return np.sum(topiclib.partial_slda_local_elbo(v.labeled[d], v.y[d], v.alphaL, v.beta[-v.Kl:], v.gammaL[d], v.phiL[d], v.eta, v.sigma_squared) for d in xrange(len(v.labeled))) run_tlc = partial(graphlib.run_variational_em, e_step_func=tlc_e_step, m_step_func=tlc_m_step, global_elbo_func=tlc_global_elbo, print_func=tlc_print_func) if __name__=='__main__': dirname = 'synthtlc' dirname = 'synthbig' # use my tlc synthetically generated dataset documents = topiclib.read_sparse(dirname + '/documents.dat') comments = topiclib.read_sparse(dirname + '/comments.dat') labeled_documents = topiclib.read_sparse(dirname + '/labeled.dat') background = topiclib.read_sparse(dirname + '/background.dat') y = np.loadtxt(dirname + '/yL.npy') real_data = (documents, comments, labeled_documents, background, y) var = TLCVars(real_data, Ku=29, Ks=5, Kb=24) try: output = run_tlc(var) except Exception,e: print e import pdb; pdb.post_mortem()
[ 1.7, 2.0, 1.2, 4.8, 5, 4.2, ]) #var = SupervisedLDAVars(test_data, K=3) #var = SupervisedLDAVars(noisy_test_data, K=3) # use my big generated dataset n = 9994 labeled_documents = topiclib.read_sparse('data/synthbigtlc/labeled.dat')[:100] y = np.loadtxt('data/synthbigtlc/yL.npy')[:100] real_data = (labeled_documents, y) var = PartialSupervisedLDAVars(real_data, Ks=5, Kb=20) try: output = run_partial_slda(var) except Exception,e: print e import pdb; pdb.post_mortem()
[(5,2), (6,1), (8,1), (9,1),], ], [ 1.7, 2.0, 1.2, 4.8, 5, 4.2, ]) #var = SupervisedLDAVars(test_data, K=3) #var = SupervisedLDAVars(noisy_test_data, K=3) # use my big generated dataset labeled_documents = topiclib.read_sparse('synthtlc/labeled.dat') y = np.loadtxt('synthtlc/yL.npy') real_data = (labeled_documents, y) var = SupervisedLDAVars(real_data, K=13) try: output = run_slda(var) except Exception,e: print e import pdb; pdb.post_mortem()