def generate_dataset(d, k, mode, nframes): """Generate a dataset useful for EM anf GMM testing. returns: data : ndarray data from the true model. tgm : GM the true model (randomly generated) gm0 : GM the initial model gm : GM the trained model """ # Generate a model w, mu, va = GM.gen_param(d, k, mode, spread=2.0) tgm = GM.fromvalues(w, mu, va) # Generate data from the model data = tgm.sample(nframes) # Run EM on the model, by running the initialization separetely. gmm = GMM(GM(d, k, mode), 'test') gmm.init_random(data) gm0 = copy.copy(gmm.gm) gmm = GMM(copy.copy(gmm.gm), 'test') em = EM() em.train(data, gmm) return data, tgm, gm0, gmm.gm
def cluster(data, k, mode='full'): d = data.shape[1] gm = GM(d, k, mode) gmm = GMM(gm) em = EM() em.train(data, gmm, maxiter=20) return gm
def cluster(data, k, mode = 'full'): d = data.shape[1] gm = GM(d, k, mode) gmm = GMM(gm) em = EM() em.train(data, gmm, maxiter = 20) return gm, gmm.bic(data)
def cluster(data, k): d = data.shape[1] gm = GM(d, k) gmm = GMM(gm) em = EM() em.train(data, gmm, maxiter=20) return gm, gmm.bic(data)
def _create_model_and_run_em(self, d, k, mode, nframes): #+++++++++++++++++++++++++++++++++++++++++++++++++ # Generate a model with k components, d dimensions #+++++++++++++++++++++++++++++++++++++++++++++++++ w, mu, va = GM.gen_param(d, k, mode, spread = 1.5) gm = GM.fromvalues(w, mu, va) # Sample nframes frames from the model data = gm.sample(nframes) #++++++++++++++++++++++++++++++++++++++++++ # Approximate the models with classical EM #++++++++++++++++++++++++++++++++++++++++++ # Init the model lgm = GM(d, k, mode) gmm = GMM(lgm, 'kmean') em = EM() lk = em.train(data, gmm)
k = 2 d = 2 mode = 'diag' nframes = 1e3 #+++++++++++++++++++++++++++++++++++++++++++ # Create an artificial GM model, samples it #+++++++++++++++++++++++++++++++++++++++++++ w, mu, va = GM.gen_param(d, k, mode, spread = 1.5) gm = GM.fromvalues(w, mu, va) # Sample nframes frames from the model data = gm.sample(nframes) #++++++++++++++++++++++++ # Learn the model with EM #++++++++++++++++++++++++ # Create a Model from a Gaussian mixture with kmean initialization lgm = GM(d, k, mode) gmm = GMM(lgm, 'kmean') # The actual EM, with likelihood computation. The threshold # is compared to the (linearly appromixated) derivative of the likelihood em = EM() like = em.train(data, gmm, maxiter = 30, thresh = 1e-8) # The computed parameters are in gmm.gm, which is the same than lgm # (remember, python does not copy most objects by default). You can for example # plot lgm against gm to compare
data = gm.sample(nframes) #++++++++++++++++++++++++ # Learn the model with EM #++++++++++++++++++++++++ # List of learned mixtures lgm[i] is a mixture with i+1 components lgm = [] kmax = 6 bics = N.zeros(kmax) em = EM() for i in range(kmax): lgm.append(GM(d, i+1, mode)) gmm = GMM(lgm[i], 'kmean') em.train(data, gmm, maxiter = 30, thresh = 1e-10) bics[i] = gmm.bic(data) print "Original model has %d clusters, bics says %d" % (k, N.argmax(bics)+1) #+++++++++++++++ # Draw the model #+++++++++++++++ import pylab as P P.subplot(3, 2, 1) for k in range(kmax): P.subplot(3, 2, k+1) level = 0.9 P.plot(data[:, 0], data[:, 1], '.', label = '_nolegend_')