit-learn-general@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
